Holo1-7B-GGUF

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

import json
import os
from typing import Any, Literal

from transformers import AutoModelForImageTextToText, AutoProcessor

# default: Load the model on the available device(s)
# We recommend enabling flash_attention_2 for better acceleration and memory saving.
model = AutoModelForImageTextToText.from_pretrained(
    "Hcompany/Holo1-7B",
    torch_dtype="auto",
    # torch_dtype=torch.bfloat16,
    # attn_implementation="flash_attention_2",
    device_map="auto",
)

# default processor
processor = AutoProcessor.from_pretrained("Hcompany/Holo1-7B")
# The default range for the number of visual tokens per image in the model is 4-1280.
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
# processor = AutoProcessor.from_pretrained(model_dir, min_pixels=min_pixels, max_pixels=max_pixels)

# Helper function to run inference
def run_inference(messages: list[dict[str, Any]]) -> str:
    # Preparation for inference
    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    inputs = processor(
        text=[text],
        images=image,
        padding=True,
        return_tensors="pt",
    )
    inputs = inputs.to("cuda")

    generated_ids = model.generate(**inputs, max_new_tokens=128)
    generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
    return processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

from PIL import Image
from transformers.models.qwen2_vl.image_processing_qwen2_vl import smart_resize
import requests

# Prepare image and instruction
image_url = "https://huggingface.co/Hcompany/Holo1-7B/resolve/main/calendar_example.jpg" 
image = Image.open(requests.get(image_url, stream=True).raw)

# Resize the image so that predicted absolute coordinates match the size of the image.
image_processor = processor.image_processor
resized_height, resized_width = smart_resize(
    image.height,
    image.width,
    factor=image_processor.patch_size * image_processor.merge_size,
    min_pixels=image_processor.min_pixels,
    max_pixels=image_processor.max_pixels,
)
image = image.resize(size=(resized_width, resized_height), resample=None)  # type: ignore

instruction = "Select July 14th as the check-out date"

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

def get_localization_prompt(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position as Click(x, y) with x num pixels from the left edge and y num pixels from the top edge."

    return [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        }
    ]


messages = get_localization_prompt(image, instruction)
coordinates_str = run_inference(messages)[0]
print(coordinates_str)
# Expected Click(352, 348)

from pydantic import BaseModel, ConfigDict

class FunctionDefinition(BaseModel):
    """Function definition data structure.

    Attributes:
        name: name of the function.
        description: description of the function.
        parameters: JSON schema for the function parameters.
        strict: Whether to enable strict schema adherence when generating the function call.
    """

    name: str
    description: str = ""
    parameters: dict[str, Any] = {}
    strict: bool = True


class ClickAction(BaseModel):
    """Click at specific coordinates on the screen."""

    model_config = ConfigDict(
        extra="forbid",
        json_schema_serialization_defaults_required=True,
        json_schema_mode_override="serialization",
        use_attribute_docstrings=True,
    )

    action: Literal["click"] = "click"
    x: int
    """The x coordinate, number of pixels from the left edge."""
    y: int
    """The y coordinate, number of pixels from the top edge."""


function_definition = FunctionDefinition(
    name="click_action",
    description=ClickAction.__doc__ or "",
    parameters=ClickAction.model_json_schema(),
    strict=True,
)


def get_localization_prompt_structured_output(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position. You must output a valid JSON format."

    return [
        {
            "role": "system",
            "content": json.dumps([function_definition.model_dump()]),
        },
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        },
    ]


messages = get_localization_prompt_structured_output(image, instruction)
coordinates_str = run_inference(messages)[0]
coordinates = ClickAction.model_validate(json.loads(coordinates_str)["arguments"])
print(coordinates)
# Expected ClickAction(action='click', x=352, y=340)

from pydantic import BaseModel, ConfigDict

class FunctionDefinition(BaseModel):
    """Function definition data structure.

    Attributes:
        name: name of the function.
        description: description of the function.
        parameters: JSON schema for the function parameters.
        strict: Whether to enable strict schema adherence when generating the function call.
    """

    name: str
    description: str = ""
    parameters: dict[str, Any] = {}
    strict: bool = True


class ClickAction(BaseModel):
    """Click at specific coordinates on the screen."""

    model_config = ConfigDict(
        extra="forbid",
        json_schema_serialization_defaults_required=True,
        json_schema_mode_override="serialization",
        use_attribute_docstrings=True,
    )

    action: Literal["click"] = "click"
    x: int
    """The x coordinate, number of pixels from the left edge."""
    y: int
    """The y coordinate, number of pixels from the top edge."""


function_definition = FunctionDefinition(
    name="click_action",
    description=ClickAction.__doc__ or "",
    parameters=ClickAction.model_json_schema(),
    strict=True,
)


def get_localization_prompt_structured_output(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position. You must output a valid JSON format."

    return [
        {
            "role": "system",
            "content": json.dumps([function_definition.model_dump()]),
        },
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        },
    ]


messages = get_localization_prompt_structured_output(image, instruction)
coordinates_str = run_inference(messages)[0]
coordinates = ClickAction.model_validate(json.loads(coordinates_str)["arguments"])
print(coordinates)
# Expected ClickAction(action='click', x=352, y=340)

from pydantic import BaseModel, ConfigDict

class FunctionDefinition(BaseModel):
    """Function definition data structure.

    Attributes:
        name: name of the function.
        description: description of the function.
        parameters: JSON schema for the function parameters.
        strict: Whether to enable strict schema adherence when generating the function call.
    """

    name: str
    description: str = ""
    parameters: dict[str, Any] = {}
    strict: bool = True


class ClickAction(BaseModel):
    """Click at specific coordinates on the screen."""

    model_config = ConfigDict(
        extra="forbid",
        json_schema_serialization_defaults_required=True,
        json_schema_mode_override="serialization",
        use_attribute_docstrings=True,
    )

    action: Literal["click"] = "click"
    x: int
    """The x coordinate, number of pixels from the left edge."""
    y: int
    """The y coordinate, number of pixels from the top edge."""


function_definition = FunctionDefinition(
    name="click_action",
    description=ClickAction.__doc__ or "",
    parameters=ClickAction.model_json_schema(),
    strict=True,
)


def get_localization_prompt_structured_output(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position. You must output a valid JSON format."

    return [
        {
            "role": "system",
            "content": json.dumps([function_definition.model_dump()]),
        },
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        },
    ]


messages = get_localization_prompt_structured_output(image, instruction)
coordinates_str = run_inference(messages)[0]
coordinates = ClickAction.model_validate(json.loads(coordinates_str)["arguments"])
print(coordinates)
# Expected ClickAction(action='click', x=352, y=340)

from pydantic import BaseModel, ConfigDict

class FunctionDefinition(BaseModel):
    """Function definition data structure.

    Attributes:
        name: name of the function.
        description: description of the function.
        parameters: JSON schema for the function parameters.
        strict: Whether to enable strict schema adherence when generating the function call.
    """

    name: str
    description: str = ""
    parameters: dict[str, Any] = {}
    strict: bool = True


class ClickAction(BaseModel):
    """Click at specific coordinates on the screen."""

    model_config = ConfigDict(
        extra="forbid",
        json_schema_serialization_defaults_required=True,
        json_schema_mode_override="serialization",
        use_attribute_docstrings=True,
    )

    action: Literal["click"] = "click"
    x: int
    """The x coordinate, number of pixels from the left edge."""
    y: int
    """The y coordinate, number of pixels from the top edge."""


function_definition = FunctionDefinition(
    name="click_action",
    description=ClickAction.__doc__ or "",
    parameters=ClickAction.model_json_schema(),
    strict=True,
)


def get_localization_prompt_structured_output(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position. You must output a valid JSON format."

    return [
        {
            "role": "system",
            "content": json.dumps([function_definition.model_dump()]),
        },
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        },
    ]


messages = get_localization_prompt_structured_output(image, instruction)
coordinates_str = run_inference(messages)[0]
coordinates = ClickAction.model_validate(json.loads(coordinates_str)["arguments"])
print(coordinates)
# Expected ClickAction(action='click', x=352, y=340)

from pydantic import BaseModel, ConfigDict

class FunctionDefinition(BaseModel):
    """Function definition data structure.

    Attributes:
        name: name of the function.
        description: description of the function.
        parameters: JSON schema for the function parameters.
        strict: Whether to enable strict schema adherence when generating the function call.
    """

    name: str
    description: str = ""
    parameters: dict[str, Any] = {}
    strict: bool = True


class ClickAction(BaseModel):
    """Click at specific coordinates on the screen."""

    model_config = ConfigDict(
        extra="forbid",
        json_schema_serialization_defaults_required=True,
        json_schema_mode_override="serialization",
        use_attribute_docstrings=True,
    )

    action: Literal["click"] = "click"
    x: int
    """The x coordinate, number of pixels from the left edge."""
    y: int
    """The y coordinate, number of pixels from the top edge."""


function_definition = FunctionDefinition(
    name="click_action",
    description=ClickAction.__doc__ or "",
    parameters=ClickAction.model_json_schema(),
    strict=True,
)


def get_localization_prompt_structured_output(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position. You must output a valid JSON format."

    return [
        {
            "role": "system",
            "content": json.dumps([function_definition.model_dump()]),
        },
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        },
    ]


messages = get_localization_prompt_structured_output(image, instruction)
coordinates_str = run_inference(messages)[0]
coordinates = ClickAction.model_validate(json.loads(coordinates_str)["arguments"])
print(coordinates)
# Expected ClickAction(action='click', x=352, y=340)

from pydantic import BaseModel, ConfigDict

class FunctionDefinition(BaseModel):
    """Function definition data structure.

    Attributes:
        name: name of the function.
        description: description of the function.
        parameters: JSON schema for the function parameters.
        strict: Whether to enable strict schema adherence when generating the function call.
    """

    name: str
    description: str = ""
    parameters: dict[str, Any] = {}
    strict: bool = True


class ClickAction(BaseModel):
    """Click at specific coordinates on the screen."""

    model_config = ConfigDict(
        extra="forbid",
        json_schema_serialization_defaults_required=True,
        json_schema_mode_override="serialization",
        use_attribute_docstrings=True,
    )

    action: Literal["click"] = "click"
    x: int
    """The x coordinate, number of pixels from the left edge."""
    y: int
    """The y coordinate, number of pixels from the top edge."""


function_definition = FunctionDefinition(
    name="click_action",
    description=ClickAction.__doc__ or "",
    parameters=ClickAction.model_json_schema(),
    strict=True,
)


def get_localization_prompt_structured_output(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position. You must output a valid JSON format."

    return [
        {
            "role": "system",
            "content": json.dumps([function_definition.model_dump()]),
        },
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        },
    ]


messages = get_localization_prompt_structured_output(image, instruction)
coordinates_str = run_inference(messages)[0]
coordinates = ClickAction.model_validate(json.loads(coordinates_str)["arguments"])
print(coordinates)
# Expected ClickAction(action='click', x=352, y=340)

from pydantic import BaseModel, ConfigDict

class FunctionDefinition(BaseModel):
    """Function definition data structure.

    Attributes:
        name: name of the function.
        description: description of the function.
        parameters: JSON schema for the function parameters.
        strict: Whether to enable strict schema adherence when generating the function call.
    """

    name: str
    description: str = ""
    parameters: dict[str, Any] = {}
    strict: bool = True


class ClickAction(BaseModel):
    """Click at specific coordinates on the screen."""

    model_config = ConfigDict(
        extra="forbid",
        json_schema_serialization_defaults_required=True,
        json_schema_mode_override="serialization",
        use_attribute_docstrings=True,
    )

    action: Literal["click"] = "click"
    x: int
    """The x coordinate, number of pixels from the left edge."""
    y: int
    """The y coordinate, number of pixels from the top edge."""


function_definition = FunctionDefinition(
    name="click_action",
    description=ClickAction.__doc__ or "",
    parameters=ClickAction.model_json_schema(),
    strict=True,
)


def get_localization_prompt_structured_output(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position. You must output a valid JSON format."

    return [
        {
            "role": "system",
            "content": json.dumps([function_definition.model_dump()]),
        },
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        },
    ]


messages = get_localization_prompt_structured_output(image, instruction)
coordinates_str = run_inference(messages)[0]
coordinates = ClickAction.model_validate(json.loads(coordinates_str)["arguments"])
print(coordinates)
# Expected ClickAction(action='click', x=352, y=340)

from pydantic import BaseModel, ConfigDict

class FunctionDefinition(BaseModel):
    """Function definition data structure.

    Attributes:
        name: name of the function.
        description: description of the function.
        parameters: JSON schema for the function parameters.
        strict: Whether to enable strict schema adherence when generating the function call.
    """

    name: str
    description: str = ""
    parameters: dict[str, Any] = {}
    strict: bool = True


class ClickAction(BaseModel):
    """Click at specific coordinates on the screen."""

    model_config = ConfigDict(
        extra="forbid",
        json_schema_serialization_defaults_required=True,
        json_schema_mode_override="serialization",
        use_attribute_docstrings=True,
    )

    action: Literal["click"] = "click"
    x: int
    """The x coordinate, number of pixels from the left edge."""
    y: int
    """The y coordinate, number of pixels from the top edge."""


function_definition = FunctionDefinition(
    name="click_action",
    description=ClickAction.__doc__ or "",
    parameters=ClickAction.model_json_schema(),
    strict=True,
)


def get_localization_prompt_structured_output(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position. You must output a valid JSON format."

    return [
        {
            "role": "system",
            "content": json.dumps([function_definition.model_dump()]),
        },
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        },
    ]


messages = get_localization_prompt_structured_output(image, instruction)
coordinates_str = run_inference(messages)[0]
coordinates = ClickAction.model_validate(json.loads(coordinates_str)["arguments"])
print(coordinates)
# Expected ClickAction(action='click', x=352, y=340)

from pydantic import BaseModel, ConfigDict

class FunctionDefinition(BaseModel):
    """Function definition data structure.

    Attributes:
        name: name of the function.
        description: description of the function.
        parameters: JSON schema for the function parameters.
        strict: Whether to enable strict schema adherence when generating the function call.
    """

    name: str
    description: str = ""
    parameters: dict[str, Any] = {}
    strict: bool = True


class ClickAction(BaseModel):
    """Click at specific coordinates on the screen."""

    model_config = ConfigDict(
        extra="forbid",
        json_schema_serialization_defaults_required=True,
        json_schema_mode_override="serialization",
        use_attribute_docstrings=True,
    )

    action: Literal["click"] = "click"
    x: int
    """The x coordinate, number of pixels from the left edge."""
    y: int
    """The y coordinate, number of pixels from the top edge."""


function_definition = FunctionDefinition(
    name="click_action",
    description=ClickAction.__doc__ or "",
    parameters=ClickAction.model_json_schema(),
    strict=True,
)


def get_localization_prompt_structured_output(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position. You must output a valid JSON format."

    return [
        {
            "role": "system",
            "content": json.dumps([function_definition.model_dump()]),
        },
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        },
    ]


messages = get_localization_prompt_structured_output(image, instruction)
coordinates_str = run_inference(messages)[0]
coordinates = ClickAction.model_validate(json.loads(coordinates_str)["arguments"])
print(coordinates)
# Expected ClickAction(action='click', x=352, y=340)

from pydantic import BaseModel, ConfigDict

class FunctionDefinition(BaseModel):
    """Function definition data structure.

    Attributes:
        name: name of the function.
        description: description of the function.
        parameters: JSON schema for the function parameters.
        strict: Whether to enable strict schema adherence when generating the function call.
    """

    name: str
    description: str = ""
    parameters: dict[str, Any] = {}
    strict: bool = True


class ClickAction(BaseModel):
    """Click at specific coordinates on the screen."""

    model_config = ConfigDict(
        extra="forbid",
        json_schema_serialization_defaults_required=True,
        json_schema_mode_override="serialization",
        use_attribute_docstrings=True,
    )

    action: Literal["click"] = "click"
    x: int
    """The x coordinate, number of pixels from the left edge."""
    y: int
    """The y coordinate, number of pixels from the top edge."""


function_definition = FunctionDefinition(
    name="click_action",
    description=ClickAction.__doc__ or "",
    parameters=ClickAction.model_json_schema(),
    strict=True,
)


def get_localization_prompt_structured_output(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position. You must output a valid JSON format."

    return [
        {
            "role": "system",
            "content": json.dumps([function_definition.model_dump()]),
        },
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        },
    ]


messages = get_localization_prompt_structured_output(image, instruction)
coordinates_str = run_inference(messages)[0]
coordinates = ClickAction.model_validate(json.loads(coordinates_str)["arguments"])
print(coordinates)
# Expected ClickAction(action='click', x=352, y=340)

from pydantic import BaseModel, ConfigDict

class FunctionDefinition(BaseModel):
    """Function definition data structure.

    Attributes:
        name: name of the function.
        description: description of the function.
        parameters: JSON schema for the function parameters.
        strict: Whether to enable strict schema adherence when generating the function call.
    """

    name: str
    description: str = ""
    parameters: dict[str, Any] = {}
    strict: bool = True


class ClickAction(BaseModel):
    """Click at specific coordinates on the screen."""

    model_config = ConfigDict(
        extra="forbid",
        json_schema_serialization_defaults_required=True,
        json_schema_mode_override="serialization",
        use_attribute_docstrings=True,
    )

    action: Literal["click"] = "click"
    x: int
    """The x coordinate, number of pixels from the left edge."""
    y: int
    """The y coordinate, number of pixels from the top edge."""


function_definition = FunctionDefinition(
    name="click_action",
    description=ClickAction.__doc__ or "",
    parameters=ClickAction.model_json_schema(),
    strict=True,
)


def get_localization_prompt_structured_output(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position. You must output a valid JSON format."

    return [
        {
            "role": "system",
            "content": json.dumps([function_definition.model_dump()]),
        },
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        },
    ]


messages = get_localization_prompt_structured_output(image, instruction)
coordinates_str = run_inference(messages)[0]
coordinates = ClickAction.model_validate(json.loads(coordinates_str)["arguments"])
print(coordinates)
# Expected ClickAction(action='click', x=352, y=340)

from pydantic import BaseModel, ConfigDict

class FunctionDefinition(BaseModel):
    """Function definition data structure.

    Attributes:
        name: name of the function.
        description: description of the function.
        parameters: JSON schema for the function parameters.
        strict: Whether to enable strict schema adherence when generating the function call.
    """

    name: str
    description: str = ""
    parameters: dict[str, Any] = {}
    strict: bool = True


class ClickAction(BaseModel):
    """Click at specific coordinates on the screen."""

    model_config = ConfigDict(
        extra="forbid",
        json_schema_serialization_defaults_required=True,
        json_schema_mode_override="serialization",
        use_attribute_docstrings=True,
    )

    action: Literal["click"] = "click"
    x: int
    """The x coordinate, number of pixels from the left edge."""
    y: int
    """The y coordinate, number of pixels from the top edge."""


function_definition = FunctionDefinition(
    name="click_action",
    description=ClickAction.__doc__ or "",
    parameters=ClickAction.model_json_schema(),
    strict=True,
)


def get_localization_prompt_structured_output(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position. You must output a valid JSON format."

    return [
        {
            "role": "system",
            "content": json.dumps([function_definition.model_dump()]),
        },
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        },
    ]


messages = get_localization_prompt_structured_output(image, instruction)
coordinates_str = run_inference(messages)[0]
coordinates = ClickAction.model_validate(json.loads(coordinates_str)["arguments"])
print(coordinates)
# Expected ClickAction(action='click', x=352, y=340)

from pydantic import BaseModel, ConfigDict

class FunctionDefinition(BaseModel):
    """Function definition data structure.

    Attributes:
        name: name of the function.
        description: description of the function.
        parameters: JSON schema for the function parameters.
        strict: Whether to enable strict schema adherence when generating the function call.
    """

    name: str
    description: str = ""
    parameters: dict[str, Any] = {}
    strict: bool = True


class ClickAction(BaseModel):
    """Click at specific coordinates on the screen."""

    model_config = ConfigDict(
        extra="forbid",
        json_schema_serialization_defaults_required=True,
        json_schema_mode_override="serialization",
        use_attribute_docstrings=True,
    )

    action: Literal["click"] = "click"
    x: int
    """The x coordinate, number of pixels from the left edge."""
    y: int
    """The y coordinate, number of pixels from the top edge."""


function_definition = FunctionDefinition(
    name="click_action",
    description=ClickAction.__doc__ or "",
    parameters=ClickAction.model_json_schema(),
    strict=True,
)


def get_localization_prompt_structured_output(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position. You must output a valid JSON format."

    return [
        {
            "role": "system",
            "content": json.dumps([function_definition.model_dump()]),
        },
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        },
    ]


messages = get_localization_prompt_structured_output(image, instruction)
coordinates_str = run_inference(messages)[0]
coordinates = ClickAction.model_validate(json.loads(coordinates_str)["arguments"])
print(coordinates)
# Expected ClickAction(action='click', x=352, y=340)

from pydantic import BaseModel, ConfigDict

class FunctionDefinition(BaseModel):
    """Function definition data structure.

    Attributes:
        name: name of the function.
        description: description of the function.
        parameters: JSON schema for the function parameters.
        strict: Whether to enable strict schema adherence when generating the function call.
    """

    name: str
    description: str = ""
    parameters: dict[str, Any] = {}
    strict: bool = True


class ClickAction(BaseModel):
    """Click at specific coordinates on the screen."""

    model_config = ConfigDict(
        extra="forbid",
        json_schema_serialization_defaults_required=True,
        json_schema_mode_override="serialization",
        use_attribute_docstrings=True,
    )

    action: Literal["click"] = "click"
    x: int
    """The x coordinate, number of pixels from the left edge."""
    y: int
    """The y coordinate, number of pixels from the top edge."""


function_definition = FunctionDefinition(
    name="click_action",
    description=ClickAction.__doc__ or "",
    parameters=ClickAction.model_json_schema(),
    strict=True,
)


def get_localization_prompt_structured_output(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position. You must output a valid JSON format."

    return [
        {
            "role": "system",
            "content": json.dumps([function_definition.model_dump()]),
        },
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        },
    ]


messages = get_localization_prompt_structured_output(image, instruction)
coordinates_str = run_inference(messages)[0]
coordinates = ClickAction.model_validate(json.loads(coordinates_str)["arguments"])
print(coordinates)
# Expected ClickAction(action='click', x=352, y=340)

from pydantic import BaseModel, ConfigDict

class FunctionDefinition(BaseModel):
    """Function definition data structure.

    Attributes:
        name: name of the function.
        description: description of the function.
        parameters: JSON schema for the function parameters.
        strict: Whether to enable strict schema adherence when generating the function call.
    """

    name: str
    description: str = ""
    parameters: dict[str, Any] = {}
    strict: bool = True


class ClickAction(BaseModel):
    """Click at specific coordinates on the screen."""

    model_config = ConfigDict(
        extra="forbid",
        json_schema_serialization_defaults_required=True,
        json_schema_mode_override="serialization",
        use_attribute_docstrings=True,
    )

    action: Literal["click"] = "click"
    x: int
    """The x coordinate, number of pixels from the left edge."""
    y: int
    """The y coordinate, number of pixels from the top edge."""


function_definition = FunctionDefinition(
    name="click_action",
    description=ClickAction.__doc__ or "",
    parameters=ClickAction.model_json_schema(),
    strict=True,
)


def get_localization_prompt_structured_output(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position. You must output a valid JSON format."

    return [
        {
            "role": "system",
            "content": json.dumps([function_definition.model_dump()]),
        },
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        },
    ]


messages = get_localization_prompt_structured_output(image, instruction)
coordinates_str = run_inference(messages)[0]
coordinates = ClickAction.model_validate(json.loads(coordinates_str)["arguments"])
print(coordinates)
# Expected ClickAction(action='click', x=352, y=340)

from pydantic import BaseModel, ConfigDict

class FunctionDefinition(BaseModel):
    """Function definition data structure.

    Attributes:
        name: name of the function.
        description: description of the function.
        parameters: JSON schema for the function parameters.
        strict: Whether to enable strict schema adherence when generating the function call.
    """

    name: str
    description: str = ""
    parameters: dict[str, Any] = {}
    strict: bool = True


class ClickAction(BaseModel):
    """Click at specific coordinates on the screen."""

    model_config = ConfigDict(
        extra="forbid",
        json_schema_serialization_defaults_required=True,
        json_schema_mode_override="serialization",
        use_attribute_docstrings=True,
    )

    action: Literal["click"] = "click"
    x: int
    """The x coordinate, number of pixels from the left edge."""
    y: int
    """The y coordinate, number of pixels from the top edge."""


function_definition = FunctionDefinition(
    name="click_action",
    description=ClickAction.__doc__ or "",
    parameters=ClickAction.model_json_schema(),
    strict=True,
)


def get_localization_prompt_structured_output(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position. You must output a valid JSON format."

    return [
        {
            "role": "system",
            "content": json.dumps([function_definition.model_dump()]),
        },
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        },
    ]


messages = get_localization_prompt_structured_output(image, instruction)
coordinates_str = run_inference(messages)[0]
coordinates = ClickAction.model_validate(json.loads(coordinates_str)["arguments"])
print(coordinates)
# Expected ClickAction(action='click', x=352, y=340)

from pydantic import BaseModel, ConfigDict

class FunctionDefinition(BaseModel):
    """Function definition data structure.

    Attributes:
        name: name of the function.
        description: description of the function.
        parameters: JSON schema for the function parameters.
        strict: Whether to enable strict schema adherence when generating the function call.
    """

    name: str
    description: str = ""
    parameters: dict[str, Any] = {}
    strict: bool = True


class ClickAction(BaseModel):
    """Click at specific coordinates on the screen."""

    model_config = ConfigDict(
        extra="forbid",
        json_schema_serialization_defaults_required=True,
        json_schema_mode_override="serialization",
        use_attribute_docstrings=True,
    )

    action: Literal["click"] = "click"
    x: int
    """The x coordinate, number of pixels from the left edge."""
    y: int
    """The y coordinate, number of pixels from the top edge."""


function_definition = FunctionDefinition(
    name="click_action",
    description=ClickAction.__doc__ or "",
    parameters=ClickAction.model_json_schema(),
    strict=True,
)


def get_localization_prompt_structured_output(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position. You must output a valid JSON format."

    return [
        {
            "role": "system",
            "content": json.dumps([function_definition.model_dump()]),
        },
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        },
    ]


messages = get_localization_prompt_structured_output(image, instruction)
coordinates_str = run_inference(messages)[0]
coordinates = ClickAction.model_validate(json.loads(coordinates_str)["arguments"])
print(coordinates)
# Expected ClickAction(action='click', x=352, y=340)

from pydantic import BaseModel, ConfigDict

class FunctionDefinition(BaseModel):
    """Function definition data structure.

    Attributes:
        name: name of the function.
        description: description of the function.
        parameters: JSON schema for the function parameters.
        strict: Whether to enable strict schema adherence when generating the function call.
    """

    name: str
    description: str = ""
    parameters: dict[str, Any] = {}
    strict: bool = True


class ClickAction(BaseModel):
    """Click at specific coordinates on the screen."""

    model_config = ConfigDict(
        extra="forbid",
        json_schema_serialization_defaults_required=True,
        json_schema_mode_override="serialization",
        use_attribute_docstrings=True,
    )

    action: Literal["click"] = "click"
    x: int
    """The x coordinate, number of pixels from the left edge."""
    y: int
    """The y coordinate, number of pixels from the top edge."""


function_definition = FunctionDefinition(
    name="click_action",
    description=ClickAction.__doc__ or "",
    parameters=ClickAction.model_json_schema(),
    strict=True,
)


def get_localization_prompt_structured_output(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position. You must output a valid JSON format."

    return [
        {
            "role": "system",
            "content": json.dumps([function_definition.model_dump()]),
        },
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        },
    ]


messages = get_localization_prompt_structured_output(image, instruction)
coordinates_str = run_inference(messages)[0]
coordinates = ClickAction.model_validate(json.loads(coordinates_str)["arguments"])
print(coordinates)
# Expected ClickAction(action='click', x=352, y=340)

from pydantic import BaseModel, ConfigDict

class FunctionDefinition(BaseModel):
    """Function definition data structure.

    Attributes:
        name: name of the function.
        description: description of the function.
        parameters: JSON schema for the function parameters.
        strict: Whether to enable strict schema adherence when generating the function call.
    """

    name: str
    description: str = ""
    parameters: dict[str, Any] = {}
    strict: bool = True


class ClickAction(BaseModel):
    """Click at specific coordinates on the screen."""

    model_config = ConfigDict(
        extra="forbid",
        json_schema_serialization_defaults_required=True,
        json_schema_mode_override="serialization",
        use_attribute_docstrings=True,
    )

    action: Literal["click"] = "click"
    x: int
    """The x coordinate, number of pixels from the left edge."""
    y: int
    """The y coordinate, number of pixels from the top edge."""


function_definition = FunctionDefinition(
    name="click_action",
    description=ClickAction.__doc__ or "",
    parameters=ClickAction.model_json_schema(),
    strict=True,
)


def get_localization_prompt_structured_output(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position. You must output a valid JSON format."

    return [
        {
            "role": "system",
            "content": json.dumps([function_definition.model_dump()]),
        },
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        },
    ]


messages = get_localization_prompt_structured_output(image, instruction)
coordinates_str = run_inference(messages)[0]
coordinates = ClickAction.model_validate(json.loads(coordinates_str)["arguments"])
print(coordinates)
# Expected ClickAction(action='click', x=352, y=340)

from pydantic import BaseModel, ConfigDict

class FunctionDefinition(BaseModel):
    """Function definition data structure.

    Attributes:
        name: name of the function.
        description: description of the function.
        parameters: JSON schema for the function parameters.
        strict: Whether to enable strict schema adherence when generating the function call.
    """

    name: str
    description: str = ""
    parameters: dict[str, Any] = {}
    strict: bool = True


class ClickAction(BaseModel):
    """Click at specific coordinates on the screen."""

    model_config = ConfigDict(
        extra="forbid",
        json_schema_serialization_defaults_required=True,
        json_schema_mode_override="serialization",
        use_attribute_docstrings=True,
    )

    action: Literal["click"] = "click"
    x: int
    """The x coordinate, number of pixels from the left edge."""
    y: int
    """The y coordinate, number of pixels from the top edge."""


function_definition = FunctionDefinition(
    name="click_action",
    description=ClickAction.__doc__ or "",
    parameters=ClickAction.model_json_schema(),
    strict=True,
)


def get_localization_prompt_structured_output(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position. You must output a valid JSON format."

    return [
        {
            "role": "system",
            "content": json.dumps([function_definition.model_dump()]),
        },
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        },
    ]


messages = get_localization_prompt_structured_output(image, instruction)
coordinates_str = run_inference(messages)[0]
coordinates = ClickAction.model_validate(json.loads(coordinates_str)["arguments"])
print(coordinates)
# Expected ClickAction(action='click', x=352, y=340)

from pydantic import BaseModel, ConfigDict

class FunctionDefinition(BaseModel):
    """Function definition data structure.

    Attributes:
        name: name of the function.
        description: description of the function.
        parameters: JSON schema for the function parameters.
        strict: Whether to enable strict schema adherence when generating the function call.
    """

    name: str
    description: str = ""
    parameters: dict[str, Any] = {}
    strict: bool = True


class ClickAction(BaseModel):
    """Click at specific coordinates on the screen."""

    model_config = ConfigDict(
        extra="forbid",
        json_schema_serialization_defaults_required=True,
        json_schema_mode_override="serialization",
        use_attribute_docstrings=True,
    )

    action: Literal["click"] = "click"
    x: int
    """The x coordinate, number of pixels from the left edge."""
    y: int
    """The y coordinate, number of pixels from the top edge."""


function_definition = FunctionDefinition(
    name="click_action",
    description=ClickAction.__doc__ or "",
    parameters=ClickAction.model_json_schema(),
    strict=True,
)


def get_localization_prompt_structured_output(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position. You must output a valid JSON format."

    return [
        {
            "role": "system",
            "content": json.dumps([function_definition.model_dump()]),
        },
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        },
    ]


messages = get_localization_prompt_structured_output(image, instruction)
coordinates_str = run_inference(messages)[0]
coordinates = ClickAction.model_validate(json.loads(coordinates_str)["arguments"])
print(coordinates)
# Expected ClickAction(action='click', x=352, y=340)

from pydantic import BaseModel, ConfigDict

class FunctionDefinition(BaseModel):
    """Function definition data structure.

    Attributes:
        name: name of the function.
        description: description of the function.
        parameters: JSON schema for the function parameters.
        strict: Whether to enable strict schema adherence when generating the function call.
    """

    name: str
    description: str = ""
    parameters: dict[str, Any] = {}
    strict: bool = True


class ClickAction(BaseModel):
    """Click at specific coordinates on the screen."""

    model_config = ConfigDict(
        extra="forbid",
        json_schema_serialization_defaults_required=True,
        json_schema_mode_override="serialization",
        use_attribute_docstrings=True,
    )

    action: Literal["click"] = "click"
    x: int
    """The x coordinate, number of pixels from the left edge."""
    y: int
    """The y coordinate, number of pixels from the top edge."""


function_definition = FunctionDefinition(
    name="click_action",
    description=ClickAction.__doc__ or "",
    parameters=ClickAction.model_json_schema(),
    strict=True,
)


def get_localization_prompt_structured_output(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position. You must output a valid JSON format."

    return [
        {
            "role": "system",
            "content": json.dumps([function_definition.model_dump()]),
        },
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        },
    ]


messages = get_localization_prompt_structured_output(image, instruction)
coordinates_str = run_inference(messages)[0]
coordinates = ClickAction.model_validate(json.loads(coordinates_str)["arguments"])
print(coordinates)
# Expected ClickAction(action='click', x=352, y=340)

from pydantic import BaseModel, ConfigDict

class FunctionDefinition(BaseModel):
    """Function definition data structure.

    Attributes:
        name: name of the function.
        description: description of the function.
        parameters: JSON schema for the function parameters.
        strict: Whether to enable strict schema adherence when generating the function call.
    """

    name: str
    description: str = ""
    parameters: dict[str, Any] = {}
    strict: bool = True


class ClickAction(BaseModel):
    """Click at specific coordinates on the screen."""

    model_config = ConfigDict(
        extra="forbid",
        json_schema_serialization_defaults_required=True,
        json_schema_mode_override="serialization",
        use_attribute_docstrings=True,
    )

    action: Literal["click"] = "click"
    x: int
    """The x coordinate, number of pixels from the left edge."""
    y: int
    """The y coordinate, number of pixels from the top edge."""


function_definition = FunctionDefinition(
    name="click_action",
    description=ClickAction.__doc__ or "",
    parameters=ClickAction.model_json_schema(),
    strict=True,
)


def get_localization_prompt_structured_output(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position. You must output a valid JSON format."

    return [
        {
            "role": "system",
            "content": json.dumps([function_definition.model_dump()]),
        },
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        },
    ]


messages = get_localization_prompt_structured_output(image, instruction)
coordinates_str = run_inference(messages)[0]
coordinates = ClickAction.model_validate(json.loads(coordinates_str)["arguments"])
print(coordinates)
# Expected ClickAction(action='click', x=352, y=340)

from pydantic import BaseModel, ConfigDict

class FunctionDefinition(BaseModel):
    """Function definition data structure.

    Attributes:
        name: name of the function.
        description: description of the function.
        parameters: JSON schema for the function parameters.
        strict: Whether to enable strict schema adherence when generating the function call.
    """

    name: str
    description: str = ""
    parameters: dict[str, Any] = {}
    strict: bool = True


class ClickAction(BaseModel):
    """Click at specific coordinates on the screen."""

    model_config = ConfigDict(
        extra="forbid",
        json_schema_serialization_defaults_required=True,
        json_schema_mode_override="serialization",
        use_attribute_docstrings=True,
    )

    action: Literal["click"] = "click"
    x: int
    """The x coordinate, number of pixels from the left edge."""
    y: int
    """The y coordinate, number of pixels from the top edge."""


function_definition = FunctionDefinition(
    name="click_action",
    description=ClickAction.__doc__ or "",
    parameters=ClickAction.model_json_schema(),
    strict=True,
)


def get_localization_prompt_structured_output(image, instruction: str) -> list[dict[str, Any]]:
    guidelines: str = "Localize an element on the GUI image according to my instructions and output a click position. You must output a valid JSON format."

    return [
        {
            "role": "system",
            "content": json.dumps([function_definition.model_dump()]),
        },
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": image,
                },
                {"type": "text", "text": f"{guidelines}
{instruction}"},
            ],
        },
    ]


messages = get_localization_prompt_structured_output(image, instruction)
coordinates_str = run_inference(messages)[0]
coordinates = ClickAction.model_validate(json.loads(coordinates_str)["arguments"])
print(coordinates)
# Expected ClickAction(action='click', x=352, y=340)