Qwen2-VL-72B-Instruct-quantized.w4a16

Name: Qwen2-VL-72B-Instruct-quantized.w4a16
Author: RedHatAI

72.0B

1 language

license:apache-2.0

RedHatAI

Image Model

OTHER

72B params

New

8 downloads

Early-stage

Try on Hugging Face Add to Compare

Edge AI:

Mobile

Laptop

Server

161GB+ RAM

Mobile

Laptop

Server

Quick Summary

Model Overview - Model Architecture: Qwen/Qwen2-VL-72B-Instruct - Input: Vision-Text - Output: Text - Model Optimizations: - Weight quantization: INT4 - Activat...

Device Compatibility

Mobile

4-6GB RAM

Laptop

16GB RAM

Server

GPU

Minimum Recommended

68GB+ RAM

Code Examples

Deploymentpythonvllm

from vllm.assets.image import ImageAsset
from vllm import LLM, SamplingParams

# prepare model
llm = LLM(
    model="neuralmagic/Qwen2-VL-72B-Instruct-quantized.w4a16",
    trust_remote_code=True,
    max_model_len=4096,
    max_num_seqs=2,
)

# prepare inputs
question = "What is the content of this image?"
inputs = {
    "prompt": f"<|user|>\n<|image_1|>\n{question}<|end|>\n<|assistant|>\n",
    "multi_modal_data": {
        "image": ImageAsset("cherry_blossom").pil_image.convert("RGB")
    },
}

# generate response
print("========== SAMPLE GENERATION ==============")
outputs = llm.generate(inputs, SamplingParams(temperature=0.2, max_tokens=64))
print(f"PROMPT  : {outputs[0].prompt}")
print(f"RESPONSE: {outputs[0].outputs[0].text}")
print("==========================================")

Deploymentpythonvllm

from vllm.assets.image import ImageAsset
from vllm import LLM, SamplingParams

# prepare model
llm = LLM(
    model="neuralmagic/Qwen2-VL-72B-Instruct-quantized.w4a16",
    trust_remote_code=True,
    max_model_len=4096,
    max_num_seqs=2,
)

# prepare inputs
question = "What is the content of this image?"
inputs = {
    "prompt": f"<|user|>\n<|image_1|>\n{question}<|end|>\n<|assistant|>\n",
    "multi_modal_data": {
        "image": ImageAsset("cherry_blossom").pil_image.convert("RGB")
    },
}

# generate response
print("========== SAMPLE GENERATION ==============")
outputs = llm.generate(inputs, SamplingParams(temperature=0.2, max_tokens=64))
print(f"PROMPT  : {outputs[0].prompt}")
print(f"RESPONSE: {outputs[0].outputs[0].text}")
print("==========================================")

Deploymentpythonvllm

from vllm.assets.image import ImageAsset
from vllm import LLM, SamplingParams

# prepare model
llm = LLM(
    model="neuralmagic/Qwen2-VL-72B-Instruct-quantized.w4a16",
    trust_remote_code=True,
    max_model_len=4096,
    max_num_seqs=2,
)

# prepare inputs
question = "What is the content of this image?"
inputs = {
    "prompt": f"<|user|>\n<|image_1|>\n{question}<|end|>\n<|assistant|>\n",
    "multi_modal_data": {
        "image": ImageAsset("cherry_blossom").pil_image.convert("RGB")
    },
}

# generate response
print("========== SAMPLE GENERATION ==============")
outputs = llm.generate(inputs, SamplingParams(temperature=0.2, max_tokens=64))
print(f"PROMPT  : {outputs[0].prompt}")
print(f"RESPONSE: {outputs[0].outputs[0].text}")
print("==========================================")

Deploymentpythonvllm

from vllm.assets.image import ImageAsset
from vllm import LLM, SamplingParams

# prepare model
llm = LLM(
    model="neuralmagic/Qwen2-VL-72B-Instruct-quantized.w4a16",
    trust_remote_code=True,
    max_model_len=4096,
    max_num_seqs=2,
)

# prepare inputs
question = "What is the content of this image?"
inputs = {
    "prompt": f"<|user|>\n<|image_1|>\n{question}<|end|>\n<|assistant|>\n",
    "multi_modal_data": {
        "image": ImageAsset("cherry_blossom").pil_image.convert("RGB")
    },
}

# generate response
print("========== SAMPLE GENERATION ==============")
outputs = llm.generate(inputs, SamplingParams(temperature=0.2, max_tokens=64))
print(f"PROMPT  : {outputs[0].prompt}")
print(f"RESPONSE: {outputs[0].outputs[0].text}")
print("==========================================")

Deploymentpythonvllm

from vllm.assets.image import ImageAsset
from vllm import LLM, SamplingParams

# prepare model
llm = LLM(
    model="neuralmagic/Qwen2-VL-72B-Instruct-quantized.w4a16",
    trust_remote_code=True,
    max_model_len=4096,
    max_num_seqs=2,
)

# prepare inputs
question = "What is the content of this image?"
inputs = {
    "prompt": f"<|user|>\n<|image_1|>\n{question}<|end|>\n<|assistant|>\n",
    "multi_modal_data": {
        "image": ImageAsset("cherry_blossom").pil_image.convert("RGB")
    },
}

# generate response
print("========== SAMPLE GENERATION ==============")
outputs = llm.generate(inputs, SamplingParams(temperature=0.2, max_tokens=64))
print(f"PROMPT  : {outputs[0].prompt}")
print(f"RESPONSE: {outputs[0].outputs[0].text}")
print("==========================================")

Deploymentpythonvllm

from vllm.assets.image import ImageAsset
from vllm import LLM, SamplingParams

# prepare model
llm = LLM(
    model="neuralmagic/Qwen2-VL-72B-Instruct-quantized.w4a16",
    trust_remote_code=True,
    max_model_len=4096,
    max_num_seqs=2,
)

# prepare inputs
question = "What is the content of this image?"
inputs = {
    "prompt": f"<|user|>\n<|image_1|>\n{question}<|end|>\n<|assistant|>\n",
    "multi_modal_data": {
        "image": ImageAsset("cherry_blossom").pil_image.convert("RGB")
    },
}

# generate response
print("========== SAMPLE GENERATION ==============")
outputs = llm.generate(inputs, SamplingParams(temperature=0.2, max_tokens=64))
print(f"PROMPT  : {outputs[0].prompt}")
print(f"RESPONSE: {outputs[0].outputs[0].text}")
print("==========================================")

Deploymentpythonvllm

from vllm.assets.image import ImageAsset
from vllm import LLM, SamplingParams

# prepare model
llm = LLM(
    model="neuralmagic/Qwen2-VL-72B-Instruct-quantized.w4a16",
    trust_remote_code=True,
    max_model_len=4096,
    max_num_seqs=2,
)

# prepare inputs
question = "What is the content of this image?"
inputs = {
    "prompt": f"<|user|>\n<|image_1|>\n{question}<|end|>\n<|assistant|>\n",
    "multi_modal_data": {
        "image": ImageAsset("cherry_blossom").pil_image.convert("RGB")
    },
}

# generate response
print("========== SAMPLE GENERATION ==============")
outputs = llm.generate(inputs, SamplingParams(temperature=0.2, max_tokens=64))
print(f"PROMPT  : {outputs[0].prompt}")
print(f"RESPONSE: {outputs[0].outputs[0].text}")
print("==========================================")

Deploymentpythonvllm

from vllm.assets.image import ImageAsset
from vllm import LLM, SamplingParams

# prepare model
llm = LLM(
    model="neuralmagic/Qwen2-VL-72B-Instruct-quantized.w4a16",
    trust_remote_code=True,
    max_model_len=4096,
    max_num_seqs=2,
)

# prepare inputs
question = "What is the content of this image?"
inputs = {
    "prompt": f"<|user|>\n<|image_1|>\n{question}<|end|>\n<|assistant|>\n",
    "multi_modal_data": {
        "image": ImageAsset("cherry_blossom").pil_image.convert("RGB")
    },
}

# generate response
print("========== SAMPLE GENERATION ==============")
outputs = llm.generate(inputs, SamplingParams(temperature=0.2, max_tokens=64))
print(f"PROMPT  : {outputs[0].prompt}")
print(f"RESPONSE: {outputs[0].outputs[0].text}")
print("==========================================")

Deploymentpythonvllm

from vllm.assets.image import ImageAsset
from vllm import LLM, SamplingParams

# prepare model
llm = LLM(
    model="neuralmagic/Qwen2-VL-72B-Instruct-quantized.w4a16",
    trust_remote_code=True,
    max_model_len=4096,
    max_num_seqs=2,
)

# prepare inputs
question = "What is the content of this image?"
inputs = {
    "prompt": f"<|user|>\n<|image_1|>\n{question}<|end|>\n<|assistant|>\n",
    "multi_modal_data": {
        "image": ImageAsset("cherry_blossom").pil_image.convert("RGB")
    },
}

# generate response
print("========== SAMPLE GENERATION ==============")
outputs = llm.generate(inputs, SamplingParams(temperature=0.2, max_tokens=64))
print(f"PROMPT  : {outputs[0].prompt}")
print(f"RESPONSE: {outputs[0].outputs[0].text}")
print("==========================================")

Deploymentpythonvllm

from vllm.assets.image import ImageAsset
from vllm import LLM, SamplingParams

# prepare model
llm = LLM(
    model="neuralmagic/Qwen2-VL-72B-Instruct-quantized.w4a16",
    trust_remote_code=True,
    max_model_len=4096,
    max_num_seqs=2,
)

# prepare inputs
question = "What is the content of this image?"
inputs = {
    "prompt": f"<|user|>\n<|image_1|>\n{question}<|end|>\n<|assistant|>\n",
    "multi_modal_data": {
        "image": ImageAsset("cherry_blossom").pil_image.convert("RGB")
    },
}

# generate response
print("========== SAMPLE GENERATION ==============")
outputs = llm.generate(inputs, SamplingParams(temperature=0.2, max_tokens=64))
print(f"PROMPT  : {outputs[0].prompt}")
print(f"RESPONSE: {outputs[0].outputs[0].text}")
print("==========================================")

Deploymentpythonvllm

from vllm.assets.image import ImageAsset
from vllm import LLM, SamplingParams

# prepare model
llm = LLM(
    model="neuralmagic/Qwen2-VL-72B-Instruct-quantized.w4a16",
    trust_remote_code=True,
    max_model_len=4096,
    max_num_seqs=2,
)

# prepare inputs
question = "What is the content of this image?"
inputs = {
    "prompt": f"<|user|>\n<|image_1|>\n{question}<|end|>\n<|assistant|>\n",
    "multi_modal_data": {
        "image": ImageAsset("cherry_blossom").pil_image.convert("RGB")
    },
}

# generate response
print("========== SAMPLE GENERATION ==============")
outputs = llm.generate(inputs, SamplingParams(temperature=0.2, max_tokens=64))
print(f"PROMPT  : {outputs[0].prompt}")
print(f"RESPONSE: {outputs[0].outputs[0].text}")
print("==========================================")

Deploymentpythonvllm

from vllm.assets.image import ImageAsset
from vllm import LLM, SamplingParams

# prepare model
llm = LLM(
    model="neuralmagic/Qwen2-VL-72B-Instruct-quantized.w4a16",
    trust_remote_code=True,
    max_model_len=4096,
    max_num_seqs=2,
)

# prepare inputs
question = "What is the content of this image?"
inputs = {
    "prompt": f"<|user|>\n<|image_1|>\n{question}<|end|>\n<|assistant|>\n",
    "multi_modal_data": {
        "image": ImageAsset("cherry_blossom").pil_image.convert("RGB")
    },
}

# generate response
print("========== SAMPLE GENERATION ==============")
outputs = llm.generate(inputs, SamplingParams(temperature=0.2, max_tokens=64))
print(f"PROMPT  : {outputs[0].prompt}")
print(f"RESPONSE: {outputs[0].outputs[0].text}")
print("==========================================")

Deploymentpythonvllm

from vllm.assets.image import ImageAsset
from vllm import LLM, SamplingParams

# prepare model
llm = LLM(
    model="neuralmagic/Qwen2-VL-72B-Instruct-quantized.w4a16",
    trust_remote_code=True,
    max_model_len=4096,
    max_num_seqs=2,
)

# prepare inputs
question = "What is the content of this image?"
inputs = {
    "prompt": f"<|user|>\n<|image_1|>\n{question}<|end|>\n<|assistant|>\n",
    "multi_modal_data": {
        "image": ImageAsset("cherry_blossom").pil_image.convert("RGB")
    },
}

# generate response
print("========== SAMPLE GENERATION ==============")
outputs = llm.generate(inputs, SamplingParams(temperature=0.2, max_tokens=64))
print(f"PROMPT  : {outputs[0].prompt}")
print(f"RESPONSE: {outputs[0].outputs[0].text}")
print("==========================================")

Deploymentpythonvllm

from vllm.assets.image import ImageAsset
from vllm import LLM, SamplingParams

# prepare model
llm = LLM(
    model="neuralmagic/Qwen2-VL-72B-Instruct-quantized.w4a16",
    trust_remote_code=True,
    max_model_len=4096,
    max_num_seqs=2,
)

# prepare inputs
question = "What is the content of this image?"
inputs = {
    "prompt": f"<|user|>\n<|image_1|>\n{question}<|end|>\n<|assistant|>\n",
    "multi_modal_data": {
        "image": ImageAsset("cherry_blossom").pil_image.convert("RGB")
    },
}

# generate response
print("========== SAMPLE GENERATION ==============")
outputs = llm.generate(inputs, SamplingParams(temperature=0.2, max_tokens=64))
print(f"PROMPT  : {outputs[0].prompt}")
print(f"RESPONSE: {outputs[0].outputs[0].text}")
print("==========================================")

Deploymentpythonvllm

from vllm.assets.image import ImageAsset
from vllm import LLM, SamplingParams

# prepare model
llm = LLM(
    model="neuralmagic/Qwen2-VL-72B-Instruct-quantized.w4a16",
    trust_remote_code=True,
    max_model_len=4096,
    max_num_seqs=2,
)

# prepare inputs
question = "What is the content of this image?"
inputs = {
    "prompt": f"<|user|>\n<|image_1|>\n{question}<|end|>\n<|assistant|>\n",
    "multi_modal_data": {
        "image": ImageAsset("cherry_blossom").pil_image.convert("RGB")
    },
}

# generate response
print("========== SAMPLE GENERATION ==============")
outputs = llm.generate(inputs, SamplingParams(temperature=0.2, max_tokens=64))
print(f"PROMPT  : {outputs[0].prompt}")
print(f"RESPONSE: {outputs[0].outputs[0].text}")
print("==========================================")

Deploymentpythonvllm

from vllm.assets.image import ImageAsset
from vllm import LLM, SamplingParams

# prepare model
llm = LLM(
    model="neuralmagic/Qwen2-VL-72B-Instruct-quantized.w4a16",
    trust_remote_code=True,
    max_model_len=4096,
    max_num_seqs=2,
)

# prepare inputs
question = "What is the content of this image?"
inputs = {
    "prompt": f"<|user|>\n<|image_1|>\n{question}<|end|>\n<|assistant|>\n",
    "multi_modal_data": {
        "image": ImageAsset("cherry_blossom").pil_image.convert("RGB")
    },
}

# generate response
print("========== SAMPLE GENERATION ==============")
outputs = llm.generate(inputs, SamplingParams(temperature=0.2, max_tokens=64))
print(f"PROMPT  : {outputs[0].prompt}")
print(f"RESPONSE: {outputs[0].outputs[0].text}")
print("==========================================")

Deploymentpythonvllm

from vllm.assets.image import ImageAsset
from vllm import LLM, SamplingParams

# prepare model
llm = LLM(
    model="neuralmagic/Qwen2-VL-72B-Instruct-quantized.w4a16",
    trust_remote_code=True,
    max_model_len=4096,
    max_num_seqs=2,
)

# prepare inputs
question = "What is the content of this image?"
inputs = {
    "prompt": f"<|user|>\n<|image_1|>\n{question}<|end|>\n<|assistant|>\n",
    "multi_modal_data": {
        "image": ImageAsset("cherry_blossom").pil_image.convert("RGB")
    },
}

# generate response
print("========== SAMPLE GENERATION ==============")
outputs = llm.generate(inputs, SamplingParams(temperature=0.2, max_tokens=64))
print(f"PROMPT  : {outputs[0].prompt}")
print(f"RESPONSE: {outputs[0].outputs[0].text}")
print("==========================================")

Deploymentpythonvllm

from vllm.assets.image import ImageAsset
from vllm import LLM, SamplingParams

# prepare model
llm = LLM(
    model="neuralmagic/Qwen2-VL-72B-Instruct-quantized.w4a16",
    trust_remote_code=True,
    max_model_len=4096,
    max_num_seqs=2,
)

# prepare inputs
question = "What is the content of this image?"
inputs = {
    "prompt": f"<|user|>\n<|image_1|>\n{question}<|end|>\n<|assistant|>\n",
    "multi_modal_data": {
        "image": ImageAsset("cherry_blossom").pil_image.convert("RGB")
    },
}

# generate response
print("========== SAMPLE GENERATION ==============")
outputs = llm.generate(inputs, SamplingParams(temperature=0.2, max_tokens=64))
print(f"PROMPT  : {outputs[0].prompt}")
print(f"RESPONSE: {outputs[0].outputs[0].text}")
print("==========================================")

Deploymentpythonvllm

from vllm.assets.image import ImageAsset
from vllm import LLM, SamplingParams

# prepare model
llm = LLM(
    model="neuralmagic/Qwen2-VL-72B-Instruct-quantized.w4a16",
    trust_remote_code=True,
    max_model_len=4096,
    max_num_seqs=2,
)

# prepare inputs
question = "What is the content of this image?"
inputs = {
    "prompt": f"<|user|>\n<|image_1|>\n{question}<|end|>\n<|assistant|>\n",
    "multi_modal_data": {
        "image": ImageAsset("cherry_blossom").pil_image.convert("RGB")
    },
}

# generate response
print("========== SAMPLE GENERATION ==============")
outputs = llm.generate(inputs, SamplingParams(temperature=0.2, max_tokens=64))
print(f"PROMPT  : {outputs[0].prompt}")
print(f"RESPONSE: {outputs[0].outputs[0].text}")
print("==========================================")

Deploymentpythonvllm

from vllm.assets.image import ImageAsset
from vllm import LLM, SamplingParams

# prepare model
llm = LLM(
    model="neuralmagic/Qwen2-VL-72B-Instruct-quantized.w4a16",
    trust_remote_code=True,
    max_model_len=4096,
    max_num_seqs=2,
)

# prepare inputs
question = "What is the content of this image?"
inputs = {
    "prompt": f"<|user|>\n<|image_1|>\n{question}<|end|>\n<|assistant|>\n",
    "multi_modal_data": {
        "image": ImageAsset("cherry_blossom").pil_image.convert("RGB")
    },
}

# generate response
print("========== SAMPLE GENERATION ==============")
outputs = llm.generate(inputs, SamplingParams(temperature=0.2, max_tokens=64))
print(f"PROMPT  : {outputs[0].prompt}")
print(f"RESPONSE: {outputs[0].outputs[0].text}")
print("==========================================")

Deploymentpythonvllm

from vllm.assets.image import ImageAsset
from vllm import LLM, SamplingParams

# prepare model
llm = LLM(
    model="neuralmagic/Qwen2-VL-72B-Instruct-quantized.w4a16",
    trust_remote_code=True,
    max_model_len=4096,
    max_num_seqs=2,
)

# prepare inputs
question = "What is the content of this image?"
inputs = {
    "prompt": f"<|user|>\n<|image_1|>\n{question}<|end|>\n<|assistant|>\n",
    "multi_modal_data": {
        "image": ImageAsset("cherry_blossom").pil_image.convert("RGB")
    },
}

# generate response
print("========== SAMPLE GENERATION ==============")
outputs = llm.generate(inputs, SamplingParams(temperature=0.2, max_tokens=64))
print(f"PROMPT  : {outputs[0].prompt}")
print(f"RESPONSE: {outputs[0].outputs[0].text}")
print("==========================================")

Deploymentpythonvllm

from vllm.assets.image import ImageAsset
from vllm import LLM, SamplingParams

# prepare model
llm = LLM(
    model="neuralmagic/Qwen2-VL-72B-Instruct-quantized.w4a16",
    trust_remote_code=True,
    max_model_len=4096,
    max_num_seqs=2,
)

# prepare inputs
question = "What is the content of this image?"
inputs = {
    "prompt": f"<|user|>\n<|image_1|>\n{question}<|end|>\n<|assistant|>\n",
    "multi_modal_data": {
        "image": ImageAsset("cherry_blossom").pil_image.convert("RGB")
    },
}

# generate response
print("========== SAMPLE GENERATION ==============")
outputs = llm.generate(inputs, SamplingParams(temperature=0.2, max_tokens=64))
print(f"PROMPT  : {outputs[0].prompt}")
print(f"RESPONSE: {outputs[0].outputs[0].text}")
print("==========================================")

Deploymentpythonvllm

from vllm.assets.image import ImageAsset
from vllm import LLM, SamplingParams

# prepare model
llm = LLM(
    model="neuralmagic/Qwen2-VL-72B-Instruct-quantized.w4a16",
    trust_remote_code=True,
    max_model_len=4096,
    max_num_seqs=2,
)

# prepare inputs
question = "What is the content of this image?"
inputs = {
    "prompt": f"<|user|>\n<|image_1|>\n{question}<|end|>\n<|assistant|>\n",
    "multi_modal_data": {
        "image": ImageAsset("cherry_blossom").pil_image.convert("RGB")
    },
}

# generate response
print("========== SAMPLE GENERATION ==============")
outputs = llm.generate(inputs, SamplingParams(temperature=0.2, max_tokens=64))
print(f"PROMPT  : {outputs[0].prompt}")
print(f"RESPONSE: {outputs[0].outputs[0].text}")
print("==========================================")

Deploymentpythonvllm

from vllm.assets.image import ImageAsset
from vllm import LLM, SamplingParams

# prepare model
llm = LLM(
    model="neuralmagic/Qwen2-VL-72B-Instruct-quantized.w4a16",
    trust_remote_code=True,
    max_model_len=4096,
    max_num_seqs=2,
)

# prepare inputs
question = "What is the content of this image?"
inputs = {
    "prompt": f"<|user|>\n<|image_1|>\n{question}<|end|>\n<|assistant|>\n",
    "multi_modal_data": {
        "image": ImageAsset("cherry_blossom").pil_image.convert("RGB")
    },
}

# generate response
print("========== SAMPLE GENERATION ==============")
outputs = llm.generate(inputs, SamplingParams(temperature=0.2, max_tokens=64))
print(f"PROMPT  : {outputs[0].prompt}")
print(f"RESPONSE: {outputs[0].outputs[0].text}")
print("==========================================")

Deploymentpythonvllm

from vllm.assets.image import ImageAsset
from vllm import LLM, SamplingParams

# prepare model
llm = LLM(
    model="neuralmagic/Qwen2-VL-72B-Instruct-quantized.w4a16",
    trust_remote_code=True,
    max_model_len=4096,
    max_num_seqs=2,
)

# prepare inputs
question = "What is the content of this image?"
inputs = {
    "prompt": f"<|user|>\n<|image_1|>\n{question}<|end|>\n<|assistant|>\n",
    "multi_modal_data": {
        "image": ImageAsset("cherry_blossom").pil_image.convert("RGB")
    },
}

# generate response
print("========== SAMPLE GENERATION ==============")
outputs = llm.generate(inputs, SamplingParams(temperature=0.2, max_tokens=64))
print(f"PROMPT  : {outputs[0].prompt}")
print(f"RESPONSE: {outputs[0].outputs[0].text}")
print("==========================================")

Deploymentpythonvllm

from vllm.assets.image import ImageAsset
from vllm import LLM, SamplingParams

# prepare model
llm = LLM(
    model="neuralmagic/Qwen2-VL-72B-Instruct-quantized.w4a16",
    trust_remote_code=True,
    max_model_len=4096,
    max_num_seqs=2,
)

# prepare inputs
question = "What is the content of this image?"
inputs = {
    "prompt": f"<|user|>\n<|image_1|>\n{question}<|end|>\n<|assistant|>\n",
    "multi_modal_data": {
        "image": ImageAsset("cherry_blossom").pil_image.convert("RGB")
    },
}

# generate response
print("========== SAMPLE GENERATION ==============")
outputs = llm.generate(inputs, SamplingParams(temperature=0.2, max_tokens=64))
print(f"PROMPT  : {outputs[0].prompt}")
print(f"RESPONSE: {outputs[0].outputs[0].text}")
print("==========================================")

Deploymentpythonvllm

from vllm.assets.image import ImageAsset
from vllm import LLM, SamplingParams

# prepare model
llm = LLM(
    model="neuralmagic/Qwen2-VL-72B-Instruct-quantized.w4a16",
    trust_remote_code=True,
    max_model_len=4096,
    max_num_seqs=2,
)

# prepare inputs
question = "What is the content of this image?"
inputs = {
    "prompt": f"<|user|>\n<|image_1|>\n{question}<|end|>\n<|assistant|>\n",
    "multi_modal_data": {
        "image": ImageAsset("cherry_blossom").pil_image.convert("RGB")
    },
}

# generate response
print("========== SAMPLE GENERATION ==============")
outputs = llm.generate(inputs, SamplingParams(temperature=0.2, max_tokens=64))
print(f"PROMPT  : {outputs[0].prompt}")
print(f"RESPONSE: {outputs[0].outputs[0].text}")
print("==========================================")

Deploymentpythonvllm

from vllm.assets.image import ImageAsset
from vllm import LLM, SamplingParams

# prepare model
llm = LLM(
    model="neuralmagic/Qwen2-VL-72B-Instruct-quantized.w4a16",
    trust_remote_code=True,
    max_model_len=4096,
    max_num_seqs=2,
)

# prepare inputs
question = "What is the content of this image?"
inputs = {
    "prompt": f"<|user|>\n<|image_1|>\n{question}<|end|>\n<|assistant|>\n",
    "multi_modal_data": {
        "image": ImageAsset("cherry_blossom").pil_image.convert("RGB")
    },
}

# generate response
print("========== SAMPLE GENERATION ==============")
outputs = llm.generate(inputs, SamplingParams(temperature=0.2, max_tokens=64))
print(f"PROMPT  : {outputs[0].prompt}")
print(f"RESPONSE: {outputs[0].outputs[0].text}")
print("==========================================")

Deploymentpythonvllm

from vllm.assets.image import ImageAsset
from vllm import LLM, SamplingParams

# prepare model
llm = LLM(
    model="neuralmagic/Qwen2-VL-72B-Instruct-quantized.w4a16",
    trust_remote_code=True,
    max_model_len=4096,
    max_num_seqs=2,
)

# prepare inputs
question = "What is the content of this image?"
inputs = {
    "prompt": f"<|user|>\n<|image_1|>\n{question}<|end|>\n<|assistant|>\n",
    "multi_modal_data": {
        "image": ImageAsset("cherry_blossom").pil_image.convert("RGB")
    },
}

# generate response
print("========== SAMPLE GENERATION ==============")
outputs = llm.generate(inputs, SamplingParams(temperature=0.2, max_tokens=64))
print(f"PROMPT  : {outputs[0].prompt}")
print(f"RESPONSE: {outputs[0].outputs[0].text}")
print("==========================================")

Deploymentpythonvllm

from vllm.assets.image import ImageAsset
from vllm import LLM, SamplingParams

# prepare model
llm = LLM(
    model="neuralmagic/Qwen2-VL-72B-Instruct-quantized.w4a16",
    trust_remote_code=True,
    max_model_len=4096,
    max_num_seqs=2,
)

# prepare inputs
question = "What is the content of this image?"
inputs = {
    "prompt": f"<|user|>\n<|image_1|>\n{question}<|end|>\n<|assistant|>\n",
    "multi_modal_data": {
        "image": ImageAsset("cherry_blossom").pil_image.convert("RGB")
    },
}

# generate response
print("========== SAMPLE GENERATION ==============")
outputs = llm.generate(inputs, SamplingParams(temperature=0.2, max_tokens=64))
print(f"PROMPT  : {outputs[0].prompt}")
print(f"RESPONSE: {outputs[0].outputs[0].text}")
print("==========================================")

Deploymentpythonvllm

from vllm.assets.image import ImageAsset
from vllm import LLM, SamplingParams

# prepare model
llm = LLM(
    model="neuralmagic/Qwen2-VL-72B-Instruct-quantized.w4a16",
    trust_remote_code=True,
    max_model_len=4096,
    max_num_seqs=2,
)

# prepare inputs
question = "What is the content of this image?"
inputs = {
    "prompt": f"<|user|>\n<|image_1|>\n{question}<|end|>\n<|assistant|>\n",
    "multi_modal_data": {
        "image": ImageAsset("cherry_blossom").pil_image.convert("RGB")
    },
}

# generate response
print("========== SAMPLE GENERATION ==============")
outputs = llm.generate(inputs, SamplingParams(temperature=0.2, max_tokens=64))
print(f"PROMPT  : {outputs[0].prompt}")
print(f"RESPONSE: {outputs[0].outputs[0].text}")
print("==========================================")

Deploymentpythonvllm

from vllm.assets.image import ImageAsset
from vllm import LLM, SamplingParams

# prepare model
llm = LLM(
    model="neuralmagic/Qwen2-VL-72B-Instruct-quantized.w4a16",
    trust_remote_code=True,
    max_model_len=4096,
    max_num_seqs=2,
)

# prepare inputs
question = "What is the content of this image?"
inputs = {
    "prompt": f"<|user|>\n<|image_1|>\n{question}<|end|>\n<|assistant|>\n",
    "multi_modal_data": {
        "image": ImageAsset("cherry_blossom").pil_image.convert("RGB")
    },
}

# generate response
print("========== SAMPLE GENERATION ==============")
outputs = llm.generate(inputs, SamplingParams(temperature=0.2, max_tokens=64))
print(f"PROMPT  : {outputs[0].prompt}")
print(f"RESPONSE: {outputs[0].outputs[0].text}")
print("==========================================")

Deploymentpythonvllm

from vllm.assets.image import ImageAsset
from vllm import LLM, SamplingParams

# prepare model
llm = LLM(
    model="neuralmagic/Qwen2-VL-72B-Instruct-quantized.w4a16",
    trust_remote_code=True,
    max_model_len=4096,
    max_num_seqs=2,
)

# prepare inputs
question = "What is the content of this image?"
inputs = {
    "prompt": f"<|user|>\n<|image_1|>\n{question}<|end|>\n<|assistant|>\n",
    "multi_modal_data": {
        "image": ImageAsset("cherry_blossom").pil_image.convert("RGB")
    },
}

# generate response
print("========== SAMPLE GENERATION ==============")
outputs = llm.generate(inputs, SamplingParams(temperature=0.2, max_tokens=64))
print(f"PROMPT  : {outputs[0].prompt}")
print(f"RESPONSE: {outputs[0].outputs[0].text}")
print("==========================================")

Deploymentpythonvllm

from vllm.assets.image import ImageAsset
from vllm import LLM, SamplingParams

# prepare model
llm = LLM(
    model="neuralmagic/Qwen2-VL-72B-Instruct-quantized.w4a16",
    trust_remote_code=True,
    max_model_len=4096,
    max_num_seqs=2,
)

# prepare inputs
question = "What is the content of this image?"
inputs = {
    "prompt": f"<|user|>\n<|image_1|>\n{question}<|end|>\n<|assistant|>\n",
    "multi_modal_data": {
        "image": ImageAsset("cherry_blossom").pil_image.convert("RGB")
    },
}

# generate response
print("========== SAMPLE GENERATION ==============")
outputs = llm.generate(inputs, SamplingParams(temperature=0.2, max_tokens=64))
print(f"PROMPT  : {outputs[0].prompt}")
print(f"RESPONSE: {outputs[0].outputs[0].text}")
print("==========================================")

Deploymentpythonvllm

from vllm.assets.image import ImageAsset
from vllm import LLM, SamplingParams

# prepare model
llm = LLM(
    model="neuralmagic/Qwen2-VL-72B-Instruct-quantized.w4a16",
    trust_remote_code=True,
    max_model_len=4096,
    max_num_seqs=2,
)

# prepare inputs
question = "What is the content of this image?"
inputs = {
    "prompt": f"<|user|>\n<|image_1|>\n{question}<|end|>\n<|assistant|>\n",
    "multi_modal_data": {
        "image": ImageAsset("cherry_blossom").pil_image.convert("RGB")
    },
}

# generate response
print("========== SAMPLE GENERATION ==============")
outputs = llm.generate(inputs, SamplingParams(temperature=0.2, max_tokens=64))
print(f"PROMPT  : {outputs[0].prompt}")
print(f"RESPONSE: {outputs[0].outputs[0].text}")
print("==========================================")

Deploymentpythonvllm

from vllm.assets.image import ImageAsset
from vllm import LLM, SamplingParams

# prepare model
llm = LLM(
    model="neuralmagic/Qwen2-VL-72B-Instruct-quantized.w4a16",
    trust_remote_code=True,
    max_model_len=4096,
    max_num_seqs=2,
)

# prepare inputs
question = "What is the content of this image?"
inputs = {
    "prompt": f"<|user|>\n<|image_1|>\n{question}<|end|>\n<|assistant|>\n",
    "multi_modal_data": {
        "image": ImageAsset("cherry_blossom").pil_image.convert("RGB")
    },
}

# generate response
print("========== SAMPLE GENERATION ==============")
outputs = llm.generate(inputs, SamplingParams(temperature=0.2, max_tokens=64))
print(f"PROMPT  : {outputs[0].prompt}")
print(f"RESPONSE: {outputs[0].outputs[0].text}")
print("==========================================")

Deploymentpythonvllm

from vllm.assets.image import ImageAsset
from vllm import LLM, SamplingParams

# prepare model
llm = LLM(
    model="neuralmagic/Qwen2-VL-72B-Instruct-quantized.w4a16",
    trust_remote_code=True,
    max_model_len=4096,
    max_num_seqs=2,
)

# prepare inputs
question = "What is the content of this image?"
inputs = {
    "prompt": f"<|user|>\n<|image_1|>\n{question}<|end|>\n<|assistant|>\n",
    "multi_modal_data": {
        "image": ImageAsset("cherry_blossom").pil_image.convert("RGB")
    },
}

# generate response
print("========== SAMPLE GENERATION ==============")
outputs = llm.generate(inputs, SamplingParams(temperature=0.2, max_tokens=64))
print(f"PROMPT  : {outputs[0].prompt}")
print(f"RESPONSE: {outputs[0].outputs[0].text}")
print("==========================================")

Deploymentpythonvllm

from vllm.assets.image import ImageAsset
from vllm import LLM, SamplingParams

# prepare model
llm = LLM(
    model="neuralmagic/Qwen2-VL-72B-Instruct-quantized.w4a16",
    trust_remote_code=True,
    max_model_len=4096,
    max_num_seqs=2,
)

# prepare inputs
question = "What is the content of this image?"
inputs = {
    "prompt": f"<|user|>\n<|image_1|>\n{question}<|end|>\n<|assistant|>\n",
    "multi_modal_data": {
        "image": ImageAsset("cherry_blossom").pil_image.convert("RGB")
    },
}

# generate response
print("========== SAMPLE GENERATION ==============")
outputs = llm.generate(inputs, SamplingParams(temperature=0.2, max_tokens=64))
print(f"PROMPT  : {outputs[0].prompt}")
print(f"RESPONSE: {outputs[0].outputs[0].text}")
print("==========================================")

Deploymentpythonvllm

from vllm.assets.image import ImageAsset
from vllm import LLM, SamplingParams

# prepare model
llm = LLM(
    model="neuralmagic/Qwen2-VL-72B-Instruct-quantized.w4a16",
    trust_remote_code=True,
    max_model_len=4096,
    max_num_seqs=2,
)

# prepare inputs
question = "What is the content of this image?"
inputs = {
    "prompt": f"<|user|>\n<|image_1|>\n{question}<|end|>\n<|assistant|>\n",
    "multi_modal_data": {
        "image": ImageAsset("cherry_blossom").pil_image.convert("RGB")
    },
}

# generate response
print("========== SAMPLE GENERATION ==============")
outputs = llm.generate(inputs, SamplingParams(temperature=0.2, max_tokens=64))
print(f"PROMPT  : {outputs[0].prompt}")
print(f"RESPONSE: {outputs[0].outputs[0].text}")
print("==========================================")

Deploymentpythonvllm

from vllm.assets.image import ImageAsset
from vllm import LLM, SamplingParams

# prepare model
llm = LLM(
    model="neuralmagic/Qwen2-VL-72B-Instruct-quantized.w4a16",
    trust_remote_code=True,
    max_model_len=4096,
    max_num_seqs=2,
)

# prepare inputs
question = "What is the content of this image?"
inputs = {
    "prompt": f"<|user|>\n<|image_1|>\n{question}<|end|>\n<|assistant|>\n",
    "multi_modal_data": {
        "image": ImageAsset("cherry_blossom").pil_image.convert("RGB")
    },
}

# generate response
print("========== SAMPLE GENERATION ==============")
outputs = llm.generate(inputs, SamplingParams(temperature=0.2, max_tokens=64))
print(f"PROMPT  : {outputs[0].prompt}")
print(f"RESPONSE: {outputs[0].outputs[0].text}")
print("==========================================")

Deploymentpythonvllm

from vllm.assets.image import ImageAsset
from vllm import LLM, SamplingParams

# prepare model
llm = LLM(
    model="neuralmagic/Qwen2-VL-72B-Instruct-quantized.w4a16",
    trust_remote_code=True,
    max_model_len=4096,
    max_num_seqs=2,
)

# prepare inputs
question = "What is the content of this image?"
inputs = {
    "prompt": f"<|user|>\n<|image_1|>\n{question}<|end|>\n<|assistant|>\n",
    "multi_modal_data": {
        "image": ImageAsset("cherry_blossom").pil_image.convert("RGB")
    },
}

# generate response
print("========== SAMPLE GENERATION ==============")
outputs = llm.generate(inputs, SamplingParams(temperature=0.2, max_tokens=64))
print(f"PROMPT  : {outputs[0].prompt}")
print(f"RESPONSE: {outputs[0].outputs[0].text}")
print("==========================================")

Deploymentpythonvllm

from vllm.assets.image import ImageAsset
from vllm import LLM, SamplingParams

# prepare model
llm = LLM(
    model="neuralmagic/Qwen2-VL-72B-Instruct-quantized.w4a16",
    trust_remote_code=True,
    max_model_len=4096,
    max_num_seqs=2,
)

# prepare inputs
question = "What is the content of this image?"
inputs = {
    "prompt": f"<|user|>\n<|image_1|>\n{question}<|end|>\n<|assistant|>\n",
    "multi_modal_data": {
        "image": ImageAsset("cherry_blossom").pil_image.convert("RGB")
    },
}

# generate response
print("========== SAMPLE GENERATION ==============")
outputs = llm.generate(inputs, SamplingParams(temperature=0.2, max_tokens=64))
print(f"PROMPT  : {outputs[0].prompt}")
print(f"RESPONSE: {outputs[0].outputs[0].text}")
print("==========================================")

Load model.pythontransformers

import base64
from io import BytesIO
import torch
from datasets import load_dataset
from qwen_vl_utils import process_vision_info
from transformers import AutoProcessor
from llmcompressor.modifiers.quantization import GPTQModifier
from llmcompressor.transformers import oneshot
from llmcompressor.transformers.tracing import TraceableQwen2VLForConditionalGeneration
from llmcompressor.transformers.utils.data_collator import qwen2_vl_data_collator
from compressed_tensors.quantization import QuantizationArgs, QuantizationType, QuantizationStrategy, ActivationOrdering, QuantizationScheme

# Load model.
model_id = "Qwen/Qwen2-VL-72B-Instruct"

model = TraceableQwen2VLForConditionalGeneration.from_pretrained(
    model_id,
    device_map="auto",
    torch_dtype="auto",
)
processor = AutoProcessor.from_pretrained(model_id, trust_remote_code=True)

# Oneshot arguments
DATASET_ID = "lmms-lab/flickr30k"
DATASET_SPLIT = {"calibration": "test[:512]"}
NUM_CALIBRATION_SAMPLES = 512
MAX_SEQUENCE_LENGTH = 2048

# Load dataset and preprocess.
ds = load_dataset(DATASET_ID, split=DATASET_SPLIT)
ds = ds.shuffle(seed=42)
dampening_frac=0.01

# Apply chat template and tokenize inputs.
def preprocess_and_tokenize(example):
    # preprocess
    buffered = BytesIO()
    example["image"].save(buffered, format="PNG")
    encoded_image = base64.b64encode(buffered.getvalue())
    encoded_image_text = encoded_image.decode("utf-8")
    base64_qwen = f"data:image;base64,{encoded_image_text}"
    messages = [
        {
            "role": "user",
            "content": [
                {"type": "image", "image": base64_qwen},
                {"type": "text", "text": "What does the image show?"},
            ],
        }
    ]
    text = processor.apply_chat_template(
        messages, tokenize=False, add_generation_prompt=True
    )
    image_inputs, video_inputs = process_vision_info(messages)

    # tokenize
    return processor(
        text=[text],
        images=image_inputs,
        videos=video_inputs,
        padding=False,
        max_length=MAX_SEQUENCE_LENGTH,
        truncation=True,
    )

ds = ds.map(preprocess_and_tokenize, remove_columns=ds["calibration"].column_names)

# Recipe
recipe = GPTQModifier(
    targets="Linear",
    config_groups={
        "config_group": QuantizationScheme(
            targets=["Linear"],
            weights=QuantizationArgs(
                num_bits=4,
                type=QuantizationType.INT,
                strategy=QuantizationStrategy.GROUP,
                group_size=128,
                symmetric=True,
                dynamic=False,
                actorder=ActivationOrdering.WEIGHT,
            ),
        ),
    },
    sequential_targets=["Qwen2VLDecoderLayer"],
    ignore=["lm_head", "re:visual.*"],
    update_size=NUM_CALIBRATION_SAMPLES,
    dampening_frac=dampening_frac
)

SAVE_DIR=f"{model_id.split('/')[1]}-quantized.w4a16

# Perform oneshot
oneshot(
    model=model,
    tokenizer=model_id,
    dataset=ds,
    recipe=recipe,
    max_seq_length=MAX_SEQUENCE_LENGTH,
    num_calibration_samples=NUM_CALIBRATION_SAMPLES,
    trust_remote_code_model=True,
    data_collator=qwen2_vl_data_collator,
    output_dir=SAVE_DIR
)

Load model.pythontransformers

import base64
from io import BytesIO
import torch
from datasets import load_dataset
from qwen_vl_utils import process_vision_info
from transformers import AutoProcessor
from llmcompressor.modifiers.quantization import GPTQModifier
from llmcompressor.transformers import oneshot
from llmcompressor.transformers.tracing import TraceableQwen2VLForConditionalGeneration
from llmcompressor.transformers.utils.data_collator import qwen2_vl_data_collator
from compressed_tensors.quantization import QuantizationArgs, QuantizationType, QuantizationStrategy, ActivationOrdering, QuantizationScheme

# Load model.
model_id = "Qwen/Qwen2-VL-72B-Instruct"

model = TraceableQwen2VLForConditionalGeneration.from_pretrained(
    model_id,
    device_map="auto",
    torch_dtype="auto",
)
processor = AutoProcessor.from_pretrained(model_id, trust_remote_code=True)

# Oneshot arguments
DATASET_ID = "lmms-lab/flickr30k"
DATASET_SPLIT = {"calibration": "test[:512]"}
NUM_CALIBRATION_SAMPLES = 512
MAX_SEQUENCE_LENGTH = 2048

# Load dataset and preprocess.
ds = load_dataset(DATASET_ID, split=DATASET_SPLIT)
ds = ds.shuffle(seed=42)
dampening_frac=0.01

# Apply chat template and tokenize inputs.
def preprocess_and_tokenize(example):
    # preprocess
    buffered = BytesIO()
    example["image"].save(buffered, format="PNG")
    encoded_image = base64.b64encode(buffered.getvalue())
    encoded_image_text = encoded_image.decode("utf-8")
    base64_qwen = f"data:image;base64,{encoded_image_text}"
    messages = [
        {
            "role": "user",
            "content": [
                {"type": "image", "image": base64_qwen},
                {"type": "text", "text": "What does the image show?"},
            ],
        }
    ]
    text = processor.apply_chat_template(
        messages, tokenize=False, add_generation_prompt=True
    )
    image_inputs, video_inputs = process_vision_info(messages)

    # tokenize
    return processor(
        text=[text],
        images=image_inputs,
        videos=video_inputs,
        padding=False,
        max_length=MAX_SEQUENCE_LENGTH,
        truncation=True,
    )

ds = ds.map(preprocess_and_tokenize, remove_columns=ds["calibration"].column_names)

# Recipe
recipe = GPTQModifier(
    targets="Linear",
    config_groups={
        "config_group": QuantizationScheme(
            targets=["Linear"],
            weights=QuantizationArgs(
                num_bits=4,
                type=QuantizationType.INT,
                strategy=QuantizationStrategy.GROUP,
                group_size=128,
                symmetric=True,
                dynamic=False,
                actorder=ActivationOrdering.WEIGHT,
            ),
        ),
    },
    sequential_targets=["Qwen2VLDecoderLayer"],
    ignore=["lm_head", "re:visual.*"],
    update_size=NUM_CALIBRATION_SAMPLES,
    dampening_frac=dampening_frac
)

SAVE_DIR=f"{model_id.split('/')[1]}-quantized.w4a16

# Perform oneshot
oneshot(
    model=model,
    tokenizer=model_id,
    dataset=ds,
    recipe=recipe,
    max_seq_length=MAX_SEQUENCE_LENGTH,
    num_calibration_samples=NUM_CALIBRATION_SAMPLES,
    trust_remote_code_model=True,
    data_collator=qwen2_vl_data_collator,
    output_dir=SAVE_DIR
)

Load model.pythontransformers

import base64
from io import BytesIO
import torch
from datasets import load_dataset
from qwen_vl_utils import process_vision_info
from transformers import AutoProcessor
from llmcompressor.modifiers.quantization import GPTQModifier
from llmcompressor.transformers import oneshot
from llmcompressor.transformers.tracing import TraceableQwen2VLForConditionalGeneration
from llmcompressor.transformers.utils.data_collator import qwen2_vl_data_collator
from compressed_tensors.quantization import QuantizationArgs, QuantizationType, QuantizationStrategy, ActivationOrdering, QuantizationScheme

# Load model.
model_id = "Qwen/Qwen2-VL-72B-Instruct"

model = TraceableQwen2VLForConditionalGeneration.from_pretrained(
    model_id,
    device_map="auto",
    torch_dtype="auto",
)
processor = AutoProcessor.from_pretrained(model_id, trust_remote_code=True)

# Oneshot arguments
DATASET_ID = "lmms-lab/flickr30k"
DATASET_SPLIT = {"calibration": "test[:512]"}
NUM_CALIBRATION_SAMPLES = 512
MAX_SEQUENCE_LENGTH = 2048

# Load dataset and preprocess.
ds = load_dataset(DATASET_ID, split=DATASET_SPLIT)
ds = ds.shuffle(seed=42)
dampening_frac=0.01

# Apply chat template and tokenize inputs.
def preprocess_and_tokenize(example):
    # preprocess
    buffered = BytesIO()
    example["image"].save(buffered, format="PNG")
    encoded_image = base64.b64encode(buffered.getvalue())
    encoded_image_text = encoded_image.decode("utf-8")
    base64_qwen = f"data:image;base64,{encoded_image_text}"
    messages = [
        {
            "role": "user",
            "content": [
                {"type": "image", "image": base64_qwen},
                {"type": "text", "text": "What does the image show?"},
            ],
        }
    ]
    text = processor.apply_chat_template(
        messages, tokenize=False, add_generation_prompt=True
    )
    image_inputs, video_inputs = process_vision_info(messages)

    # tokenize
    return processor(
        text=[text],
        images=image_inputs,
        videos=video_inputs,
        padding=False,
        max_length=MAX_SEQUENCE_LENGTH,
        truncation=True,
    )

ds = ds.map(preprocess_and_tokenize, remove_columns=ds["calibration"].column_names)

# Recipe
recipe = GPTQModifier(
    targets="Linear",
    config_groups={
        "config_group": QuantizationScheme(
            targets=["Linear"],
            weights=QuantizationArgs(
                num_bits=4,
                type=QuantizationType.INT,
                strategy=QuantizationStrategy.GROUP,
                group_size=128,
                symmetric=True,
                dynamic=False,
                actorder=ActivationOrdering.WEIGHT,
            ),
        ),
    },
    sequential_targets=["Qwen2VLDecoderLayer"],
    ignore=["lm_head", "re:visual.*"],
    update_size=NUM_CALIBRATION_SAMPLES,
    dampening_frac=dampening_frac
)

SAVE_DIR=f"{model_id.split('/')[1]}-quantized.w4a16

# Perform oneshot
oneshot(
    model=model,
    tokenizer=model_id,
    dataset=ds,
    recipe=recipe,
    max_seq_length=MAX_SEQUENCE_LENGTH,
    num_calibration_samples=NUM_CALIBRATION_SAMPLES,
    trust_remote_code_model=True,
    data_collator=qwen2_vl_data_collator,
    output_dir=SAVE_DIR
)

Load model.pythontransformers

import base64
from io import BytesIO
import torch
from datasets import load_dataset
from qwen_vl_utils import process_vision_info
from transformers import AutoProcessor
from llmcompressor.modifiers.quantization import GPTQModifier
from llmcompressor.transformers import oneshot
from llmcompressor.transformers.tracing import TraceableQwen2VLForConditionalGeneration
from llmcompressor.transformers.utils.data_collator import qwen2_vl_data_collator
from compressed_tensors.quantization import QuantizationArgs, QuantizationType, QuantizationStrategy, ActivationOrdering, QuantizationScheme

# Load model.
model_id = "Qwen/Qwen2-VL-72B-Instruct"

model = TraceableQwen2VLForConditionalGeneration.from_pretrained(
    model_id,
    device_map="auto",
    torch_dtype="auto",
)
processor = AutoProcessor.from_pretrained(model_id, trust_remote_code=True)

# Oneshot arguments
DATASET_ID = "lmms-lab/flickr30k"
DATASET_SPLIT = {"calibration": "test[:512]"}
NUM_CALIBRATION_SAMPLES = 512
MAX_SEQUENCE_LENGTH = 2048

# Load dataset and preprocess.
ds = load_dataset(DATASET_ID, split=DATASET_SPLIT)
ds = ds.shuffle(seed=42)
dampening_frac=0.01

# Apply chat template and tokenize inputs.
def preprocess_and_tokenize(example):
    # preprocess
    buffered = BytesIO()
    example["image"].save(buffered, format="PNG")
    encoded_image = base64.b64encode(buffered.getvalue())
    encoded_image_text = encoded_image.decode("utf-8")
    base64_qwen = f"data:image;base64,{encoded_image_text}"
    messages = [
        {
            "role": "user",
            "content": [
                {"type": "image", "image": base64_qwen},
                {"type": "text", "text": "What does the image show?"},
            ],
        }
    ]
    text = processor.apply_chat_template(
        messages, tokenize=False, add_generation_prompt=True
    )
    image_inputs, video_inputs = process_vision_info(messages)

    # tokenize
    return processor(
        text=[text],
        images=image_inputs,
        videos=video_inputs,
        padding=False,
        max_length=MAX_SEQUENCE_LENGTH,
        truncation=True,
    )

ds = ds.map(preprocess_and_tokenize, remove_columns=ds["calibration"].column_names)

# Recipe
recipe = GPTQModifier(
    targets="Linear",
    config_groups={
        "config_group": QuantizationScheme(
            targets=["Linear"],
            weights=QuantizationArgs(
                num_bits=4,
                type=QuantizationType.INT,
                strategy=QuantizationStrategy.GROUP,
                group_size=128,
                symmetric=True,
                dynamic=False,
                actorder=ActivationOrdering.WEIGHT,
            ),
        ),
    },
    sequential_targets=["Qwen2VLDecoderLayer"],
    ignore=["lm_head", "re:visual.*"],
    update_size=NUM_CALIBRATION_SAMPLES,
    dampening_frac=dampening_frac
)

SAVE_DIR=f"{model_id.split('/')[1]}-quantized.w4a16

# Perform oneshot
oneshot(
    model=model,
    tokenizer=model_id,
    dataset=ds,
    recipe=recipe,
    max_seq_length=MAX_SEQUENCE_LENGTH,
    num_calibration_samples=NUM_CALIBRATION_SAMPLES,
    trust_remote_code_model=True,
    data_collator=qwen2_vl_data_collator,
    output_dir=SAVE_DIR
)

Load model.pythontransformers

import base64
from io import BytesIO
import torch
from datasets import load_dataset
from qwen_vl_utils import process_vision_info
from transformers import AutoProcessor
from llmcompressor.modifiers.quantization import GPTQModifier
from llmcompressor.transformers import oneshot
from llmcompressor.transformers.tracing import TraceableQwen2VLForConditionalGeneration
from llmcompressor.transformers.utils.data_collator import qwen2_vl_data_collator
from compressed_tensors.quantization import QuantizationArgs, QuantizationType, QuantizationStrategy, ActivationOrdering, QuantizationScheme

# Load model.
model_id = "Qwen/Qwen2-VL-72B-Instruct"

model = TraceableQwen2VLForConditionalGeneration.from_pretrained(
    model_id,
    device_map="auto",
    torch_dtype="auto",
)
processor = AutoProcessor.from_pretrained(model_id, trust_remote_code=True)

# Oneshot arguments
DATASET_ID = "lmms-lab/flickr30k"
DATASET_SPLIT = {"calibration": "test[:512]"}
NUM_CALIBRATION_SAMPLES = 512
MAX_SEQUENCE_LENGTH = 2048

# Load dataset and preprocess.
ds = load_dataset(DATASET_ID, split=DATASET_SPLIT)
ds = ds.shuffle(seed=42)
dampening_frac=0.01

# Apply chat template and tokenize inputs.
def preprocess_and_tokenize(example):
    # preprocess
    buffered = BytesIO()
    example["image"].save(buffered, format="PNG")
    encoded_image = base64.b64encode(buffered.getvalue())
    encoded_image_text = encoded_image.decode("utf-8")
    base64_qwen = f"data:image;base64,{encoded_image_text}"
    messages = [
        {
            "role": "user",
            "content": [
                {"type": "image", "image": base64_qwen},
                {"type": "text", "text": "What does the image show?"},
            ],
        }
    ]
    text = processor.apply_chat_template(
        messages, tokenize=False, add_generation_prompt=True
    )
    image_inputs, video_inputs = process_vision_info(messages)

    # tokenize
    return processor(
        text=[text],
        images=image_inputs,
        videos=video_inputs,
        padding=False,
        max_length=MAX_SEQUENCE_LENGTH,
        truncation=True,
    )

ds = ds.map(preprocess_and_tokenize, remove_columns=ds["calibration"].column_names)

# Recipe
recipe = GPTQModifier(
    targets="Linear",
    config_groups={
        "config_group": QuantizationScheme(
            targets=["Linear"],
            weights=QuantizationArgs(
                num_bits=4,
                type=QuantizationType.INT,
                strategy=QuantizationStrategy.GROUP,
                group_size=128,
                symmetric=True,
                dynamic=False,
                actorder=ActivationOrdering.WEIGHT,
            ),
        ),
    },
    sequential_targets=["Qwen2VLDecoderLayer"],
    ignore=["lm_head", "re:visual.*"],
    update_size=NUM_CALIBRATION_SAMPLES,
    dampening_frac=dampening_frac
)

SAVE_DIR=f"{model_id.split('/')[1]}-quantized.w4a16

# Perform oneshot
oneshot(
    model=model,
    tokenizer=model_id,
    dataset=ds,
    recipe=recipe,
    max_seq_length=MAX_SEQUENCE_LENGTH,
    num_calibration_samples=NUM_CALIBRATION_SAMPLES,
    trust_remote_code_model=True,
    data_collator=qwen2_vl_data_collator,
    output_dir=SAVE_DIR
)

Load model.pythontransformers

import base64
from io import BytesIO
import torch
from datasets import load_dataset
from qwen_vl_utils import process_vision_info
from transformers import AutoProcessor
from llmcompressor.modifiers.quantization import GPTQModifier
from llmcompressor.transformers import oneshot
from llmcompressor.transformers.tracing import TraceableQwen2VLForConditionalGeneration
from llmcompressor.transformers.utils.data_collator import qwen2_vl_data_collator
from compressed_tensors.quantization import QuantizationArgs, QuantizationType, QuantizationStrategy, ActivationOrdering, QuantizationScheme

# Load model.
model_id = "Qwen/Qwen2-VL-72B-Instruct"

model = TraceableQwen2VLForConditionalGeneration.from_pretrained(
    model_id,
    device_map="auto",
    torch_dtype="auto",
)
processor = AutoProcessor.from_pretrained(model_id, trust_remote_code=True)

# Oneshot arguments
DATASET_ID = "lmms-lab/flickr30k"
DATASET_SPLIT = {"calibration": "test[:512]"}
NUM_CALIBRATION_SAMPLES = 512
MAX_SEQUENCE_LENGTH = 2048

# Load dataset and preprocess.
ds = load_dataset(DATASET_ID, split=DATASET_SPLIT)
ds = ds.shuffle(seed=42)
dampening_frac=0.01

# Apply chat template and tokenize inputs.
def preprocess_and_tokenize(example):
    # preprocess
    buffered = BytesIO()
    example["image"].save(buffered, format="PNG")
    encoded_image = base64.b64encode(buffered.getvalue())
    encoded_image_text = encoded_image.decode("utf-8")
    base64_qwen = f"data:image;base64,{encoded_image_text}"
    messages = [
        {
            "role": "user",
            "content": [
                {"type": "image", "image": base64_qwen},
                {"type": "text", "text": "What does the image show?"},
            ],
        }
    ]
    text = processor.apply_chat_template(
        messages, tokenize=False, add_generation_prompt=True
    )
    image_inputs, video_inputs = process_vision_info(messages)

    # tokenize
    return processor(
        text=[text],
        images=image_inputs,
        videos=video_inputs,
        padding=False,
        max_length=MAX_SEQUENCE_LENGTH,
        truncation=True,
    )

ds = ds.map(preprocess_and_tokenize, remove_columns=ds["calibration"].column_names)

# Recipe
recipe = GPTQModifier(
    targets="Linear",
    config_groups={
        "config_group": QuantizationScheme(
            targets=["Linear"],
            weights=QuantizationArgs(
                num_bits=4,
                type=QuantizationType.INT,
                strategy=QuantizationStrategy.GROUP,
                group_size=128,
                symmetric=True,
                dynamic=False,
                actorder=ActivationOrdering.WEIGHT,
            ),
        ),
    },
    sequential_targets=["Qwen2VLDecoderLayer"],
    ignore=["lm_head", "re:visual.*"],
    update_size=NUM_CALIBRATION_SAMPLES,
    dampening_frac=dampening_frac
)

SAVE_DIR=f"{model_id.split('/')[1]}-quantized.w4a16

# Perform oneshot
oneshot(
    model=model,
    tokenizer=model_id,
    dataset=ds,
    recipe=recipe,
    max_seq_length=MAX_SEQUENCE_LENGTH,
    num_calibration_samples=NUM_CALIBRATION_SAMPLES,
    trust_remote_code_model=True,
    data_collator=qwen2_vl_data_collator,
    output_dir=SAVE_DIR
)

Load model.pythontransformers

import base64
from io import BytesIO
import torch
from datasets import load_dataset
from qwen_vl_utils import process_vision_info
from transformers import AutoProcessor
from llmcompressor.modifiers.quantization import GPTQModifier
from llmcompressor.transformers import oneshot
from llmcompressor.transformers.tracing import TraceableQwen2VLForConditionalGeneration
from llmcompressor.transformers.utils.data_collator import qwen2_vl_data_collator
from compressed_tensors.quantization import QuantizationArgs, QuantizationType, QuantizationStrategy, ActivationOrdering, QuantizationScheme

# Load model.
model_id = "Qwen/Qwen2-VL-72B-Instruct"

model = TraceableQwen2VLForConditionalGeneration.from_pretrained(
    model_id,
    device_map="auto",
    torch_dtype="auto",
)
processor = AutoProcessor.from_pretrained(model_id, trust_remote_code=True)

# Oneshot arguments
DATASET_ID = "lmms-lab/flickr30k"
DATASET_SPLIT = {"calibration": "test[:512]"}
NUM_CALIBRATION_SAMPLES = 512
MAX_SEQUENCE_LENGTH = 2048

# Load dataset and preprocess.
ds = load_dataset(DATASET_ID, split=DATASET_SPLIT)
ds = ds.shuffle(seed=42)
dampening_frac=0.01

# Apply chat template and tokenize inputs.
def preprocess_and_tokenize(example):
    # preprocess
    buffered = BytesIO()
    example["image"].save(buffered, format="PNG")
    encoded_image = base64.b64encode(buffered.getvalue())
    encoded_image_text = encoded_image.decode("utf-8")
    base64_qwen = f"data:image;base64,{encoded_image_text}"
    messages = [
        {
            "role": "user",
            "content": [
                {"type": "image", "image": base64_qwen},
                {"type": "text", "text": "What does the image show?"},
            ],
        }
    ]
    text = processor.apply_chat_template(
        messages, tokenize=False, add_generation_prompt=True
    )
    image_inputs, video_inputs = process_vision_info(messages)

    # tokenize
    return processor(
        text=[text],
        images=image_inputs,
        videos=video_inputs,
        padding=False,
        max_length=MAX_SEQUENCE_LENGTH,
        truncation=True,
    )

ds = ds.map(preprocess_and_tokenize, remove_columns=ds["calibration"].column_names)

# Recipe
recipe = GPTQModifier(
    targets="Linear",
    config_groups={
        "config_group": QuantizationScheme(
            targets=["Linear"],
            weights=QuantizationArgs(
                num_bits=4,
                type=QuantizationType.INT,
                strategy=QuantizationStrategy.GROUP,
                group_size=128,
                symmetric=True,
                dynamic=False,
                actorder=ActivationOrdering.WEIGHT,
            ),
        ),
    },
    sequential_targets=["Qwen2VLDecoderLayer"],
    ignore=["lm_head", "re:visual.*"],
    update_size=NUM_CALIBRATION_SAMPLES,
    dampening_frac=dampening_frac
)

SAVE_DIR=f"{model_id.split('/')[1]}-quantized.w4a16

# Perform oneshot
oneshot(
    model=model,
    tokenizer=model_id,
    dataset=ds,
    recipe=recipe,
    max_seq_length=MAX_SEQUENCE_LENGTH,
    num_calibration_samples=NUM_CALIBRATION_SAMPLES,
    trust_remote_code_model=True,
    data_collator=qwen2_vl_data_collator,
    output_dir=SAVE_DIR
)

Load model.pythontransformers

import base64
from io import BytesIO
import torch
from datasets import load_dataset
from qwen_vl_utils import process_vision_info
from transformers import AutoProcessor
from llmcompressor.modifiers.quantization import GPTQModifier
from llmcompressor.transformers import oneshot
from llmcompressor.transformers.tracing import TraceableQwen2VLForConditionalGeneration
from llmcompressor.transformers.utils.data_collator import qwen2_vl_data_collator
from compressed_tensors.quantization import QuantizationArgs, QuantizationType, QuantizationStrategy, ActivationOrdering, QuantizationScheme

# Load model.
model_id = "Qwen/Qwen2-VL-72B-Instruct"

model = TraceableQwen2VLForConditionalGeneration.from_pretrained(
    model_id,
    device_map="auto",
    torch_dtype="auto",
)
processor = AutoProcessor.from_pretrained(model_id, trust_remote_code=True)

# Oneshot arguments
DATASET_ID = "lmms-lab/flickr30k"
DATASET_SPLIT = {"calibration": "test[:512]"}
NUM_CALIBRATION_SAMPLES = 512
MAX_SEQUENCE_LENGTH = 2048

# Load dataset and preprocess.
ds = load_dataset(DATASET_ID, split=DATASET_SPLIT)
ds = ds.shuffle(seed=42)
dampening_frac=0.01

# Apply chat template and tokenize inputs.
def preprocess_and_tokenize(example):
    # preprocess
    buffered = BytesIO()
    example["image"].save(buffered, format="PNG")
    encoded_image = base64.b64encode(buffered.getvalue())
    encoded_image_text = encoded_image.decode("utf-8")
    base64_qwen = f"data:image;base64,{encoded_image_text}"
    messages = [
        {
            "role": "user",
            "content": [
                {"type": "image", "image": base64_qwen},
                {"type": "text", "text": "What does the image show?"},
            ],
        }
    ]
    text = processor.apply_chat_template(
        messages, tokenize=False, add_generation_prompt=True
    )
    image_inputs, video_inputs = process_vision_info(messages)

    # tokenize
    return processor(
        text=[text],
        images=image_inputs,
        videos=video_inputs,
        padding=False,
        max_length=MAX_SEQUENCE_LENGTH,
        truncation=True,
    )

ds = ds.map(preprocess_and_tokenize, remove_columns=ds["calibration"].column_names)

# Recipe
recipe = GPTQModifier(
    targets="Linear",
    config_groups={
        "config_group": QuantizationScheme(
            targets=["Linear"],
            weights=QuantizationArgs(
                num_bits=4,
                type=QuantizationType.INT,
                strategy=QuantizationStrategy.GROUP,
                group_size=128,
                symmetric=True,
                dynamic=False,
                actorder=ActivationOrdering.WEIGHT,
            ),
        ),
    },
    sequential_targets=["Qwen2VLDecoderLayer"],
    ignore=["lm_head", "re:visual.*"],
    update_size=NUM_CALIBRATION_SAMPLES,
    dampening_frac=dampening_frac
)

SAVE_DIR=f"{model_id.split('/')[1]}-quantized.w4a16

# Perform oneshot
oneshot(
    model=model,
    tokenizer=model_id,
    dataset=ds,
    recipe=recipe,
    max_seq_length=MAX_SEQUENCE_LENGTH,
    num_calibration_samples=NUM_CALIBRATION_SAMPLES,
    trust_remote_code_model=True,
    data_collator=qwen2_vl_data_collator,
    output_dir=SAVE_DIR
)

Load model.pythontransformers

import base64
from io import BytesIO
import torch
from datasets import load_dataset
from qwen_vl_utils import process_vision_info
from transformers import AutoProcessor
from llmcompressor.modifiers.quantization import GPTQModifier
from llmcompressor.transformers import oneshot
from llmcompressor.transformers.tracing import TraceableQwen2VLForConditionalGeneration
from llmcompressor.transformers.utils.data_collator import qwen2_vl_data_collator
from compressed_tensors.quantization import QuantizationArgs, QuantizationType, QuantizationStrategy, ActivationOrdering, QuantizationScheme

# Load model.
model_id = "Qwen/Qwen2-VL-72B-Instruct"

model = TraceableQwen2VLForConditionalGeneration.from_pretrained(
    model_id,
    device_map="auto",
    torch_dtype="auto",
)
processor = AutoProcessor.from_pretrained(model_id, trust_remote_code=True)

# Oneshot arguments
DATASET_ID = "lmms-lab/flickr30k"
DATASET_SPLIT = {"calibration": "test[:512]"}
NUM_CALIBRATION_SAMPLES = 512
MAX_SEQUENCE_LENGTH = 2048

# Load dataset and preprocess.
ds = load_dataset(DATASET_ID, split=DATASET_SPLIT)
ds = ds.shuffle(seed=42)
dampening_frac=0.01

# Apply chat template and tokenize inputs.
def preprocess_and_tokenize(example):
    # preprocess
    buffered = BytesIO()
    example["image"].save(buffered, format="PNG")
    encoded_image = base64.b64encode(buffered.getvalue())
    encoded_image_text = encoded_image.decode("utf-8")
    base64_qwen = f"data:image;base64,{encoded_image_text}"
    messages = [
        {
            "role": "user",
            "content": [
                {"type": "image", "image": base64_qwen},
                {"type": "text", "text": "What does the image show?"},
            ],
        }
    ]
    text = processor.apply_chat_template(
        messages, tokenize=False, add_generation_prompt=True
    )
    image_inputs, video_inputs = process_vision_info(messages)

    # tokenize
    return processor(
        text=[text],
        images=image_inputs,
        videos=video_inputs,
        padding=False,
        max_length=MAX_SEQUENCE_LENGTH,
        truncation=True,
    )

ds = ds.map(preprocess_and_tokenize, remove_columns=ds["calibration"].column_names)

# Recipe
recipe = GPTQModifier(
    targets="Linear",
    config_groups={
        "config_group": QuantizationScheme(
            targets=["Linear"],
            weights=QuantizationArgs(
                num_bits=4,
                type=QuantizationType.INT,
                strategy=QuantizationStrategy.GROUP,
                group_size=128,
                symmetric=True,
                dynamic=False,
                actorder=ActivationOrdering.WEIGHT,
            ),
        ),
    },
    sequential_targets=["Qwen2VLDecoderLayer"],
    ignore=["lm_head", "re:visual.*"],
    update_size=NUM_CALIBRATION_SAMPLES,
    dampening_frac=dampening_frac
)

SAVE_DIR=f"{model_id.split('/')[1]}-quantized.w4a16

# Perform oneshot
oneshot(
    model=model,
    tokenizer=model_id,
    dataset=ds,
    recipe=recipe,
    max_seq_length=MAX_SEQUENCE_LENGTH,
    num_calibration_samples=NUM_CALIBRATION_SAMPLES,
    trust_remote_code_model=True,
    data_collator=qwen2_vl_data_collator,
    output_dir=SAVE_DIR
)

Load model.pythontransformers

import base64
from io import BytesIO
import torch
from datasets import load_dataset
from qwen_vl_utils import process_vision_info
from transformers import AutoProcessor
from llmcompressor.modifiers.quantization import GPTQModifier
from llmcompressor.transformers import oneshot
from llmcompressor.transformers.tracing import TraceableQwen2VLForConditionalGeneration
from llmcompressor.transformers.utils.data_collator import qwen2_vl_data_collator
from compressed_tensors.quantization import QuantizationArgs, QuantizationType, QuantizationStrategy, ActivationOrdering, QuantizationScheme

# Load model.
model_id = "Qwen/Qwen2-VL-72B-Instruct"

model = TraceableQwen2VLForConditionalGeneration.from_pretrained(
    model_id,
    device_map="auto",
    torch_dtype="auto",
)
processor = AutoProcessor.from_pretrained(model_id, trust_remote_code=True)

# Oneshot arguments
DATASET_ID = "lmms-lab/flickr30k"
DATASET_SPLIT = {"calibration": "test[:512]"}
NUM_CALIBRATION_SAMPLES = 512
MAX_SEQUENCE_LENGTH = 2048

# Load dataset and preprocess.
ds = load_dataset(DATASET_ID, split=DATASET_SPLIT)
ds = ds.shuffle(seed=42)
dampening_frac=0.01

# Apply chat template and tokenize inputs.
def preprocess_and_tokenize(example):
    # preprocess
    buffered = BytesIO()
    example["image"].save(buffered, format="PNG")
    encoded_image = base64.b64encode(buffered.getvalue())
    encoded_image_text = encoded_image.decode("utf-8")
    base64_qwen = f"data:image;base64,{encoded_image_text}"
    messages = [
        {
            "role": "user",
            "content": [
                {"type": "image", "image": base64_qwen},
                {"type": "text", "text": "What does the image show?"},
            ],
        }
    ]
    text = processor.apply_chat_template(
        messages, tokenize=False, add_generation_prompt=True
    )
    image_inputs, video_inputs = process_vision_info(messages)

    # tokenize
    return processor(
        text=[text],
        images=image_inputs,
        videos=video_inputs,
        padding=False,
        max_length=MAX_SEQUENCE_LENGTH,
        truncation=True,
    )

ds = ds.map(preprocess_and_tokenize, remove_columns=ds["calibration"].column_names)

# Recipe
recipe = GPTQModifier(
    targets="Linear",
    config_groups={
        "config_group": QuantizationScheme(
            targets=["Linear"],
            weights=QuantizationArgs(
                num_bits=4,
                type=QuantizationType.INT,
                strategy=QuantizationStrategy.GROUP,
                group_size=128,
                symmetric=True,
                dynamic=False,
                actorder=ActivationOrdering.WEIGHT,
            ),
        ),
    },
    sequential_targets=["Qwen2VLDecoderLayer"],
    ignore=["lm_head", "re:visual.*"],
    update_size=NUM_CALIBRATION_SAMPLES,
    dampening_frac=dampening_frac
)

SAVE_DIR=f"{model_id.split('/')[1]}-quantized.w4a16

# Perform oneshot
oneshot(
    model=model,
    tokenizer=model_id,
    dataset=ds,
    recipe=recipe,
    max_seq_length=MAX_SEQUENCE_LENGTH,
    num_calibration_samples=NUM_CALIBRATION_SAMPLES,
    trust_remote_code_model=True,
    data_collator=qwen2_vl_data_collator,
    output_dir=SAVE_DIR
)

Load model.pythontransformers

import base64
from io import BytesIO
import torch
from datasets import load_dataset
from qwen_vl_utils import process_vision_info
from transformers import AutoProcessor
from llmcompressor.modifiers.quantization import GPTQModifier
from llmcompressor.transformers import oneshot
from llmcompressor.transformers.tracing import TraceableQwen2VLForConditionalGeneration
from llmcompressor.transformers.utils.data_collator import qwen2_vl_data_collator
from compressed_tensors.quantization import QuantizationArgs, QuantizationType, QuantizationStrategy, ActivationOrdering, QuantizationScheme

# Load model.
model_id = "Qwen/Qwen2-VL-72B-Instruct"

model = TraceableQwen2VLForConditionalGeneration.from_pretrained(
    model_id,
    device_map="auto",
    torch_dtype="auto",
)
processor = AutoProcessor.from_pretrained(model_id, trust_remote_code=True)

# Oneshot arguments
DATASET_ID = "lmms-lab/flickr30k"
DATASET_SPLIT = {"calibration": "test[:512]"}
NUM_CALIBRATION_SAMPLES = 512
MAX_SEQUENCE_LENGTH = 2048

# Load dataset and preprocess.
ds = load_dataset(DATASET_ID, split=DATASET_SPLIT)
ds = ds.shuffle(seed=42)
dampening_frac=0.01

# Apply chat template and tokenize inputs.
def preprocess_and_tokenize(example):
    # preprocess
    buffered = BytesIO()
    example["image"].save(buffered, format="PNG")
    encoded_image = base64.b64encode(buffered.getvalue())
    encoded_image_text = encoded_image.decode("utf-8")
    base64_qwen = f"data:image;base64,{encoded_image_text}"
    messages = [
        {
            "role": "user",
            "content": [
                {"type": "image", "image": base64_qwen},
                {"type": "text", "text": "What does the image show?"},
            ],
        }
    ]
    text = processor.apply_chat_template(
        messages, tokenize=False, add_generation_prompt=True
    )
    image_inputs, video_inputs = process_vision_info(messages)

    # tokenize
    return processor(
        text=[text],
        images=image_inputs,
        videos=video_inputs,
        padding=False,
        max_length=MAX_SEQUENCE_LENGTH,
        truncation=True,
    )

ds = ds.map(preprocess_and_tokenize, remove_columns=ds["calibration"].column_names)

# Recipe
recipe = GPTQModifier(
    targets="Linear",
    config_groups={
        "config_group": QuantizationScheme(
            targets=["Linear"],
            weights=QuantizationArgs(
                num_bits=4,
                type=QuantizationType.INT,
                strategy=QuantizationStrategy.GROUP,
                group_size=128,
                symmetric=True,
                dynamic=False,
                actorder=ActivationOrdering.WEIGHT,
            ),
        ),
    },
    sequential_targets=["Qwen2VLDecoderLayer"],
    ignore=["lm_head", "re:visual.*"],
    update_size=NUM_CALIBRATION_SAMPLES,
    dampening_frac=dampening_frac
)

SAVE_DIR=f"{model_id.split('/')[1]}-quantized.w4a16

# Perform oneshot
oneshot(
    model=model,
    tokenizer=model_id,
    dataset=ds,
    recipe=recipe,
    max_seq_length=MAX_SEQUENCE_LENGTH,
    num_calibration_samples=NUM_CALIBRATION_SAMPLES,
    trust_remote_code_model=True,
    data_collator=qwen2_vl_data_collator,
    output_dir=SAVE_DIR
)

Load model.pythontransformers

import base64
from io import BytesIO
import torch
from datasets import load_dataset
from qwen_vl_utils import process_vision_info
from transformers import AutoProcessor
from llmcompressor.modifiers.quantization import GPTQModifier
from llmcompressor.transformers import oneshot
from llmcompressor.transformers.tracing import TraceableQwen2VLForConditionalGeneration
from llmcompressor.transformers.utils.data_collator import qwen2_vl_data_collator
from compressed_tensors.quantization import QuantizationArgs, QuantizationType, QuantizationStrategy, ActivationOrdering, QuantizationScheme

# Load model.
model_id = "Qwen/Qwen2-VL-72B-Instruct"

model = TraceableQwen2VLForConditionalGeneration.from_pretrained(
    model_id,
    device_map="auto",
    torch_dtype="auto",
)
processor = AutoProcessor.from_pretrained(model_id, trust_remote_code=True)

# Oneshot arguments
DATASET_ID = "lmms-lab/flickr30k"
DATASET_SPLIT = {"calibration": "test[:512]"}
NUM_CALIBRATION_SAMPLES = 512
MAX_SEQUENCE_LENGTH = 2048

# Load dataset and preprocess.
ds = load_dataset(DATASET_ID, split=DATASET_SPLIT)
ds = ds.shuffle(seed=42)
dampening_frac=0.01

# Apply chat template and tokenize inputs.
def preprocess_and_tokenize(example):
    # preprocess
    buffered = BytesIO()
    example["image"].save(buffered, format="PNG")
    encoded_image = base64.b64encode(buffered.getvalue())
    encoded_image_text = encoded_image.decode("utf-8")
    base64_qwen = f"data:image;base64,{encoded_image_text}"
    messages = [
        {
            "role": "user",
            "content": [
                {"type": "image", "image": base64_qwen},
                {"type": "text", "text": "What does the image show?"},
            ],
        }
    ]
    text = processor.apply_chat_template(
        messages, tokenize=False, add_generation_prompt=True
    )
    image_inputs, video_inputs = process_vision_info(messages)

    # tokenize
    return processor(
        text=[text],
        images=image_inputs,
        videos=video_inputs,
        padding=False,
        max_length=MAX_SEQUENCE_LENGTH,
        truncation=True,
    )

ds = ds.map(preprocess_and_tokenize, remove_columns=ds["calibration"].column_names)

# Recipe
recipe = GPTQModifier(
    targets="Linear",
    config_groups={
        "config_group": QuantizationScheme(
            targets=["Linear"],
            weights=QuantizationArgs(
                num_bits=4,
                type=QuantizationType.INT,
                strategy=QuantizationStrategy.GROUP,
                group_size=128,
                symmetric=True,
                dynamic=False,
                actorder=ActivationOrdering.WEIGHT,
            ),
        ),
    },
    sequential_targets=["Qwen2VLDecoderLayer"],
    ignore=["lm_head", "re:visual.*"],
    update_size=NUM_CALIBRATION_SAMPLES,
    dampening_frac=dampening_frac
)

SAVE_DIR=f"{model_id.split('/')[1]}-quantized.w4a16

# Perform oneshot
oneshot(
    model=model,
    tokenizer=model_id,
    dataset=ds,
    recipe=recipe,
    max_seq_length=MAX_SEQUENCE_LENGTH,
    num_calibration_samples=NUM_CALIBRATION_SAMPLES,
    trust_remote_code_model=True,
    data_collator=qwen2_vl_data_collator,
    output_dir=SAVE_DIR
)

Load model.pythontransformers

import base64
from io import BytesIO
import torch
from datasets import load_dataset
from qwen_vl_utils import process_vision_info
from transformers import AutoProcessor
from llmcompressor.modifiers.quantization import GPTQModifier
from llmcompressor.transformers import oneshot
from llmcompressor.transformers.tracing import TraceableQwen2VLForConditionalGeneration
from llmcompressor.transformers.utils.data_collator import qwen2_vl_data_collator
from compressed_tensors.quantization import QuantizationArgs, QuantizationType, QuantizationStrategy, ActivationOrdering, QuantizationScheme

# Load model.
model_id = "Qwen/Qwen2-VL-72B-Instruct"

model = TraceableQwen2VLForConditionalGeneration.from_pretrained(
    model_id,
    device_map="auto",
    torch_dtype="auto",
)
processor = AutoProcessor.from_pretrained(model_id, trust_remote_code=True)

# Oneshot arguments
DATASET_ID = "lmms-lab/flickr30k"
DATASET_SPLIT = {"calibration": "test[:512]"}
NUM_CALIBRATION_SAMPLES = 512
MAX_SEQUENCE_LENGTH = 2048

# Load dataset and preprocess.
ds = load_dataset(DATASET_ID, split=DATASET_SPLIT)
ds = ds.shuffle(seed=42)
dampening_frac=0.01

# Apply chat template and tokenize inputs.
def preprocess_and_tokenize(example):
    # preprocess
    buffered = BytesIO()
    example["image"].save(buffered, format="PNG")
    encoded_image = base64.b64encode(buffered.getvalue())
    encoded_image_text = encoded_image.decode("utf-8")
    base64_qwen = f"data:image;base64,{encoded_image_text}"
    messages = [
        {
            "role": "user",
            "content": [
                {"type": "image", "image": base64_qwen},
                {"type": "text", "text": "What does the image show?"},
            ],
        }
    ]
    text = processor.apply_chat_template(
        messages, tokenize=False, add_generation_prompt=True
    )
    image_inputs, video_inputs = process_vision_info(messages)

    # tokenize
    return processor(
        text=[text],
        images=image_inputs,
        videos=video_inputs,
        padding=False,
        max_length=MAX_SEQUENCE_LENGTH,
        truncation=True,
    )

ds = ds.map(preprocess_and_tokenize, remove_columns=ds["calibration"].column_names)

# Recipe
recipe = GPTQModifier(
    targets="Linear",
    config_groups={
        "config_group": QuantizationScheme(
            targets=["Linear"],
            weights=QuantizationArgs(
                num_bits=4,
                type=QuantizationType.INT,
                strategy=QuantizationStrategy.GROUP,
                group_size=128,
                symmetric=True,
                dynamic=False,
                actorder=ActivationOrdering.WEIGHT,
            ),
        ),
    },
    sequential_targets=["Qwen2VLDecoderLayer"],
    ignore=["lm_head", "re:visual.*"],
    update_size=NUM_CALIBRATION_SAMPLES,
    dampening_frac=dampening_frac
)

SAVE_DIR=f"{model_id.split('/')[1]}-quantized.w4a16

# Perform oneshot
oneshot(
    model=model,
    tokenizer=model_id,
    dataset=ds,
    recipe=recipe,
    max_seq_length=MAX_SEQUENCE_LENGTH,
    num_calibration_samples=NUM_CALIBRATION_SAMPLES,
    trust_remote_code_model=True,
    data_collator=qwen2_vl_data_collator,
    output_dir=SAVE_DIR
)

Load model.pythontransformers

import base64
from io import BytesIO
import torch
from datasets import load_dataset
from qwen_vl_utils import process_vision_info
from transformers import AutoProcessor
from llmcompressor.modifiers.quantization import GPTQModifier
from llmcompressor.transformers import oneshot
from llmcompressor.transformers.tracing import TraceableQwen2VLForConditionalGeneration
from llmcompressor.transformers.utils.data_collator import qwen2_vl_data_collator
from compressed_tensors.quantization import QuantizationArgs, QuantizationType, QuantizationStrategy, ActivationOrdering, QuantizationScheme

# Load model.
model_id = "Qwen/Qwen2-VL-72B-Instruct"

model = TraceableQwen2VLForConditionalGeneration.from_pretrained(
    model_id,
    device_map="auto",
    torch_dtype="auto",
)
processor = AutoProcessor.from_pretrained(model_id, trust_remote_code=True)

# Oneshot arguments
DATASET_ID = "lmms-lab/flickr30k"
DATASET_SPLIT = {"calibration": "test[:512]"}
NUM_CALIBRATION_SAMPLES = 512
MAX_SEQUENCE_LENGTH = 2048

# Load dataset and preprocess.
ds = load_dataset(DATASET_ID, split=DATASET_SPLIT)
ds = ds.shuffle(seed=42)
dampening_frac=0.01

# Apply chat template and tokenize inputs.
def preprocess_and_tokenize(example):
    # preprocess
    buffered = BytesIO()
    example["image"].save(buffered, format="PNG")
    encoded_image = base64.b64encode(buffered.getvalue())
    encoded_image_text = encoded_image.decode("utf-8")
    base64_qwen = f"data:image;base64,{encoded_image_text}"
    messages = [
        {
            "role": "user",
            "content": [
                {"type": "image", "image": base64_qwen},
                {"type": "text", "text": "What does the image show?"},
            ],
        }
    ]
    text = processor.apply_chat_template(
        messages, tokenize=False, add_generation_prompt=True
    )
    image_inputs, video_inputs = process_vision_info(messages)

    # tokenize
    return processor(
        text=[text],
        images=image_inputs,
        videos=video_inputs,
        padding=False,
        max_length=MAX_SEQUENCE_LENGTH,
        truncation=True,
    )

ds = ds.map(preprocess_and_tokenize, remove_columns=ds["calibration"].column_names)

# Recipe
recipe = GPTQModifier(
    targets="Linear",
    config_groups={
        "config_group": QuantizationScheme(
            targets=["Linear"],
            weights=QuantizationArgs(
                num_bits=4,
                type=QuantizationType.INT,
                strategy=QuantizationStrategy.GROUP,
                group_size=128,
                symmetric=True,
                dynamic=False,
                actorder=ActivationOrdering.WEIGHT,
            ),
        ),
    },
    sequential_targets=["Qwen2VLDecoderLayer"],
    ignore=["lm_head", "re:visual.*"],
    update_size=NUM_CALIBRATION_SAMPLES,
    dampening_frac=dampening_frac
)

SAVE_DIR=f"{model_id.split('/')[1]}-quantized.w4a16

# Perform oneshot
oneshot(
    model=model,
    tokenizer=model_id,
    dataset=ds,
    recipe=recipe,
    max_seq_length=MAX_SEQUENCE_LENGTH,
    num_calibration_samples=NUM_CALIBRATION_SAMPLES,
    trust_remote_code_model=True,
    data_collator=qwen2_vl_data_collator,
    output_dir=SAVE_DIR
)

Load model.pythontransformers

import base64
from io import BytesIO
import torch
from datasets import load_dataset
from qwen_vl_utils import process_vision_info
from transformers import AutoProcessor
from llmcompressor.modifiers.quantization import GPTQModifier
from llmcompressor.transformers import oneshot
from llmcompressor.transformers.tracing import TraceableQwen2VLForConditionalGeneration
from llmcompressor.transformers.utils.data_collator import qwen2_vl_data_collator
from compressed_tensors.quantization import QuantizationArgs, QuantizationType, QuantizationStrategy, ActivationOrdering, QuantizationScheme

# Load model.
model_id = "Qwen/Qwen2-VL-72B-Instruct"

model = TraceableQwen2VLForConditionalGeneration.from_pretrained(
    model_id,
    device_map="auto",
    torch_dtype="auto",
)
processor = AutoProcessor.from_pretrained(model_id, trust_remote_code=True)

# Oneshot arguments
DATASET_ID = "lmms-lab/flickr30k"
DATASET_SPLIT = {"calibration": "test[:512]"}
NUM_CALIBRATION_SAMPLES = 512
MAX_SEQUENCE_LENGTH = 2048

# Load dataset and preprocess.
ds = load_dataset(DATASET_ID, split=DATASET_SPLIT)
ds = ds.shuffle(seed=42)
dampening_frac=0.01

# Apply chat template and tokenize inputs.
def preprocess_and_tokenize(example):
    # preprocess
    buffered = BytesIO()
    example["image"].save(buffered, format="PNG")
    encoded_image = base64.b64encode(buffered.getvalue())
    encoded_image_text = encoded_image.decode("utf-8")
    base64_qwen = f"data:image;base64,{encoded_image_text}"
    messages = [
        {
            "role": "user",
            "content": [
                {"type": "image", "image": base64_qwen},
                {"type": "text", "text": "What does the image show?"},
            ],
        }
    ]
    text = processor.apply_chat_template(
        messages, tokenize=False, add_generation_prompt=True
    )
    image_inputs, video_inputs = process_vision_info(messages)

    # tokenize
    return processor(
        text=[text],
        images=image_inputs,
        videos=video_inputs,
        padding=False,
        max_length=MAX_SEQUENCE_LENGTH,
        truncation=True,
    )

ds = ds.map(preprocess_and_tokenize, remove_columns=ds["calibration"].column_names)

# Recipe
recipe = GPTQModifier(
    targets="Linear",
    config_groups={
        "config_group": QuantizationScheme(
            targets=["Linear"],
            weights=QuantizationArgs(
                num_bits=4,
                type=QuantizationType.INT,
                strategy=QuantizationStrategy.GROUP,
                group_size=128,
                symmetric=True,
                dynamic=False,
                actorder=ActivationOrdering.WEIGHT,
            ),
        ),
    },
    sequential_targets=["Qwen2VLDecoderLayer"],
    ignore=["lm_head", "re:visual.*"],
    update_size=NUM_CALIBRATION_SAMPLES,
    dampening_frac=dampening_frac
)

SAVE_DIR=f"{model_id.split('/')[1]}-quantized.w4a16

# Perform oneshot
oneshot(
    model=model,
    tokenizer=model_id,
    dataset=ds,
    recipe=recipe,
    max_seq_length=MAX_SEQUENCE_LENGTH,
    num_calibration_samples=NUM_CALIBRATION_SAMPLES,
    trust_remote_code_model=True,
    data_collator=qwen2_vl_data_collator,
    output_dir=SAVE_DIR
)

Load model.pythontransformers

import base64
from io import BytesIO
import torch
from datasets import load_dataset
from qwen_vl_utils import process_vision_info
from transformers import AutoProcessor
from llmcompressor.modifiers.quantization import GPTQModifier
from llmcompressor.transformers import oneshot
from llmcompressor.transformers.tracing import TraceableQwen2VLForConditionalGeneration
from llmcompressor.transformers.utils.data_collator import qwen2_vl_data_collator
from compressed_tensors.quantization import QuantizationArgs, QuantizationType, QuantizationStrategy, ActivationOrdering, QuantizationScheme

# Load model.
model_id = "Qwen/Qwen2-VL-72B-Instruct"

model = TraceableQwen2VLForConditionalGeneration.from_pretrained(
    model_id,
    device_map="auto",
    torch_dtype="auto",
)
processor = AutoProcessor.from_pretrained(model_id, trust_remote_code=True)

# Oneshot arguments
DATASET_ID = "lmms-lab/flickr30k"
DATASET_SPLIT = {"calibration": "test[:512]"}
NUM_CALIBRATION_SAMPLES = 512
MAX_SEQUENCE_LENGTH = 2048

# Load dataset and preprocess.
ds = load_dataset(DATASET_ID, split=DATASET_SPLIT)
ds = ds.shuffle(seed=42)
dampening_frac=0.01

# Apply chat template and tokenize inputs.
def preprocess_and_tokenize(example):
    # preprocess
    buffered = BytesIO()
    example["image"].save(buffered, format="PNG")
    encoded_image = base64.b64encode(buffered.getvalue())
    encoded_image_text = encoded_image.decode("utf-8")
    base64_qwen = f"data:image;base64,{encoded_image_text}"
    messages = [
        {
            "role": "user",
            "content": [
                {"type": "image", "image": base64_qwen},
                {"type": "text", "text": "What does the image show?"},
            ],
        }
    ]
    text = processor.apply_chat_template(
        messages, tokenize=False, add_generation_prompt=True
    )
    image_inputs, video_inputs = process_vision_info(messages)

    # tokenize
    return processor(
        text=[text],
        images=image_inputs,
        videos=video_inputs,
        padding=False,
        max_length=MAX_SEQUENCE_LENGTH,
        truncation=True,
    )

ds = ds.map(preprocess_and_tokenize, remove_columns=ds["calibration"].column_names)

# Recipe
recipe = GPTQModifier(
    targets="Linear",
    config_groups={
        "config_group": QuantizationScheme(
            targets=["Linear"],
            weights=QuantizationArgs(
                num_bits=4,
                type=QuantizationType.INT,
                strategy=QuantizationStrategy.GROUP,
                group_size=128,
                symmetric=True,
                dynamic=False,
                actorder=ActivationOrdering.WEIGHT,
            ),
        ),
    },
    sequential_targets=["Qwen2VLDecoderLayer"],
    ignore=["lm_head", "re:visual.*"],
    update_size=NUM_CALIBRATION_SAMPLES,
    dampening_frac=dampening_frac
)

SAVE_DIR=f"{model_id.split('/')[1]}-quantized.w4a16

# Perform oneshot
oneshot(
    model=model,
    tokenizer=model_id,
    dataset=ds,
    recipe=recipe,
    max_seq_length=MAX_SEQUENCE_LENGTH,
    num_calibration_samples=NUM_CALIBRATION_SAMPLES,
    trust_remote_code_model=True,
    data_collator=qwen2_vl_data_collator,
    output_dir=SAVE_DIR
)

Load model.pythontransformers

import base64
from io import BytesIO
import torch
from datasets import load_dataset
from qwen_vl_utils import process_vision_info
from transformers import AutoProcessor
from llmcompressor.modifiers.quantization import GPTQModifier
from llmcompressor.transformers import oneshot
from llmcompressor.transformers.tracing import TraceableQwen2VLForConditionalGeneration
from llmcompressor.transformers.utils.data_collator import qwen2_vl_data_collator
from compressed_tensors.quantization import QuantizationArgs, QuantizationType, QuantizationStrategy, ActivationOrdering, QuantizationScheme

# Load model.
model_id = "Qwen/Qwen2-VL-72B-Instruct"

model = TraceableQwen2VLForConditionalGeneration.from_pretrained(
    model_id,
    device_map="auto",
    torch_dtype="auto",
)
processor = AutoProcessor.from_pretrained(model_id, trust_remote_code=True)

# Oneshot arguments
DATASET_ID = "lmms-lab/flickr30k"
DATASET_SPLIT = {"calibration": "test[:512]"}
NUM_CALIBRATION_SAMPLES = 512
MAX_SEQUENCE_LENGTH = 2048

# Load dataset and preprocess.
ds = load_dataset(DATASET_ID, split=DATASET_SPLIT)
ds = ds.shuffle(seed=42)
dampening_frac=0.01

# Apply chat template and tokenize inputs.
def preprocess_and_tokenize(example):
    # preprocess
    buffered = BytesIO()
    example["image"].save(buffered, format="PNG")
    encoded_image = base64.b64encode(buffered.getvalue())
    encoded_image_text = encoded_image.decode("utf-8")
    base64_qwen = f"data:image;base64,{encoded_image_text}"
    messages = [
        {
            "role": "user",
            "content": [
                {"type": "image", "image": base64_qwen},
                {"type": "text", "text": "What does the image show?"},
            ],
        }
    ]
    text = processor.apply_chat_template(
        messages, tokenize=False, add_generation_prompt=True
    )
    image_inputs, video_inputs = process_vision_info(messages)

    # tokenize
    return processor(
        text=[text],
        images=image_inputs,
        videos=video_inputs,
        padding=False,
        max_length=MAX_SEQUENCE_LENGTH,
        truncation=True,
    )

ds = ds.map(preprocess_and_tokenize, remove_columns=ds["calibration"].column_names)

# Recipe
recipe = GPTQModifier(
    targets="Linear",
    config_groups={
        "config_group": QuantizationScheme(
            targets=["Linear"],
            weights=QuantizationArgs(
                num_bits=4,
                type=QuantizationType.INT,
                strategy=QuantizationStrategy.GROUP,
                group_size=128,
                symmetric=True,
                dynamic=False,
                actorder=ActivationOrdering.WEIGHT,
            ),
        ),
    },
    sequential_targets=["Qwen2VLDecoderLayer"],
    ignore=["lm_head", "re:visual.*"],
    update_size=NUM_CALIBRATION_SAMPLES,
    dampening_frac=dampening_frac
)

SAVE_DIR=f"{model_id.split('/')[1]}-quantized.w4a16

# Perform oneshot
oneshot(
    model=model,
    tokenizer=model_id,
    dataset=ds,
    recipe=recipe,
    max_seq_length=MAX_SEQUENCE_LENGTH,
    num_calibration_samples=NUM_CALIBRATION_SAMPLES,
    trust_remote_code_model=True,
    data_collator=qwen2_vl_data_collator,
    output_dir=SAVE_DIR
)

Load model.pythontransformers

import base64
from io import BytesIO
import torch
from datasets import load_dataset
from qwen_vl_utils import process_vision_info
from transformers import AutoProcessor
from llmcompressor.modifiers.quantization import GPTQModifier
from llmcompressor.transformers import oneshot
from llmcompressor.transformers.tracing import TraceableQwen2VLForConditionalGeneration
from llmcompressor.transformers.utils.data_collator import qwen2_vl_data_collator
from compressed_tensors.quantization import QuantizationArgs, QuantizationType, QuantizationStrategy, ActivationOrdering, QuantizationScheme

# Load model.
model_id = "Qwen/Qwen2-VL-72B-Instruct"

model = TraceableQwen2VLForConditionalGeneration.from_pretrained(
    model_id,
    device_map="auto",
    torch_dtype="auto",
)
processor = AutoProcessor.from_pretrained(model_id, trust_remote_code=True)

# Oneshot arguments
DATASET_ID = "lmms-lab/flickr30k"
DATASET_SPLIT = {"calibration": "test[:512]"}
NUM_CALIBRATION_SAMPLES = 512
MAX_SEQUENCE_LENGTH = 2048

# Load dataset and preprocess.
ds = load_dataset(DATASET_ID, split=DATASET_SPLIT)
ds = ds.shuffle(seed=42)
dampening_frac=0.01

# Apply chat template and tokenize inputs.
def preprocess_and_tokenize(example):
    # preprocess
    buffered = BytesIO()
    example["image"].save(buffered, format="PNG")
    encoded_image = base64.b64encode(buffered.getvalue())
    encoded_image_text = encoded_image.decode("utf-8")
    base64_qwen = f"data:image;base64,{encoded_image_text}"
    messages = [
        {
            "role": "user",
            "content": [
                {"type": "image", "image": base64_qwen},
                {"type": "text", "text": "What does the image show?"},
            ],
        }
    ]
    text = processor.apply_chat_template(
        messages, tokenize=False, add_generation_prompt=True
    )
    image_inputs, video_inputs = process_vision_info(messages)

    # tokenize
    return processor(
        text=[text],
        images=image_inputs,
        videos=video_inputs,
        padding=False,
        max_length=MAX_SEQUENCE_LENGTH,
        truncation=True,
    )

ds = ds.map(preprocess_and_tokenize, remove_columns=ds["calibration"].column_names)

# Recipe
recipe = GPTQModifier(
    targets="Linear",
    config_groups={
        "config_group": QuantizationScheme(
            targets=["Linear"],
            weights=QuantizationArgs(
                num_bits=4,
                type=QuantizationType.INT,
                strategy=QuantizationStrategy.GROUP,
                group_size=128,
                symmetric=True,
                dynamic=False,
                actorder=ActivationOrdering.WEIGHT,
            ),
        ),
    },
    sequential_targets=["Qwen2VLDecoderLayer"],
    ignore=["lm_head", "re:visual.*"],
    update_size=NUM_CALIBRATION_SAMPLES,
    dampening_frac=dampening_frac
)

SAVE_DIR=f"{model_id.split('/')[1]}-quantized.w4a16

# Perform oneshot
oneshot(
    model=model,
    tokenizer=model_id,
    dataset=ds,
    recipe=recipe,
    max_seq_length=MAX_SEQUENCE_LENGTH,
    num_calibration_samples=NUM_CALIBRATION_SAMPLES,
    trust_remote_code_model=True,
    data_collator=qwen2_vl_data_collator,
    output_dir=SAVE_DIR
)

Load model.pythontransformers

import base64
from io import BytesIO
import torch
from datasets import load_dataset
from qwen_vl_utils import process_vision_info
from transformers import AutoProcessor
from llmcompressor.modifiers.quantization import GPTQModifier
from llmcompressor.transformers import oneshot
from llmcompressor.transformers.tracing import TraceableQwen2VLForConditionalGeneration
from llmcompressor.transformers.utils.data_collator import qwen2_vl_data_collator
from compressed_tensors.quantization import QuantizationArgs, QuantizationType, QuantizationStrategy, ActivationOrdering, QuantizationScheme

# Load model.
model_id = "Qwen/Qwen2-VL-72B-Instruct"

model = TraceableQwen2VLForConditionalGeneration.from_pretrained(
    model_id,
    device_map="auto",
    torch_dtype="auto",
)
processor = AutoProcessor.from_pretrained(model_id, trust_remote_code=True)

# Oneshot arguments
DATASET_ID = "lmms-lab/flickr30k"
DATASET_SPLIT = {"calibration": "test[:512]"}
NUM_CALIBRATION_SAMPLES = 512
MAX_SEQUENCE_LENGTH = 2048

# Load dataset and preprocess.
ds = load_dataset(DATASET_ID, split=DATASET_SPLIT)
ds = ds.shuffle(seed=42)
dampening_frac=0.01

# Apply chat template and tokenize inputs.
def preprocess_and_tokenize(example):
    # preprocess
    buffered = BytesIO()
    example["image"].save(buffered, format="PNG")
    encoded_image = base64.b64encode(buffered.getvalue())
    encoded_image_text = encoded_image.decode("utf-8")
    base64_qwen = f"data:image;base64,{encoded_image_text}"
    messages = [
        {
            "role": "user",
            "content": [
                {"type": "image", "image": base64_qwen},
                {"type": "text", "text": "What does the image show?"},
            ],
        }
    ]
    text = processor.apply_chat_template(
        messages, tokenize=False, add_generation_prompt=True
    )
    image_inputs, video_inputs = process_vision_info(messages)

    # tokenize
    return processor(
        text=[text],
        images=image_inputs,
        videos=video_inputs,
        padding=False,
        max_length=MAX_SEQUENCE_LENGTH,
        truncation=True,
    )

ds = ds.map(preprocess_and_tokenize, remove_columns=ds["calibration"].column_names)

# Recipe
recipe = GPTQModifier(
    targets="Linear",
    config_groups={
        "config_group": QuantizationScheme(
            targets=["Linear"],
            weights=QuantizationArgs(
                num_bits=4,
                type=QuantizationType.INT,
                strategy=QuantizationStrategy.GROUP,
                group_size=128,
                symmetric=True,
                dynamic=False,
                actorder=ActivationOrdering.WEIGHT,
            ),
        ),
    },
    sequential_targets=["Qwen2VLDecoderLayer"],
    ignore=["lm_head", "re:visual.*"],
    update_size=NUM_CALIBRATION_SAMPLES,
    dampening_frac=dampening_frac
)

SAVE_DIR=f"{model_id.split('/')[1]}-quantized.w4a16

# Perform oneshot
oneshot(
    model=model,
    tokenizer=model_id,
    dataset=ds,
    recipe=recipe,
    max_seq_length=MAX_SEQUENCE_LENGTH,
    num_calibration_samples=NUM_CALIBRATION_SAMPLES,
    trust_remote_code_model=True,
    data_collator=qwen2_vl_data_collator,
    output_dir=SAVE_DIR
)

Load model.pythontransformers

import base64
from io import BytesIO
import torch
from datasets import load_dataset
from qwen_vl_utils import process_vision_info
from transformers import AutoProcessor
from llmcompressor.modifiers.quantization import GPTQModifier
from llmcompressor.transformers import oneshot
from llmcompressor.transformers.tracing import TraceableQwen2VLForConditionalGeneration
from llmcompressor.transformers.utils.data_collator import qwen2_vl_data_collator
from compressed_tensors.quantization import QuantizationArgs, QuantizationType, QuantizationStrategy, ActivationOrdering, QuantizationScheme

# Load model.
model_id = "Qwen/Qwen2-VL-72B-Instruct"

model = TraceableQwen2VLForConditionalGeneration.from_pretrained(
    model_id,
    device_map="auto",
    torch_dtype="auto",
)
processor = AutoProcessor.from_pretrained(model_id, trust_remote_code=True)

# Oneshot arguments
DATASET_ID = "lmms-lab/flickr30k"
DATASET_SPLIT = {"calibration": "test[:512]"}
NUM_CALIBRATION_SAMPLES = 512
MAX_SEQUENCE_LENGTH = 2048

# Load dataset and preprocess.
ds = load_dataset(DATASET_ID, split=DATASET_SPLIT)
ds = ds.shuffle(seed=42)
dampening_frac=0.01

# Apply chat template and tokenize inputs.
def preprocess_and_tokenize(example):
    # preprocess
    buffered = BytesIO()
    example["image"].save(buffered, format="PNG")
    encoded_image = base64.b64encode(buffered.getvalue())
    encoded_image_text = encoded_image.decode("utf-8")
    base64_qwen = f"data:image;base64,{encoded_image_text}"
    messages = [
        {
            "role": "user",
            "content": [
                {"type": "image", "image": base64_qwen},
                {"type": "text", "text": "What does the image show?"},
            ],
        }
    ]
    text = processor.apply_chat_template(
        messages, tokenize=False, add_generation_prompt=True
    )
    image_inputs, video_inputs = process_vision_info(messages)

    # tokenize
    return processor(
        text=[text],
        images=image_inputs,
        videos=video_inputs,
        padding=False,
        max_length=MAX_SEQUENCE_LENGTH,
        truncation=True,
    )

ds = ds.map(preprocess_and_tokenize, remove_columns=ds["calibration"].column_names)

# Recipe
recipe = GPTQModifier(
    targets="Linear",
    config_groups={
        "config_group": QuantizationScheme(
            targets=["Linear"],
            weights=QuantizationArgs(
                num_bits=4,
                type=QuantizationType.INT,
                strategy=QuantizationStrategy.GROUP,
                group_size=128,
                symmetric=True,
                dynamic=False,
                actorder=ActivationOrdering.WEIGHT,
            ),
        ),
    },
    sequential_targets=["Qwen2VLDecoderLayer"],
    ignore=["lm_head", "re:visual.*"],
    update_size=NUM_CALIBRATION_SAMPLES,
    dampening_frac=dampening_frac
)

SAVE_DIR=f"{model_id.split('/')[1]}-quantized.w4a16

# Perform oneshot
oneshot(
    model=model,
    tokenizer=model_id,
    dataset=ds,
    recipe=recipe,
    max_seq_length=MAX_SEQUENCE_LENGTH,
    num_calibration_samples=NUM_CALIBRATION_SAMPLES,
    trust_remote_code_model=True,
    data_collator=qwen2_vl_data_collator,
    output_dir=SAVE_DIR
)

Load model.pythontransformers

import base64
from io import BytesIO
import torch
from datasets import load_dataset
from qwen_vl_utils import process_vision_info
from transformers import AutoProcessor
from llmcompressor.modifiers.quantization import GPTQModifier
from llmcompressor.transformers import oneshot
from llmcompressor.transformers.tracing import TraceableQwen2VLForConditionalGeneration
from llmcompressor.transformers.utils.data_collator import qwen2_vl_data_collator
from compressed_tensors.quantization import QuantizationArgs, QuantizationType, QuantizationStrategy, ActivationOrdering, QuantizationScheme

# Load model.
model_id = "Qwen/Qwen2-VL-72B-Instruct"

model = TraceableQwen2VLForConditionalGeneration.from_pretrained(
    model_id,
    device_map="auto",
    torch_dtype="auto",
)
processor = AutoProcessor.from_pretrained(model_id, trust_remote_code=True)

# Oneshot arguments
DATASET_ID = "lmms-lab/flickr30k"
DATASET_SPLIT = {"calibration": "test[:512]"}
NUM_CALIBRATION_SAMPLES = 512
MAX_SEQUENCE_LENGTH = 2048

# Load dataset and preprocess.
ds = load_dataset(DATASET_ID, split=DATASET_SPLIT)
ds = ds.shuffle(seed=42)
dampening_frac=0.01

# Apply chat template and tokenize inputs.
def preprocess_and_tokenize(example):
    # preprocess
    buffered = BytesIO()
    example["image"].save(buffered, format="PNG")
    encoded_image = base64.b64encode(buffered.getvalue())
    encoded_image_text = encoded_image.decode("utf-8")
    base64_qwen = f"data:image;base64,{encoded_image_text}"
    messages = [
        {
            "role": "user",
            "content": [
                {"type": "image", "image": base64_qwen},
                {"type": "text", "text": "What does the image show?"},
            ],
        }
    ]
    text = processor.apply_chat_template(
        messages, tokenize=False, add_generation_prompt=True
    )
    image_inputs, video_inputs = process_vision_info(messages)

    # tokenize
    return processor(
        text=[text],
        images=image_inputs,
        videos=video_inputs,
        padding=False,
        max_length=MAX_SEQUENCE_LENGTH,
        truncation=True,
    )

ds = ds.map(preprocess_and_tokenize, remove_columns=ds["calibration"].column_names)

# Recipe
recipe = GPTQModifier(
    targets="Linear",
    config_groups={
        "config_group": QuantizationScheme(
            targets=["Linear"],
            weights=QuantizationArgs(
                num_bits=4,
                type=QuantizationType.INT,
                strategy=QuantizationStrategy.GROUP,
                group_size=128,
                symmetric=True,
                dynamic=False,
                actorder=ActivationOrdering.WEIGHT,
            ),
        ),
    },
    sequential_targets=["Qwen2VLDecoderLayer"],
    ignore=["lm_head", "re:visual.*"],
    update_size=NUM_CALIBRATION_SAMPLES,
    dampening_frac=dampening_frac
)

SAVE_DIR=f"{model_id.split('/')[1]}-quantized.w4a16

# Perform oneshot
oneshot(
    model=model,
    tokenizer=model_id,
    dataset=ds,
    recipe=recipe,
    max_seq_length=MAX_SEQUENCE_LENGTH,
    num_calibration_samples=NUM_CALIBRATION_SAMPLES,
    trust_remote_code_model=True,
    data_collator=qwen2_vl_data_collator,
    output_dir=SAVE_DIR
)

Load model.pythontransformers

import base64
from io import BytesIO
import torch
from datasets import load_dataset
from qwen_vl_utils import process_vision_info
from transformers import AutoProcessor
from llmcompressor.modifiers.quantization import GPTQModifier
from llmcompressor.transformers import oneshot
from llmcompressor.transformers.tracing import TraceableQwen2VLForConditionalGeneration
from llmcompressor.transformers.utils.data_collator import qwen2_vl_data_collator
from compressed_tensors.quantization import QuantizationArgs, QuantizationType, QuantizationStrategy, ActivationOrdering, QuantizationScheme

# Load model.
model_id = "Qwen/Qwen2-VL-72B-Instruct"

model = TraceableQwen2VLForConditionalGeneration.from_pretrained(
    model_id,
    device_map="auto",
    torch_dtype="auto",
)
processor = AutoProcessor.from_pretrained(model_id, trust_remote_code=True)

# Oneshot arguments
DATASET_ID = "lmms-lab/flickr30k"
DATASET_SPLIT = {"calibration": "test[:512]"}
NUM_CALIBRATION_SAMPLES = 512
MAX_SEQUENCE_LENGTH = 2048

# Load dataset and preprocess.
ds = load_dataset(DATASET_ID, split=DATASET_SPLIT)
ds = ds.shuffle(seed=42)
dampening_frac=0.01

# Apply chat template and tokenize inputs.
def preprocess_and_tokenize(example):
    # preprocess
    buffered = BytesIO()
    example["image"].save(buffered, format="PNG")
    encoded_image = base64.b64encode(buffered.getvalue())
    encoded_image_text = encoded_image.decode("utf-8")
    base64_qwen = f"data:image;base64,{encoded_image_text}"
    messages = [
        {
            "role": "user",
            "content": [
                {"type": "image", "image": base64_qwen},
                {"type": "text", "text": "What does the image show?"},
            ],
        }
    ]
    text = processor.apply_chat_template(
        messages, tokenize=False, add_generation_prompt=True
    )
    image_inputs, video_inputs = process_vision_info(messages)

    # tokenize
    return processor(
        text=[text],
        images=image_inputs,
        videos=video_inputs,
        padding=False,
        max_length=MAX_SEQUENCE_LENGTH,
        truncation=True,
    )

ds = ds.map(preprocess_and_tokenize, remove_columns=ds["calibration"].column_names)

# Recipe
recipe = GPTQModifier(
    targets="Linear",
    config_groups={
        "config_group": QuantizationScheme(
            targets=["Linear"],
            weights=QuantizationArgs(
                num_bits=4,
                type=QuantizationType.INT,
                strategy=QuantizationStrategy.GROUP,
                group_size=128,
                symmetric=True,
                dynamic=False,
                actorder=ActivationOrdering.WEIGHT,
            ),
        ),
    },
    sequential_targets=["Qwen2VLDecoderLayer"],
    ignore=["lm_head", "re:visual.*"],
    update_size=NUM_CALIBRATION_SAMPLES,
    dampening_frac=dampening_frac
)

SAVE_DIR=f"{model_id.split('/')[1]}-quantized.w4a16

# Perform oneshot
oneshot(
    model=model,
    tokenizer=model_id,
    dataset=ds,
    recipe=recipe,
    max_seq_length=MAX_SEQUENCE_LENGTH,
    num_calibration_samples=NUM_CALIBRATION_SAMPLES,
    trust_remote_code_model=True,
    data_collator=qwen2_vl_data_collator,
    output_dir=SAVE_DIR
)

Load model.pythontransformers

import base64
from io import BytesIO
import torch
from datasets import load_dataset
from qwen_vl_utils import process_vision_info
from transformers import AutoProcessor
from llmcompressor.modifiers.quantization import GPTQModifier
from llmcompressor.transformers import oneshot
from llmcompressor.transformers.tracing import TraceableQwen2VLForConditionalGeneration
from llmcompressor.transformers.utils.data_collator import qwen2_vl_data_collator
from compressed_tensors.quantization import QuantizationArgs, QuantizationType, QuantizationStrategy, ActivationOrdering, QuantizationScheme

# Load model.
model_id = "Qwen/Qwen2-VL-72B-Instruct"

model = TraceableQwen2VLForConditionalGeneration.from_pretrained(
    model_id,
    device_map="auto",
    torch_dtype="auto",
)
processor = AutoProcessor.from_pretrained(model_id, trust_remote_code=True)

# Oneshot arguments
DATASET_ID = "lmms-lab/flickr30k"
DATASET_SPLIT = {"calibration": "test[:512]"}
NUM_CALIBRATION_SAMPLES = 512
MAX_SEQUENCE_LENGTH = 2048

# Load dataset and preprocess.
ds = load_dataset(DATASET_ID, split=DATASET_SPLIT)
ds = ds.shuffle(seed=42)
dampening_frac=0.01

# Apply chat template and tokenize inputs.
def preprocess_and_tokenize(example):
    # preprocess
    buffered = BytesIO()
    example["image"].save(buffered, format="PNG")
    encoded_image = base64.b64encode(buffered.getvalue())
    encoded_image_text = encoded_image.decode("utf-8")
    base64_qwen = f"data:image;base64,{encoded_image_text}"
    messages = [
        {
            "role": "user",
            "content": [
                {"type": "image", "image": base64_qwen},
                {"type": "text", "text": "What does the image show?"},
            ],
        }
    ]
    text = processor.apply_chat_template(
        messages, tokenize=False, add_generation_prompt=True
    )
    image_inputs, video_inputs = process_vision_info(messages)

    # tokenize
    return processor(
        text=[text],
        images=image_inputs,
        videos=video_inputs,
        padding=False,
        max_length=MAX_SEQUENCE_LENGTH,
        truncation=True,
    )

ds = ds.map(preprocess_and_tokenize, remove_columns=ds["calibration"].column_names)

# Recipe
recipe = GPTQModifier(
    targets="Linear",
    config_groups={
        "config_group": QuantizationScheme(
            targets=["Linear"],
            weights=QuantizationArgs(
                num_bits=4,
                type=QuantizationType.INT,
                strategy=QuantizationStrategy.GROUP,
                group_size=128,
                symmetric=True,
                dynamic=False,
                actorder=ActivationOrdering.WEIGHT,
            ),
        ),
    },
    sequential_targets=["Qwen2VLDecoderLayer"],
    ignore=["lm_head", "re:visual.*"],
    update_size=NUM_CALIBRATION_SAMPLES,
    dampening_frac=dampening_frac
)

SAVE_DIR=f"{model_id.split('/')[1]}-quantized.w4a16

# Perform oneshot
oneshot(
    model=model,
    tokenizer=model_id,
    dataset=ds,
    recipe=recipe,
    max_seq_length=MAX_SEQUENCE_LENGTH,
    num_calibration_samples=NUM_CALIBRATION_SAMPLES,
    trust_remote_code_model=True,
    data_collator=qwen2_vl_data_collator,
    output_dir=SAVE_DIR
)

Load model.pythontransformers

import base64
from io import BytesIO
import torch
from datasets import load_dataset
from qwen_vl_utils import process_vision_info
from transformers import AutoProcessor
from llmcompressor.modifiers.quantization import GPTQModifier
from llmcompressor.transformers import oneshot
from llmcompressor.transformers.tracing import TraceableQwen2VLForConditionalGeneration
from llmcompressor.transformers.utils.data_collator import qwen2_vl_data_collator
from compressed_tensors.quantization import QuantizationArgs, QuantizationType, QuantizationStrategy, ActivationOrdering, QuantizationScheme

# Load model.
model_id = "Qwen/Qwen2-VL-72B-Instruct"

model = TraceableQwen2VLForConditionalGeneration.from_pretrained(
    model_id,
    device_map="auto",
    torch_dtype="auto",
)
processor = AutoProcessor.from_pretrained(model_id, trust_remote_code=True)

# Oneshot arguments
DATASET_ID = "lmms-lab/flickr30k"
DATASET_SPLIT = {"calibration": "test[:512]"}
NUM_CALIBRATION_SAMPLES = 512
MAX_SEQUENCE_LENGTH = 2048

# Load dataset and preprocess.
ds = load_dataset(DATASET_ID, split=DATASET_SPLIT)
ds = ds.shuffle(seed=42)
dampening_frac=0.01

# Apply chat template and tokenize inputs.
def preprocess_and_tokenize(example):
    # preprocess
    buffered = BytesIO()
    example["image"].save(buffered, format="PNG")
    encoded_image = base64.b64encode(buffered.getvalue())
    encoded_image_text = encoded_image.decode("utf-8")
    base64_qwen = f"data:image;base64,{encoded_image_text}"
    messages = [
        {
            "role": "user",
            "content": [
                {"type": "image", "image": base64_qwen},
                {"type": "text", "text": "What does the image show?"},
            ],
        }
    ]
    text = processor.apply_chat_template(
        messages, tokenize=False, add_generation_prompt=True
    )
    image_inputs, video_inputs = process_vision_info(messages)

    # tokenize
    return processor(
        text=[text],
        images=image_inputs,
        videos=video_inputs,
        padding=False,
        max_length=MAX_SEQUENCE_LENGTH,
        truncation=True,
    )

ds = ds.map(preprocess_and_tokenize, remove_columns=ds["calibration"].column_names)

# Recipe
recipe = GPTQModifier(
    targets="Linear",
    config_groups={
        "config_group": QuantizationScheme(
            targets=["Linear"],
            weights=QuantizationArgs(
                num_bits=4,
                type=QuantizationType.INT,
                strategy=QuantizationStrategy.GROUP,
                group_size=128,
                symmetric=True,
                dynamic=False,
                actorder=ActivationOrdering.WEIGHT,
            ),
        ),
    },
    sequential_targets=["Qwen2VLDecoderLayer"],
    ignore=["lm_head", "re:visual.*"],
    update_size=NUM_CALIBRATION_SAMPLES,
    dampening_frac=dampening_frac
)

SAVE_DIR=f"{model_id.split('/')[1]}-quantized.w4a16

# Perform oneshot
oneshot(
    model=model,
    tokenizer=model_id,
    dataset=ds,
    recipe=recipe,
    max_seq_length=MAX_SEQUENCE_LENGTH,
    num_calibration_samples=NUM_CALIBRATION_SAMPLES,
    trust_remote_code_model=True,
    data_collator=qwen2_vl_data_collator,
    output_dir=SAVE_DIR
)

Load model.pythontransformers

import base64
from io import BytesIO
import torch
from datasets import load_dataset
from qwen_vl_utils import process_vision_info
from transformers import AutoProcessor
from llmcompressor.modifiers.quantization import GPTQModifier
from llmcompressor.transformers import oneshot
from llmcompressor.transformers.tracing import TraceableQwen2VLForConditionalGeneration
from llmcompressor.transformers.utils.data_collator import qwen2_vl_data_collator
from compressed_tensors.quantization import QuantizationArgs, QuantizationType, QuantizationStrategy, ActivationOrdering, QuantizationScheme

# Load model.
model_id = "Qwen/Qwen2-VL-72B-Instruct"

model = TraceableQwen2VLForConditionalGeneration.from_pretrained(
    model_id,
    device_map="auto",
    torch_dtype="auto",
)
processor = AutoProcessor.from_pretrained(model_id, trust_remote_code=True)

# Oneshot arguments
DATASET_ID = "lmms-lab/flickr30k"
DATASET_SPLIT = {"calibration": "test[:512]"}
NUM_CALIBRATION_SAMPLES = 512
MAX_SEQUENCE_LENGTH = 2048

# Load dataset and preprocess.
ds = load_dataset(DATASET_ID, split=DATASET_SPLIT)
ds = ds.shuffle(seed=42)
dampening_frac=0.01

# Apply chat template and tokenize inputs.
def preprocess_and_tokenize(example):
    # preprocess
    buffered = BytesIO()
    example["image"].save(buffered, format="PNG")
    encoded_image = base64.b64encode(buffered.getvalue())
    encoded_image_text = encoded_image.decode("utf-8")
    base64_qwen = f"data:image;base64,{encoded_image_text}"
    messages = [
        {
            "role": "user",
            "content": [
                {"type": "image", "image": base64_qwen},
                {"type": "text", "text": "What does the image show?"},
            ],
        }
    ]
    text = processor.apply_chat_template(
        messages, tokenize=False, add_generation_prompt=True
    )
    image_inputs, video_inputs = process_vision_info(messages)

    # tokenize
    return processor(
        text=[text],
        images=image_inputs,
        videos=video_inputs,
        padding=False,
        max_length=MAX_SEQUENCE_LENGTH,
        truncation=True,
    )

ds = ds.map(preprocess_and_tokenize, remove_columns=ds["calibration"].column_names)

# Recipe
recipe = GPTQModifier(
    targets="Linear",
    config_groups={
        "config_group": QuantizationScheme(
            targets=["Linear"],
            weights=QuantizationArgs(
                num_bits=4,
                type=QuantizationType.INT,
                strategy=QuantizationStrategy.GROUP,
                group_size=128,
                symmetric=True,
                dynamic=False,
                actorder=ActivationOrdering.WEIGHT,
            ),
        ),
    },
    sequential_targets=["Qwen2VLDecoderLayer"],
    ignore=["lm_head", "re:visual.*"],
    update_size=NUM_CALIBRATION_SAMPLES,
    dampening_frac=dampening_frac
)

SAVE_DIR=f"{model_id.split('/')[1]}-quantized.w4a16

# Perform oneshot
oneshot(
    model=model,
    tokenizer=model_id,
    dataset=ds,
    recipe=recipe,
    max_seq_length=MAX_SEQUENCE_LENGTH,
    num_calibration_samples=NUM_CALIBRATION_SAMPLES,
    trust_remote_code_model=True,
    data_collator=qwen2_vl_data_collator,
    output_dir=SAVE_DIR
)

Load model.pythontransformers

import base64
from io import BytesIO
import torch
from datasets import load_dataset
from qwen_vl_utils import process_vision_info
from transformers import AutoProcessor
from llmcompressor.modifiers.quantization import GPTQModifier
from llmcompressor.transformers import oneshot
from llmcompressor.transformers.tracing import TraceableQwen2VLForConditionalGeneration
from llmcompressor.transformers.utils.data_collator import qwen2_vl_data_collator
from compressed_tensors.quantization import QuantizationArgs, QuantizationType, QuantizationStrategy, ActivationOrdering, QuantizationScheme

# Load model.
model_id = "Qwen/Qwen2-VL-72B-Instruct"

model = TraceableQwen2VLForConditionalGeneration.from_pretrained(
    model_id,
    device_map="auto",
    torch_dtype="auto",
)
processor = AutoProcessor.from_pretrained(model_id, trust_remote_code=True)

# Oneshot arguments
DATASET_ID = "lmms-lab/flickr30k"
DATASET_SPLIT = {"calibration": "test[:512]"}
NUM_CALIBRATION_SAMPLES = 512
MAX_SEQUENCE_LENGTH = 2048

# Load dataset and preprocess.
ds = load_dataset(DATASET_ID, split=DATASET_SPLIT)
ds = ds.shuffle(seed=42)
dampening_frac=0.01

# Apply chat template and tokenize inputs.
def preprocess_and_tokenize(example):
    # preprocess
    buffered = BytesIO()
    example["image"].save(buffered, format="PNG")
    encoded_image = base64.b64encode(buffered.getvalue())
    encoded_image_text = encoded_image.decode("utf-8")
    base64_qwen = f"data:image;base64,{encoded_image_text}"
    messages = [
        {
            "role": "user",
            "content": [
                {"type": "image", "image": base64_qwen},
                {"type": "text", "text": "What does the image show?"},
            ],
        }
    ]
    text = processor.apply_chat_template(
        messages, tokenize=False, add_generation_prompt=True
    )
    image_inputs, video_inputs = process_vision_info(messages)

    # tokenize
    return processor(
        text=[text],
        images=image_inputs,
        videos=video_inputs,
        padding=False,
        max_length=MAX_SEQUENCE_LENGTH,
        truncation=True,
    )

ds = ds.map(preprocess_and_tokenize, remove_columns=ds["calibration"].column_names)

# Recipe
recipe = GPTQModifier(
    targets="Linear",
    config_groups={
        "config_group": QuantizationScheme(
            targets=["Linear"],
            weights=QuantizationArgs(
                num_bits=4,
                type=QuantizationType.INT,
                strategy=QuantizationStrategy.GROUP,
                group_size=128,
                symmetric=True,
                dynamic=False,
                actorder=ActivationOrdering.WEIGHT,
            ),
        ),
    },
    sequential_targets=["Qwen2VLDecoderLayer"],
    ignore=["lm_head", "re:visual.*"],
    update_size=NUM_CALIBRATION_SAMPLES,
    dampening_frac=dampening_frac
)

SAVE_DIR=f"{model_id.split('/')[1]}-quantized.w4a16

# Perform oneshot
oneshot(
    model=model,
    tokenizer=model_id,
    dataset=ds,
    recipe=recipe,
    max_seq_length=MAX_SEQUENCE_LENGTH,
    num_calibration_samples=NUM_CALIBRATION_SAMPLES,
    trust_remote_code_model=True,
    data_collator=qwen2_vl_data_collator,
    output_dir=SAVE_DIR
)

Load model.pythontransformers

import base64
from io import BytesIO
import torch
from datasets import load_dataset
from qwen_vl_utils import process_vision_info
from transformers import AutoProcessor
from llmcompressor.modifiers.quantization import GPTQModifier
from llmcompressor.transformers import oneshot
from llmcompressor.transformers.tracing import TraceableQwen2VLForConditionalGeneration
from llmcompressor.transformers.utils.data_collator import qwen2_vl_data_collator
from compressed_tensors.quantization import QuantizationArgs, QuantizationType, QuantizationStrategy, ActivationOrdering, QuantizationScheme

# Load model.
model_id = "Qwen/Qwen2-VL-72B-Instruct"

model = TraceableQwen2VLForConditionalGeneration.from_pretrained(
    model_id,
    device_map="auto",
    torch_dtype="auto",
)
processor = AutoProcessor.from_pretrained(model_id, trust_remote_code=True)

# Oneshot arguments
DATASET_ID = "lmms-lab/flickr30k"
DATASET_SPLIT = {"calibration": "test[:512]"}
NUM_CALIBRATION_SAMPLES = 512
MAX_SEQUENCE_LENGTH = 2048

# Load dataset and preprocess.
ds = load_dataset(DATASET_ID, split=DATASET_SPLIT)
ds = ds.shuffle(seed=42)
dampening_frac=0.01

# Apply chat template and tokenize inputs.
def preprocess_and_tokenize(example):
    # preprocess
    buffered = BytesIO()
    example["image"].save(buffered, format="PNG")
    encoded_image = base64.b64encode(buffered.getvalue())
    encoded_image_text = encoded_image.decode("utf-8")
    base64_qwen = f"data:image;base64,{encoded_image_text}"
    messages = [
        {
            "role": "user",
            "content": [
                {"type": "image", "image": base64_qwen},
                {"type": "text", "text": "What does the image show?"},
            ],
        }
    ]
    text = processor.apply_chat_template(
        messages, tokenize=False, add_generation_prompt=True
    )
    image_inputs, video_inputs = process_vision_info(messages)

    # tokenize
    return processor(
        text=[text],
        images=image_inputs,
        videos=video_inputs,
        padding=False,
        max_length=MAX_SEQUENCE_LENGTH,
        truncation=True,
    )

ds = ds.map(preprocess_and_tokenize, remove_columns=ds["calibration"].column_names)

# Recipe
recipe = GPTQModifier(
    targets="Linear",
    config_groups={
        "config_group": QuantizationScheme(
            targets=["Linear"],
            weights=QuantizationArgs(
                num_bits=4,
                type=QuantizationType.INT,
                strategy=QuantizationStrategy.GROUP,
                group_size=128,
                symmetric=True,
                dynamic=False,
                actorder=ActivationOrdering.WEIGHT,
            ),
        ),
    },
    sequential_targets=["Qwen2VLDecoderLayer"],
    ignore=["lm_head", "re:visual.*"],
    update_size=NUM_CALIBRATION_SAMPLES,
    dampening_frac=dampening_frac
)

SAVE_DIR=f"{model_id.split('/')[1]}-quantized.w4a16

# Perform oneshot
oneshot(
    model=model,
    tokenizer=model_id,
    dataset=ds,
    recipe=recipe,
    max_seq_length=MAX_SEQUENCE_LENGTH,
    num_calibration_samples=NUM_CALIBRATION_SAMPLES,
    trust_remote_code_model=True,
    data_collator=qwen2_vl_data_collator,
    output_dir=SAVE_DIR
)

Load model.pythontransformers

import base64
from io import BytesIO
import torch
from datasets import load_dataset
from qwen_vl_utils import process_vision_info
from transformers import AutoProcessor
from llmcompressor.modifiers.quantization import GPTQModifier
from llmcompressor.transformers import oneshot
from llmcompressor.transformers.tracing import TraceableQwen2VLForConditionalGeneration
from llmcompressor.transformers.utils.data_collator import qwen2_vl_data_collator
from compressed_tensors.quantization import QuantizationArgs, QuantizationType, QuantizationStrategy, ActivationOrdering, QuantizationScheme

# Load model.
model_id = "Qwen/Qwen2-VL-72B-Instruct"

model = TraceableQwen2VLForConditionalGeneration.from_pretrained(
    model_id,
    device_map="auto",
    torch_dtype="auto",
)
processor = AutoProcessor.from_pretrained(model_id, trust_remote_code=True)

# Oneshot arguments
DATASET_ID = "lmms-lab/flickr30k"
DATASET_SPLIT = {"calibration": "test[:512]"}
NUM_CALIBRATION_SAMPLES = 512
MAX_SEQUENCE_LENGTH = 2048

# Load dataset and preprocess.
ds = load_dataset(DATASET_ID, split=DATASET_SPLIT)
ds = ds.shuffle(seed=42)
dampening_frac=0.01

# Apply chat template and tokenize inputs.
def preprocess_and_tokenize(example):
    # preprocess
    buffered = BytesIO()
    example["image"].save(buffered, format="PNG")
    encoded_image = base64.b64encode(buffered.getvalue())
    encoded_image_text = encoded_image.decode("utf-8")
    base64_qwen = f"data:image;base64,{encoded_image_text}"
    messages = [
        {
            "role": "user",
            "content": [
                {"type": "image", "image": base64_qwen},
                {"type": "text", "text": "What does the image show?"},
            ],
        }
    ]
    text = processor.apply_chat_template(
        messages, tokenize=False, add_generation_prompt=True
    )
    image_inputs, video_inputs = process_vision_info(messages)

    # tokenize
    return processor(
        text=[text],
        images=image_inputs,
        videos=video_inputs,
        padding=False,
        max_length=MAX_SEQUENCE_LENGTH,
        truncation=True,
    )

ds = ds.map(preprocess_and_tokenize, remove_columns=ds["calibration"].column_names)

# Recipe
recipe = GPTQModifier(
    targets="Linear",
    config_groups={
        "config_group": QuantizationScheme(
            targets=["Linear"],
            weights=QuantizationArgs(
                num_bits=4,
                type=QuantizationType.INT,
                strategy=QuantizationStrategy.GROUP,
                group_size=128,
                symmetric=True,
                dynamic=False,
                actorder=ActivationOrdering.WEIGHT,
            ),
        ),
    },
    sequential_targets=["Qwen2VLDecoderLayer"],
    ignore=["lm_head", "re:visual.*"],
    update_size=NUM_CALIBRATION_SAMPLES,
    dampening_frac=dampening_frac
)

SAVE_DIR=f"{model_id.split('/')[1]}-quantized.w4a16

# Perform oneshot
oneshot(
    model=model,
    tokenizer=model_id,
    dataset=ds,
    recipe=recipe,
    max_seq_length=MAX_SEQUENCE_LENGTH,
    num_calibration_samples=NUM_CALIBRATION_SAMPLES,
    trust_remote_code_model=True,
    data_collator=qwen2_vl_data_collator,
    output_dir=SAVE_DIR
)

Load model.pythontransformers

import base64
from io import BytesIO
import torch
from datasets import load_dataset
from qwen_vl_utils import process_vision_info
from transformers import AutoProcessor
from llmcompressor.modifiers.quantization import GPTQModifier
from llmcompressor.transformers import oneshot
from llmcompressor.transformers.tracing import TraceableQwen2VLForConditionalGeneration
from llmcompressor.transformers.utils.data_collator import qwen2_vl_data_collator
from compressed_tensors.quantization import QuantizationArgs, QuantizationType, QuantizationStrategy, ActivationOrdering, QuantizationScheme

# Load model.
model_id = "Qwen/Qwen2-VL-72B-Instruct"

model = TraceableQwen2VLForConditionalGeneration.from_pretrained(
    model_id,
    device_map="auto",
    torch_dtype="auto",
)
processor = AutoProcessor.from_pretrained(model_id, trust_remote_code=True)

# Oneshot arguments
DATASET_ID = "lmms-lab/flickr30k"
DATASET_SPLIT = {"calibration": "test[:512]"}
NUM_CALIBRATION_SAMPLES = 512
MAX_SEQUENCE_LENGTH = 2048

# Load dataset and preprocess.
ds = load_dataset(DATASET_ID, split=DATASET_SPLIT)
ds = ds.shuffle(seed=42)
dampening_frac=0.01

# Apply chat template and tokenize inputs.
def preprocess_and_tokenize(example):
    # preprocess
    buffered = BytesIO()
    example["image"].save(buffered, format="PNG")
    encoded_image = base64.b64encode(buffered.getvalue())
    encoded_image_text = encoded_image.decode("utf-8")
    base64_qwen = f"data:image;base64,{encoded_image_text}"
    messages = [
        {
            "role": "user",
            "content": [
                {"type": "image", "image": base64_qwen},
                {"type": "text", "text": "What does the image show?"},
            ],
        }
    ]
    text = processor.apply_chat_template(
        messages, tokenize=False, add_generation_prompt=True
    )
    image_inputs, video_inputs = process_vision_info(messages)

    # tokenize
    return processor(
        text=[text],
        images=image_inputs,
        videos=video_inputs,
        padding=False,
        max_length=MAX_SEQUENCE_LENGTH,
        truncation=True,
    )

ds = ds.map(preprocess_and_tokenize, remove_columns=ds["calibration"].column_names)

# Recipe
recipe = GPTQModifier(
    targets="Linear",
    config_groups={
        "config_group": QuantizationScheme(
            targets=["Linear"],
            weights=QuantizationArgs(
                num_bits=4,
                type=QuantizationType.INT,
                strategy=QuantizationStrategy.GROUP,
                group_size=128,
                symmetric=True,
                dynamic=False,
                actorder=ActivationOrdering.WEIGHT,
            ),
        ),
    },
    sequential_targets=["Qwen2VLDecoderLayer"],
    ignore=["lm_head", "re:visual.*"],
    update_size=NUM_CALIBRATION_SAMPLES,
    dampening_frac=dampening_frac
)

SAVE_DIR=f"{model_id.split('/')[1]}-quantized.w4a16

# Perform oneshot
oneshot(
    model=model,
    tokenizer=model_id,
    dataset=ds,
    recipe=recipe,
    max_seq_length=MAX_SEQUENCE_LENGTH,
    num_calibration_samples=NUM_CALIBRATION_SAMPLES,
    trust_remote_code_model=True,
    data_collator=qwen2_vl_data_collator,
    output_dir=SAVE_DIR
)

Load model.pythontransformers

import base64
from io import BytesIO
import torch
from datasets import load_dataset
from qwen_vl_utils import process_vision_info
from transformers import AutoProcessor
from llmcompressor.modifiers.quantization import GPTQModifier
from llmcompressor.transformers import oneshot
from llmcompressor.transformers.tracing import TraceableQwen2VLForConditionalGeneration
from llmcompressor.transformers.utils.data_collator import qwen2_vl_data_collator
from compressed_tensors.quantization import QuantizationArgs, QuantizationType, QuantizationStrategy, ActivationOrdering, QuantizationScheme

# Load model.
model_id = "Qwen/Qwen2-VL-72B-Instruct"

model = TraceableQwen2VLForConditionalGeneration.from_pretrained(
    model_id,
    device_map="auto",
    torch_dtype="auto",
)
processor = AutoProcessor.from_pretrained(model_id, trust_remote_code=True)

# Oneshot arguments
DATASET_ID = "lmms-lab/flickr30k"
DATASET_SPLIT = {"calibration": "test[:512]"}
NUM_CALIBRATION_SAMPLES = 512
MAX_SEQUENCE_LENGTH = 2048

# Load dataset and preprocess.
ds = load_dataset(DATASET_ID, split=DATASET_SPLIT)
ds = ds.shuffle(seed=42)
dampening_frac=0.01

# Apply chat template and tokenize inputs.
def preprocess_and_tokenize(example):
    # preprocess
    buffered = BytesIO()
    example["image"].save(buffered, format="PNG")
    encoded_image = base64.b64encode(buffered.getvalue())
    encoded_image_text = encoded_image.decode("utf-8")
    base64_qwen = f"data:image;base64,{encoded_image_text}"
    messages = [
        {
            "role": "user",
            "content": [
                {"type": "image", "image": base64_qwen},
                {"type": "text", "text": "What does the image show?"},
            ],
        }
    ]
    text = processor.apply_chat_template(
        messages, tokenize=False, add_generation_prompt=True
    )
    image_inputs, video_inputs = process_vision_info(messages)

    # tokenize
    return processor(
        text=[text],
        images=image_inputs,
        videos=video_inputs,
        padding=False,
        max_length=MAX_SEQUENCE_LENGTH,
        truncation=True,
    )

ds = ds.map(preprocess_and_tokenize, remove_columns=ds["calibration"].column_names)

# Recipe
recipe = GPTQModifier(
    targets="Linear",
    config_groups={
        "config_group": QuantizationScheme(
            targets=["Linear"],
            weights=QuantizationArgs(
                num_bits=4,
                type=QuantizationType.INT,
                strategy=QuantizationStrategy.GROUP,
                group_size=128,
                symmetric=True,
                dynamic=False,
                actorder=ActivationOrdering.WEIGHT,
            ),
        ),
    },
    sequential_targets=["Qwen2VLDecoderLayer"],
    ignore=["lm_head", "re:visual.*"],
    update_size=NUM_CALIBRATION_SAMPLES,
    dampening_frac=dampening_frac
)

SAVE_DIR=f"{model_id.split('/')[1]}-quantized.w4a16

# Perform oneshot
oneshot(
    model=model,
    tokenizer=model_id,
    dataset=ds,
    recipe=recipe,
    max_seq_length=MAX_SEQUENCE_LENGTH,
    num_calibration_samples=NUM_CALIBRATION_SAMPLES,
    trust_remote_code_model=True,
    data_collator=qwen2_vl_data_collator,
    output_dir=SAVE_DIR
)

Load model.pythontransformers

import base64
from io import BytesIO
import torch
from datasets import load_dataset
from qwen_vl_utils import process_vision_info
from transformers import AutoProcessor
from llmcompressor.modifiers.quantization import GPTQModifier
from llmcompressor.transformers import oneshot
from llmcompressor.transformers.tracing import TraceableQwen2VLForConditionalGeneration
from llmcompressor.transformers.utils.data_collator import qwen2_vl_data_collator
from compressed_tensors.quantization import QuantizationArgs, QuantizationType, QuantizationStrategy, ActivationOrdering, QuantizationScheme

# Load model.
model_id = "Qwen/Qwen2-VL-72B-Instruct"

model = TraceableQwen2VLForConditionalGeneration.from_pretrained(
    model_id,
    device_map="auto",
    torch_dtype="auto",
)
processor = AutoProcessor.from_pretrained(model_id, trust_remote_code=True)

# Oneshot arguments
DATASET_ID = "lmms-lab/flickr30k"
DATASET_SPLIT = {"calibration": "test[:512]"}
NUM_CALIBRATION_SAMPLES = 512
MAX_SEQUENCE_LENGTH = 2048

# Load dataset and preprocess.
ds = load_dataset(DATASET_ID, split=DATASET_SPLIT)
ds = ds.shuffle(seed=42)
dampening_frac=0.01

# Apply chat template and tokenize inputs.
def preprocess_and_tokenize(example):
    # preprocess
    buffered = BytesIO()
    example["image"].save(buffered, format="PNG")
    encoded_image = base64.b64encode(buffered.getvalue())
    encoded_image_text = encoded_image.decode("utf-8")
    base64_qwen = f"data:image;base64,{encoded_image_text}"
    messages = [
        {
            "role": "user",
            "content": [
                {"type": "image", "image": base64_qwen},
                {"type": "text", "text": "What does the image show?"},
            ],
        }
    ]
    text = processor.apply_chat_template(
        messages, tokenize=False, add_generation_prompt=True
    )
    image_inputs, video_inputs = process_vision_info(messages)

    # tokenize
    return processor(
        text=[text],
        images=image_inputs,
        videos=video_inputs,
        padding=False,
        max_length=MAX_SEQUENCE_LENGTH,
        truncation=True,
    )

ds = ds.map(preprocess_and_tokenize, remove_columns=ds["calibration"].column_names)

# Recipe
recipe = GPTQModifier(
    targets="Linear",
    config_groups={
        "config_group": QuantizationScheme(
            targets=["Linear"],
            weights=QuantizationArgs(
                num_bits=4,
                type=QuantizationType.INT,
                strategy=QuantizationStrategy.GROUP,
                group_size=128,
                symmetric=True,
                dynamic=False,
                actorder=ActivationOrdering.WEIGHT,
            ),
        ),
    },
    sequential_targets=["Qwen2VLDecoderLayer"],
    ignore=["lm_head", "re:visual.*"],
    update_size=NUM_CALIBRATION_SAMPLES,
    dampening_frac=dampening_frac
)

SAVE_DIR=f"{model_id.split('/')[1]}-quantized.w4a16

# Perform oneshot
oneshot(
    model=model,
    tokenizer=model_id,
    dataset=ds,
    recipe=recipe,
    max_seq_length=MAX_SEQUENCE_LENGTH,
    num_calibration_samples=NUM_CALIBRATION_SAMPLES,
    trust_remote_code_model=True,
    data_collator=qwen2_vl_data_collator,
    output_dir=SAVE_DIR
)

Load model.pythontransformers

import base64
from io import BytesIO
import torch
from datasets import load_dataset
from qwen_vl_utils import process_vision_info
from transformers import AutoProcessor
from llmcompressor.modifiers.quantization import GPTQModifier
from llmcompressor.transformers import oneshot
from llmcompressor.transformers.tracing import TraceableQwen2VLForConditionalGeneration
from llmcompressor.transformers.utils.data_collator import qwen2_vl_data_collator
from compressed_tensors.quantization import QuantizationArgs, QuantizationType, QuantizationStrategy, ActivationOrdering, QuantizationScheme

# Load model.
model_id = "Qwen/Qwen2-VL-72B-Instruct"

model = TraceableQwen2VLForConditionalGeneration.from_pretrained(
    model_id,
    device_map="auto",
    torch_dtype="auto",
)
processor = AutoProcessor.from_pretrained(model_id, trust_remote_code=True)

# Oneshot arguments
DATASET_ID = "lmms-lab/flickr30k"
DATASET_SPLIT = {"calibration": "test[:512]"}
NUM_CALIBRATION_SAMPLES = 512
MAX_SEQUENCE_LENGTH = 2048

# Load dataset and preprocess.
ds = load_dataset(DATASET_ID, split=DATASET_SPLIT)
ds = ds.shuffle(seed=42)
dampening_frac=0.01

# Apply chat template and tokenize inputs.
def preprocess_and_tokenize(example):
    # preprocess
    buffered = BytesIO()
    example["image"].save(buffered, format="PNG")
    encoded_image = base64.b64encode(buffered.getvalue())
    encoded_image_text = encoded_image.decode("utf-8")
    base64_qwen = f"data:image;base64,{encoded_image_text}"
    messages = [
        {
            "role": "user",
            "content": [
                {"type": "image", "image": base64_qwen},
                {"type": "text", "text": "What does the image show?"},
            ],
        }
    ]
    text = processor.apply_chat_template(
        messages, tokenize=False, add_generation_prompt=True
    )
    image_inputs, video_inputs = process_vision_info(messages)

    # tokenize
    return processor(
        text=[text],
        images=image_inputs,
        videos=video_inputs,
        padding=False,
        max_length=MAX_SEQUENCE_LENGTH,
        truncation=True,
    )

ds = ds.map(preprocess_and_tokenize, remove_columns=ds["calibration"].column_names)

# Recipe
recipe = GPTQModifier(
    targets="Linear",
    config_groups={
        "config_group": QuantizationScheme(
            targets=["Linear"],
            weights=QuantizationArgs(
                num_bits=4,
                type=QuantizationType.INT,
                strategy=QuantizationStrategy.GROUP,
                group_size=128,
                symmetric=True,
                dynamic=False,
                actorder=ActivationOrdering.WEIGHT,
            ),
        ),
    },
    sequential_targets=["Qwen2VLDecoderLayer"],
    ignore=["lm_head", "re:visual.*"],
    update_size=NUM_CALIBRATION_SAMPLES,
    dampening_frac=dampening_frac
)

SAVE_DIR=f"{model_id.split('/')[1]}-quantized.w4a16

# Perform oneshot
oneshot(
    model=model,
    tokenizer=model_id,
    dataset=ds,
    recipe=recipe,
    max_seq_length=MAX_SEQUENCE_LENGTH,
    num_calibration_samples=NUM_CALIBRATION_SAMPLES,
    trust_remote_code_model=True,
    data_collator=qwen2_vl_data_collator,
    output_dir=SAVE_DIR
)

Load model.pythontransformers

import base64
from io import BytesIO
import torch
from datasets import load_dataset
from qwen_vl_utils import process_vision_info
from transformers import AutoProcessor
from llmcompressor.modifiers.quantization import GPTQModifier
from llmcompressor.transformers import oneshot
from llmcompressor.transformers.tracing import TraceableQwen2VLForConditionalGeneration
from llmcompressor.transformers.utils.data_collator import qwen2_vl_data_collator
from compressed_tensors.quantization import QuantizationArgs, QuantizationType, QuantizationStrategy, ActivationOrdering, QuantizationScheme

# Load model.
model_id = "Qwen/Qwen2-VL-72B-Instruct"

model = TraceableQwen2VLForConditionalGeneration.from_pretrained(
    model_id,
    device_map="auto",
    torch_dtype="auto",
)
processor = AutoProcessor.from_pretrained(model_id, trust_remote_code=True)

# Oneshot arguments
DATASET_ID = "lmms-lab/flickr30k"
DATASET_SPLIT = {"calibration": "test[:512]"}
NUM_CALIBRATION_SAMPLES = 512
MAX_SEQUENCE_LENGTH = 2048

# Load dataset and preprocess.
ds = load_dataset(DATASET_ID, split=DATASET_SPLIT)
ds = ds.shuffle(seed=42)
dampening_frac=0.01

# Apply chat template and tokenize inputs.
def preprocess_and_tokenize(example):
    # preprocess
    buffered = BytesIO()
    example["image"].save(buffered, format="PNG")
    encoded_image = base64.b64encode(buffered.getvalue())
    encoded_image_text = encoded_image.decode("utf-8")
    base64_qwen = f"data:image;base64,{encoded_image_text}"
    messages = [
        {
            "role": "user",
            "content": [
                {"type": "image", "image": base64_qwen},
                {"type": "text", "text": "What does the image show?"},
            ],
        }
    ]
    text = processor.apply_chat_template(
        messages, tokenize=False, add_generation_prompt=True
    )
    image_inputs, video_inputs = process_vision_info(messages)

    # tokenize
    return processor(
        text=[text],
        images=image_inputs,
        videos=video_inputs,
        padding=False,
        max_length=MAX_SEQUENCE_LENGTH,
        truncation=True,
    )

ds = ds.map(preprocess_and_tokenize, remove_columns=ds["calibration"].column_names)

# Recipe
recipe = GPTQModifier(
    targets="Linear",
    config_groups={
        "config_group": QuantizationScheme(
            targets=["Linear"],
            weights=QuantizationArgs(
                num_bits=4,
                type=QuantizationType.INT,
                strategy=QuantizationStrategy.GROUP,
                group_size=128,
                symmetric=True,
                dynamic=False,
                actorder=ActivationOrdering.WEIGHT,
            ),
        ),
    },
    sequential_targets=["Qwen2VLDecoderLayer"],
    ignore=["lm_head", "re:visual.*"],
    update_size=NUM_CALIBRATION_SAMPLES,
    dampening_frac=dampening_frac
)

SAVE_DIR=f"{model_id.split('/')[1]}-quantized.w4a16

# Perform oneshot
oneshot(
    model=model,
    tokenizer=model_id,
    dataset=ds,
    recipe=recipe,
    max_seq_length=MAX_SEQUENCE_LENGTH,
    num_calibration_samples=NUM_CALIBRATION_SAMPLES,
    trust_remote_code_model=True,
    data_collator=qwen2_vl_data_collator,
    output_dir=SAVE_DIR
)

Load model.pythontransformers

import base64
from io import BytesIO
import torch
from datasets import load_dataset
from qwen_vl_utils import process_vision_info
from transformers import AutoProcessor
from llmcompressor.modifiers.quantization import GPTQModifier
from llmcompressor.transformers import oneshot
from llmcompressor.transformers.tracing import TraceableQwen2VLForConditionalGeneration
from llmcompressor.transformers.utils.data_collator import qwen2_vl_data_collator
from compressed_tensors.quantization import QuantizationArgs, QuantizationType, QuantizationStrategy, ActivationOrdering, QuantizationScheme

# Load model.
model_id = "Qwen/Qwen2-VL-72B-Instruct"

model = TraceableQwen2VLForConditionalGeneration.from_pretrained(
    model_id,
    device_map="auto",
    torch_dtype="auto",
)
processor = AutoProcessor.from_pretrained(model_id, trust_remote_code=True)

# Oneshot arguments
DATASET_ID = "lmms-lab/flickr30k"
DATASET_SPLIT = {"calibration": "test[:512]"}
NUM_CALIBRATION_SAMPLES = 512
MAX_SEQUENCE_LENGTH = 2048

# Load dataset and preprocess.
ds = load_dataset(DATASET_ID, split=DATASET_SPLIT)
ds = ds.shuffle(seed=42)
dampening_frac=0.01

# Apply chat template and tokenize inputs.
def preprocess_and_tokenize(example):
    # preprocess
    buffered = BytesIO()
    example["image"].save(buffered, format="PNG")
    encoded_image = base64.b64encode(buffered.getvalue())
    encoded_image_text = encoded_image.decode("utf-8")
    base64_qwen = f"data:image;base64,{encoded_image_text}"
    messages = [
        {
            "role": "user",
            "content": [
                {"type": "image", "image": base64_qwen},
                {"type": "text", "text": "What does the image show?"},
            ],
        }
    ]
    text = processor.apply_chat_template(
        messages, tokenize=False, add_generation_prompt=True
    )
    image_inputs, video_inputs = process_vision_info(messages)

    # tokenize
    return processor(
        text=[text],
        images=image_inputs,
        videos=video_inputs,
        padding=False,
        max_length=MAX_SEQUENCE_LENGTH,
        truncation=True,
    )

ds = ds.map(preprocess_and_tokenize, remove_columns=ds["calibration"].column_names)

# Recipe
recipe = GPTQModifier(
    targets="Linear",
    config_groups={
        "config_group": QuantizationScheme(
            targets=["Linear"],
            weights=QuantizationArgs(
                num_bits=4,
                type=QuantizationType.INT,
                strategy=QuantizationStrategy.GROUP,
                group_size=128,
                symmetric=True,
                dynamic=False,
                actorder=ActivationOrdering.WEIGHT,
            ),
        ),
    },
    sequential_targets=["Qwen2VLDecoderLayer"],
    ignore=["lm_head", "re:visual.*"],
    update_size=NUM_CALIBRATION_SAMPLES,
    dampening_frac=dampening_frac
)

SAVE_DIR=f"{model_id.split('/')[1]}-quantized.w4a16

# Perform oneshot
oneshot(
    model=model,
    tokenizer=model_id,
    dataset=ds,
    recipe=recipe,
    max_seq_length=MAX_SEQUENCE_LENGTH,
    num_calibration_samples=NUM_CALIBRATION_SAMPLES,
    trust_remote_code_model=True,
    data_collator=qwen2_vl_data_collator,
    output_dir=SAVE_DIR
)

Load model.pythontransformers

import base64
from io import BytesIO
import torch
from datasets import load_dataset
from qwen_vl_utils import process_vision_info
from transformers import AutoProcessor
from llmcompressor.modifiers.quantization import GPTQModifier
from llmcompressor.transformers import oneshot
from llmcompressor.transformers.tracing import TraceableQwen2VLForConditionalGeneration
from llmcompressor.transformers.utils.data_collator import qwen2_vl_data_collator
from compressed_tensors.quantization import QuantizationArgs, QuantizationType, QuantizationStrategy, ActivationOrdering, QuantizationScheme

# Load model.
model_id = "Qwen/Qwen2-VL-72B-Instruct"

model = TraceableQwen2VLForConditionalGeneration.from_pretrained(
    model_id,
    device_map="auto",
    torch_dtype="auto",
)
processor = AutoProcessor.from_pretrained(model_id, trust_remote_code=True)

# Oneshot arguments
DATASET_ID = "lmms-lab/flickr30k"
DATASET_SPLIT = {"calibration": "test[:512]"}
NUM_CALIBRATION_SAMPLES = 512
MAX_SEQUENCE_LENGTH = 2048

# Load dataset and preprocess.
ds = load_dataset(DATASET_ID, split=DATASET_SPLIT)
ds = ds.shuffle(seed=42)
dampening_frac=0.01

# Apply chat template and tokenize inputs.
def preprocess_and_tokenize(example):
    # preprocess
    buffered = BytesIO()
    example["image"].save(buffered, format="PNG")
    encoded_image = base64.b64encode(buffered.getvalue())
    encoded_image_text = encoded_image.decode("utf-8")
    base64_qwen = f"data:image;base64,{encoded_image_text}"
    messages = [
        {
            "role": "user",
            "content": [
                {"type": "image", "image": base64_qwen},
                {"type": "text", "text": "What does the image show?"},
            ],
        }
    ]
    text = processor.apply_chat_template(
        messages, tokenize=False, add_generation_prompt=True
    )
    image_inputs, video_inputs = process_vision_info(messages)

    # tokenize
    return processor(
        text=[text],
        images=image_inputs,
        videos=video_inputs,
        padding=False,
        max_length=MAX_SEQUENCE_LENGTH,
        truncation=True,
    )

ds = ds.map(preprocess_and_tokenize, remove_columns=ds["calibration"].column_names)

# Recipe
recipe = GPTQModifier(
    targets="Linear",
    config_groups={
        "config_group": QuantizationScheme(
            targets=["Linear"],
            weights=QuantizationArgs(
                num_bits=4,
                type=QuantizationType.INT,
                strategy=QuantizationStrategy.GROUP,
                group_size=128,
                symmetric=True,
                dynamic=False,
                actorder=ActivationOrdering.WEIGHT,
            ),
        ),
    },
    sequential_targets=["Qwen2VLDecoderLayer"],
    ignore=["lm_head", "re:visual.*"],
    update_size=NUM_CALIBRATION_SAMPLES,
    dampening_frac=dampening_frac
)

SAVE_DIR=f"{model_id.split('/')[1]}-quantized.w4a16

# Perform oneshot
oneshot(
    model=model,
    tokenizer=model_id,
    dataset=ds,
    recipe=recipe,
    max_seq_length=MAX_SEQUENCE_LENGTH,
    num_calibration_samples=NUM_CALIBRATION_SAMPLES,
    trust_remote_code_model=True,
    data_collator=qwen2_vl_data_collator,
    output_dir=SAVE_DIR
)

Load model.pythontransformers

import base64
from io import BytesIO
import torch
from datasets import load_dataset
from qwen_vl_utils import process_vision_info
from transformers import AutoProcessor
from llmcompressor.modifiers.quantization import GPTQModifier
from llmcompressor.transformers import oneshot
from llmcompressor.transformers.tracing import TraceableQwen2VLForConditionalGeneration
from llmcompressor.transformers.utils.data_collator import qwen2_vl_data_collator
from compressed_tensors.quantization import QuantizationArgs, QuantizationType, QuantizationStrategy, ActivationOrdering, QuantizationScheme

# Load model.
model_id = "Qwen/Qwen2-VL-72B-Instruct"

model = TraceableQwen2VLForConditionalGeneration.from_pretrained(
    model_id,
    device_map="auto",
    torch_dtype="auto",
)
processor = AutoProcessor.from_pretrained(model_id, trust_remote_code=True)

# Oneshot arguments
DATASET_ID = "lmms-lab/flickr30k"
DATASET_SPLIT = {"calibration": "test[:512]"}
NUM_CALIBRATION_SAMPLES = 512
MAX_SEQUENCE_LENGTH = 2048

# Load dataset and preprocess.
ds = load_dataset(DATASET_ID, split=DATASET_SPLIT)
ds = ds.shuffle(seed=42)
dampening_frac=0.01

# Apply chat template and tokenize inputs.
def preprocess_and_tokenize(example):
    # preprocess
    buffered = BytesIO()
    example["image"].save(buffered, format="PNG")
    encoded_image = base64.b64encode(buffered.getvalue())
    encoded_image_text = encoded_image.decode("utf-8")
    base64_qwen = f"data:image;base64,{encoded_image_text}"
    messages = [
        {
            "role": "user",
            "content": [
                {"type": "image", "image": base64_qwen},
                {"type": "text", "text": "What does the image show?"},
            ],
        }
    ]
    text = processor.apply_chat_template(
        messages, tokenize=False, add_generation_prompt=True
    )
    image_inputs, video_inputs = process_vision_info(messages)

    # tokenize
    return processor(
        text=[text],
        images=image_inputs,
        videos=video_inputs,
        padding=False,
        max_length=MAX_SEQUENCE_LENGTH,
        truncation=True,
    )

ds = ds.map(preprocess_and_tokenize, remove_columns=ds["calibration"].column_names)

# Recipe
recipe = GPTQModifier(
    targets="Linear",
    config_groups={
        "config_group": QuantizationScheme(
            targets=["Linear"],
            weights=QuantizationArgs(
                num_bits=4,
                type=QuantizationType.INT,
                strategy=QuantizationStrategy.GROUP,
                group_size=128,
                symmetric=True,
                dynamic=False,
                actorder=ActivationOrdering.WEIGHT,
            ),
        ),
    },
    sequential_targets=["Qwen2VLDecoderLayer"],
    ignore=["lm_head", "re:visual.*"],
    update_size=NUM_CALIBRATION_SAMPLES,
    dampening_frac=dampening_frac
)

SAVE_DIR=f"{model_id.split('/')[1]}-quantized.w4a16

# Perform oneshot
oneshot(
    model=model,
    tokenizer=model_id,
    dataset=ds,
    recipe=recipe,
    max_seq_length=MAX_SEQUENCE_LENGTH,
    num_calibration_samples=NUM_CALIBRATION_SAMPLES,
    trust_remote_code_model=True,
    data_collator=qwen2_vl_data_collator,
    output_dir=SAVE_DIR
)

Load model.pythontransformers

import base64
from io import BytesIO
import torch
from datasets import load_dataset
from qwen_vl_utils import process_vision_info
from transformers import AutoProcessor
from llmcompressor.modifiers.quantization import GPTQModifier
from llmcompressor.transformers import oneshot
from llmcompressor.transformers.tracing import TraceableQwen2VLForConditionalGeneration
from llmcompressor.transformers.utils.data_collator import qwen2_vl_data_collator
from compressed_tensors.quantization import QuantizationArgs, QuantizationType, QuantizationStrategy, ActivationOrdering, QuantizationScheme

# Load model.
model_id = "Qwen/Qwen2-VL-72B-Instruct"

model = TraceableQwen2VLForConditionalGeneration.from_pretrained(
    model_id,
    device_map="auto",
    torch_dtype="auto",
)
processor = AutoProcessor.from_pretrained(model_id, trust_remote_code=True)

# Oneshot arguments
DATASET_ID = "lmms-lab/flickr30k"
DATASET_SPLIT = {"calibration": "test[:512]"}
NUM_CALIBRATION_SAMPLES = 512
MAX_SEQUENCE_LENGTH = 2048

# Load dataset and preprocess.
ds = load_dataset(DATASET_ID, split=DATASET_SPLIT)
ds = ds.shuffle(seed=42)
dampening_frac=0.01

# Apply chat template and tokenize inputs.
def preprocess_and_tokenize(example):
    # preprocess
    buffered = BytesIO()
    example["image"].save(buffered, format="PNG")
    encoded_image = base64.b64encode(buffered.getvalue())
    encoded_image_text = encoded_image.decode("utf-8")
    base64_qwen = f"data:image;base64,{encoded_image_text}"
    messages = [
        {
            "role": "user",
            "content": [
                {"type": "image", "image": base64_qwen},
                {"type": "text", "text": "What does the image show?"},
            ],
        }
    ]
    text = processor.apply_chat_template(
        messages, tokenize=False, add_generation_prompt=True
    )
    image_inputs, video_inputs = process_vision_info(messages)

    # tokenize
    return processor(
        text=[text],
        images=image_inputs,
        videos=video_inputs,
        padding=False,
        max_length=MAX_SEQUENCE_LENGTH,
        truncation=True,
    )

ds = ds.map(preprocess_and_tokenize, remove_columns=ds["calibration"].column_names)

# Recipe
recipe = GPTQModifier(
    targets="Linear",
    config_groups={
        "config_group": QuantizationScheme(
            targets=["Linear"],
            weights=QuantizationArgs(
                num_bits=4,
                type=QuantizationType.INT,
                strategy=QuantizationStrategy.GROUP,
                group_size=128,
                symmetric=True,
                dynamic=False,
                actorder=ActivationOrdering.WEIGHT,
            ),
        ),
    },
    sequential_targets=["Qwen2VLDecoderLayer"],
    ignore=["lm_head", "re:visual.*"],
    update_size=NUM_CALIBRATION_SAMPLES,
    dampening_frac=dampening_frac
)

SAVE_DIR=f"{model_id.split('/')[1]}-quantized.w4a16

# Perform oneshot
oneshot(
    model=model,
    tokenizer=model_id,
    dataset=ds,
    recipe=recipe,
    max_seq_length=MAX_SEQUENCE_LENGTH,
    num_calibration_samples=NUM_CALIBRATION_SAMPLES,
    trust_remote_code_model=True,
    data_collator=qwen2_vl_data_collator,
    output_dir=SAVE_DIR
)

Load model.pythontransformers

import base64
from io import BytesIO
import torch
from datasets import load_dataset
from qwen_vl_utils import process_vision_info
from transformers import AutoProcessor
from llmcompressor.modifiers.quantization import GPTQModifier
from llmcompressor.transformers import oneshot
from llmcompressor.transformers.tracing import TraceableQwen2VLForConditionalGeneration
from llmcompressor.transformers.utils.data_collator import qwen2_vl_data_collator
from compressed_tensors.quantization import QuantizationArgs, QuantizationType, QuantizationStrategy, ActivationOrdering, QuantizationScheme

# Load model.
model_id = "Qwen/Qwen2-VL-72B-Instruct"

model = TraceableQwen2VLForConditionalGeneration.from_pretrained(
    model_id,
    device_map="auto",
    torch_dtype="auto",
)
processor = AutoProcessor.from_pretrained(model_id, trust_remote_code=True)

# Oneshot arguments
DATASET_ID = "lmms-lab/flickr30k"
DATASET_SPLIT = {"calibration": "test[:512]"}
NUM_CALIBRATION_SAMPLES = 512
MAX_SEQUENCE_LENGTH = 2048

# Load dataset and preprocess.
ds = load_dataset(DATASET_ID, split=DATASET_SPLIT)
ds = ds.shuffle(seed=42)
dampening_frac=0.01

# Apply chat template and tokenize inputs.
def preprocess_and_tokenize(example):
    # preprocess
    buffered = BytesIO()
    example["image"].save(buffered, format="PNG")
    encoded_image = base64.b64encode(buffered.getvalue())
    encoded_image_text = encoded_image.decode("utf-8")
    base64_qwen = f"data:image;base64,{encoded_image_text}"
    messages = [
        {
            "role": "user",
            "content": [
                {"type": "image", "image": base64_qwen},
                {"type": "text", "text": "What does the image show?"},
            ],
        }
    ]
    text = processor.apply_chat_template(
        messages, tokenize=False, add_generation_prompt=True
    )
    image_inputs, video_inputs = process_vision_info(messages)

    # tokenize
    return processor(
        text=[text],
        images=image_inputs,
        videos=video_inputs,
        padding=False,
        max_length=MAX_SEQUENCE_LENGTH,
        truncation=True,
    )

ds = ds.map(preprocess_and_tokenize, remove_columns=ds["calibration"].column_names)

# Recipe
recipe = GPTQModifier(
    targets="Linear",
    config_groups={
        "config_group": QuantizationScheme(
            targets=["Linear"],
            weights=QuantizationArgs(
                num_bits=4,
                type=QuantizationType.INT,
                strategy=QuantizationStrategy.GROUP,
                group_size=128,
                symmetric=True,
                dynamic=False,
                actorder=ActivationOrdering.WEIGHT,
            ),
        ),
    },
    sequential_targets=["Qwen2VLDecoderLayer"],
    ignore=["lm_head", "re:visual.*"],
    update_size=NUM_CALIBRATION_SAMPLES,
    dampening_frac=dampening_frac
)

SAVE_DIR=f"{model_id.split('/')[1]}-quantized.w4a16

# Perform oneshot
oneshot(
    model=model,
    tokenizer=model_id,
    dataset=ds,
    recipe=recipe,
    max_seq_length=MAX_SEQUENCE_LENGTH,
    num_calibration_samples=NUM_CALIBRATION_SAMPLES,
    trust_remote_code_model=True,
    data_collator=qwen2_vl_data_collator,
    output_dir=SAVE_DIR
)

Load model.pythontransformers

import base64
from io import BytesIO
import torch
from datasets import load_dataset
from qwen_vl_utils import process_vision_info
from transformers import AutoProcessor
from llmcompressor.modifiers.quantization import GPTQModifier
from llmcompressor.transformers import oneshot
from llmcompressor.transformers.tracing import TraceableQwen2VLForConditionalGeneration
from llmcompressor.transformers.utils.data_collator import qwen2_vl_data_collator
from compressed_tensors.quantization import QuantizationArgs, QuantizationType, QuantizationStrategy, ActivationOrdering, QuantizationScheme

# Load model.
model_id = "Qwen/Qwen2-VL-72B-Instruct"

model = TraceableQwen2VLForConditionalGeneration.from_pretrained(
    model_id,
    device_map="auto",
    torch_dtype="auto",
)
processor = AutoProcessor.from_pretrained(model_id, trust_remote_code=True)

# Oneshot arguments
DATASET_ID = "lmms-lab/flickr30k"
DATASET_SPLIT = {"calibration": "test[:512]"}
NUM_CALIBRATION_SAMPLES = 512
MAX_SEQUENCE_LENGTH = 2048

# Load dataset and preprocess.
ds = load_dataset(DATASET_ID, split=DATASET_SPLIT)
ds = ds.shuffle(seed=42)
dampening_frac=0.01

# Apply chat template and tokenize inputs.
def preprocess_and_tokenize(example):
    # preprocess
    buffered = BytesIO()
    example["image"].save(buffered, format="PNG")
    encoded_image = base64.b64encode(buffered.getvalue())
    encoded_image_text = encoded_image.decode("utf-8")
    base64_qwen = f"data:image;base64,{encoded_image_text}"
    messages = [
        {
            "role": "user",
            "content": [
                {"type": "image", "image": base64_qwen},
                {"type": "text", "text": "What does the image show?"},
            ],
        }
    ]
    text = processor.apply_chat_template(
        messages, tokenize=False, add_generation_prompt=True
    )
    image_inputs, video_inputs = process_vision_info(messages)

    # tokenize
    return processor(
        text=[text],
        images=image_inputs,
        videos=video_inputs,
        padding=False,
        max_length=MAX_SEQUENCE_LENGTH,
        truncation=True,
    )

ds = ds.map(preprocess_and_tokenize, remove_columns=ds["calibration"].column_names)

# Recipe
recipe = GPTQModifier(
    targets="Linear",
    config_groups={
        "config_group": QuantizationScheme(
            targets=["Linear"],
            weights=QuantizationArgs(
                num_bits=4,
                type=QuantizationType.INT,
                strategy=QuantizationStrategy.GROUP,
                group_size=128,
                symmetric=True,
                dynamic=False,
                actorder=ActivationOrdering.WEIGHT,
            ),
        ),
    },
    sequential_targets=["Qwen2VLDecoderLayer"],
    ignore=["lm_head", "re:visual.*"],
    update_size=NUM_CALIBRATION_SAMPLES,
    dampening_frac=dampening_frac
)

SAVE_DIR=f"{model_id.split('/')[1]}-quantized.w4a16

# Perform oneshot
oneshot(
    model=model,
    tokenizer=model_id,
    dataset=ds,
    recipe=recipe,
    max_seq_length=MAX_SEQUENCE_LENGTH,
    num_calibration_samples=NUM_CALIBRATION_SAMPLES,
    trust_remote_code_model=True,
    data_collator=qwen2_vl_data_collator,
    output_dir=SAVE_DIR
)

Load model.pythontransformers

import base64
from io import BytesIO
import torch
from datasets import load_dataset
from qwen_vl_utils import process_vision_info
from transformers import AutoProcessor
from llmcompressor.modifiers.quantization import GPTQModifier
from llmcompressor.transformers import oneshot
from llmcompressor.transformers.tracing import TraceableQwen2VLForConditionalGeneration
from llmcompressor.transformers.utils.data_collator import qwen2_vl_data_collator
from compressed_tensors.quantization import QuantizationArgs, QuantizationType, QuantizationStrategy, ActivationOrdering, QuantizationScheme

# Load model.
model_id = "Qwen/Qwen2-VL-72B-Instruct"

model = TraceableQwen2VLForConditionalGeneration.from_pretrained(
    model_id,
    device_map="auto",
    torch_dtype="auto",
)
processor = AutoProcessor.from_pretrained(model_id, trust_remote_code=True)

# Oneshot arguments
DATASET_ID = "lmms-lab/flickr30k"
DATASET_SPLIT = {"calibration": "test[:512]"}
NUM_CALIBRATION_SAMPLES = 512
MAX_SEQUENCE_LENGTH = 2048

# Load dataset and preprocess.
ds = load_dataset(DATASET_ID, split=DATASET_SPLIT)
ds = ds.shuffle(seed=42)
dampening_frac=0.01

# Apply chat template and tokenize inputs.
def preprocess_and_tokenize(example):
    # preprocess
    buffered = BytesIO()
    example["image"].save(buffered, format="PNG")
    encoded_image = base64.b64encode(buffered.getvalue())
    encoded_image_text = encoded_image.decode("utf-8")
    base64_qwen = f"data:image;base64,{encoded_image_text}"
    messages = [
        {
            "role": "user",
            "content": [
                {"type": "image", "image": base64_qwen},
                {"type": "text", "text": "What does the image show?"},
            ],
        }
    ]
    text = processor.apply_chat_template(
        messages, tokenize=False, add_generation_prompt=True
    )
    image_inputs, video_inputs = process_vision_info(messages)

    # tokenize
    return processor(
        text=[text],
        images=image_inputs,
        videos=video_inputs,
        padding=False,
        max_length=MAX_SEQUENCE_LENGTH,
        truncation=True,
    )

ds = ds.map(preprocess_and_tokenize, remove_columns=ds["calibration"].column_names)

# Recipe
recipe = GPTQModifier(
    targets="Linear",
    config_groups={
        "config_group": QuantizationScheme(
            targets=["Linear"],
            weights=QuantizationArgs(
                num_bits=4,
                type=QuantizationType.INT,
                strategy=QuantizationStrategy.GROUP,
                group_size=128,
                symmetric=True,
                dynamic=False,
                actorder=ActivationOrdering.WEIGHT,
            ),
        ),
    },
    sequential_targets=["Qwen2VLDecoderLayer"],
    ignore=["lm_head", "re:visual.*"],
    update_size=NUM_CALIBRATION_SAMPLES,
    dampening_frac=dampening_frac
)

SAVE_DIR=f"{model_id.split('/')[1]}-quantized.w4a16

# Perform oneshot
oneshot(
    model=model,
    tokenizer=model_id,
    dataset=ds,
    recipe=recipe,
    max_seq_length=MAX_SEQUENCE_LENGTH,
    num_calibration_samples=NUM_CALIBRATION_SAMPLES,
    trust_remote_code_model=True,
    data_collator=qwen2_vl_data_collator,
    output_dir=SAVE_DIR
)

Load model.pythontransformers

import base64
from io import BytesIO
import torch
from datasets import load_dataset
from qwen_vl_utils import process_vision_info
from transformers import AutoProcessor
from llmcompressor.modifiers.quantization import GPTQModifier
from llmcompressor.transformers import oneshot
from llmcompressor.transformers.tracing import TraceableQwen2VLForConditionalGeneration
from llmcompressor.transformers.utils.data_collator import qwen2_vl_data_collator
from compressed_tensors.quantization import QuantizationArgs, QuantizationType, QuantizationStrategy, ActivationOrdering, QuantizationScheme

# Load model.
model_id = "Qwen/Qwen2-VL-72B-Instruct"

model = TraceableQwen2VLForConditionalGeneration.from_pretrained(
    model_id,
    device_map="auto",
    torch_dtype="auto",
)
processor = AutoProcessor.from_pretrained(model_id, trust_remote_code=True)

# Oneshot arguments
DATASET_ID = "lmms-lab/flickr30k"
DATASET_SPLIT = {"calibration": "test[:512]"}
NUM_CALIBRATION_SAMPLES = 512
MAX_SEQUENCE_LENGTH = 2048

# Load dataset and preprocess.
ds = load_dataset(DATASET_ID, split=DATASET_SPLIT)
ds = ds.shuffle(seed=42)
dampening_frac=0.01

# Apply chat template and tokenize inputs.
def preprocess_and_tokenize(example):
    # preprocess
    buffered = BytesIO()
    example["image"].save(buffered, format="PNG")
    encoded_image = base64.b64encode(buffered.getvalue())
    encoded_image_text = encoded_image.decode("utf-8")
    base64_qwen = f"data:image;base64,{encoded_image_text}"
    messages = [
        {
            "role": "user",
            "content": [
                {"type": "image", "image": base64_qwen},
                {"type": "text", "text": "What does the image show?"},
            ],
        }
    ]
    text = processor.apply_chat_template(
        messages, tokenize=False, add_generation_prompt=True
    )
    image_inputs, video_inputs = process_vision_info(messages)

    # tokenize
    return processor(
        text=[text],
        images=image_inputs,
        videos=video_inputs,
        padding=False,
        max_length=MAX_SEQUENCE_LENGTH,
        truncation=True,
    )

ds = ds.map(preprocess_and_tokenize, remove_columns=ds["calibration"].column_names)

# Recipe
recipe = GPTQModifier(
    targets="Linear",
    config_groups={
        "config_group": QuantizationScheme(
            targets=["Linear"],
            weights=QuantizationArgs(
                num_bits=4,
                type=QuantizationType.INT,
                strategy=QuantizationStrategy.GROUP,
                group_size=128,
                symmetric=True,
                dynamic=False,
                actorder=ActivationOrdering.WEIGHT,
            ),
        ),
    },
    sequential_targets=["Qwen2VLDecoderLayer"],
    ignore=["lm_head", "re:visual.*"],
    update_size=NUM_CALIBRATION_SAMPLES,
    dampening_frac=dampening_frac
)

SAVE_DIR=f"{model_id.split('/')[1]}-quantized.w4a16

# Perform oneshot
oneshot(
    model=model,
    tokenizer=model_id,
    dataset=ds,
    recipe=recipe,
    max_seq_length=MAX_SEQUENCE_LENGTH,
    num_calibration_samples=NUM_CALIBRATION_SAMPLES,
    trust_remote_code_model=True,
    data_collator=qwen2_vl_data_collator,
    output_dir=SAVE_DIR
)

Load model.pythontransformers

import base64
from io import BytesIO
import torch
from datasets import load_dataset
from qwen_vl_utils import process_vision_info
from transformers import AutoProcessor
from llmcompressor.modifiers.quantization import GPTQModifier
from llmcompressor.transformers import oneshot
from llmcompressor.transformers.tracing import TraceableQwen2VLForConditionalGeneration
from llmcompressor.transformers.utils.data_collator import qwen2_vl_data_collator
from compressed_tensors.quantization import QuantizationArgs, QuantizationType, QuantizationStrategy, ActivationOrdering, QuantizationScheme

# Load model.
model_id = "Qwen/Qwen2-VL-72B-Instruct"

model = TraceableQwen2VLForConditionalGeneration.from_pretrained(
    model_id,
    device_map="auto",
    torch_dtype="auto",
)
processor = AutoProcessor.from_pretrained(model_id, trust_remote_code=True)

# Oneshot arguments
DATASET_ID = "lmms-lab/flickr30k"
DATASET_SPLIT = {"calibration": "test[:512]"}
NUM_CALIBRATION_SAMPLES = 512
MAX_SEQUENCE_LENGTH = 2048

# Load dataset and preprocess.
ds = load_dataset(DATASET_ID, split=DATASET_SPLIT)
ds = ds.shuffle(seed=42)
dampening_frac=0.01

# Apply chat template and tokenize inputs.
def preprocess_and_tokenize(example):
    # preprocess
    buffered = BytesIO()
    example["image"].save(buffered, format="PNG")
    encoded_image = base64.b64encode(buffered.getvalue())
    encoded_image_text = encoded_image.decode("utf-8")
    base64_qwen = f"data:image;base64,{encoded_image_text}"
    messages = [
        {
            "role": "user",
            "content": [
                {"type": "image", "image": base64_qwen},
                {"type": "text", "text": "What does the image show?"},
            ],
        }
    ]
    text = processor.apply_chat_template(
        messages, tokenize=False, add_generation_prompt=True
    )
    image_inputs, video_inputs = process_vision_info(messages)

    # tokenize
    return processor(
        text=[text],
        images=image_inputs,
        videos=video_inputs,
        padding=False,
        max_length=MAX_SEQUENCE_LENGTH,
        truncation=True,
    )

ds = ds.map(preprocess_and_tokenize, remove_columns=ds["calibration"].column_names)

# Recipe
recipe = GPTQModifier(
    targets="Linear",
    config_groups={
        "config_group": QuantizationScheme(
            targets=["Linear"],
            weights=QuantizationArgs(
                num_bits=4,
                type=QuantizationType.INT,
                strategy=QuantizationStrategy.GROUP,
                group_size=128,
                symmetric=True,
                dynamic=False,
                actorder=ActivationOrdering.WEIGHT,
            ),
        ),
    },
    sequential_targets=["Qwen2VLDecoderLayer"],
    ignore=["lm_head", "re:visual.*"],
    update_size=NUM_CALIBRATION_SAMPLES,
    dampening_frac=dampening_frac
)

SAVE_DIR=f"{model_id.split('/')[1]}-quantized.w4a16

# Perform oneshot
oneshot(
    model=model,
    tokenizer=model_id,
    dataset=ds,
    recipe=recipe,
    max_seq_length=MAX_SEQUENCE_LENGTH,
    num_calibration_samples=NUM_CALIBRATION_SAMPLES,
    trust_remote_code_model=True,
    data_collator=qwen2_vl_data_collator,
    output_dir=SAVE_DIR
)

Vision Taskstextvllm

vllm serve neuralmagic/pixtral-12b-quantized.w8a8 --tensor_parallel_size 1 --max_model_len 25000 --trust_remote_code --max_num_seqs 8 --gpu_memory_utilization 0.9 --dtype float16 --limit_mm_per_prompt image=7

python -m eval.run eval_vllm \
        --model_name neuralmagic/pixtral-12b-quantized.w8a8 \
        --url http://0.0.0.0:8000 \
        --output_dir ~/tmp \
        --eval_name <vision_task_name>

Vision Taskstextvllm

vllm serve neuralmagic/pixtral-12b-quantized.w8a8 --tensor_parallel_size 1 --max_model_len 25000 --trust_remote_code --max_num_seqs 8 --gpu_memory_utilization 0.9 --dtype float16 --limit_mm_per_prompt image=7

python -m eval.run eval_vllm \
        --model_name neuralmagic/pixtral-12b-quantized.w8a8 \
        --url http://0.0.0.0:8000 \
        --output_dir ~/tmp \
        --eval_name <vision_task_name>

Vision Taskstextvllm

vllm serve neuralmagic/pixtral-12b-quantized.w8a8 --tensor_parallel_size 1 --max_model_len 25000 --trust_remote_code --max_num_seqs 8 --gpu_memory_utilization 0.9 --dtype float16 --limit_mm_per_prompt image=7

python -m eval.run eval_vllm \
        --model_name neuralmagic/pixtral-12b-quantized.w8a8 \
        --url http://0.0.0.0:8000 \
        --output_dir ~/tmp \
        --eval_name <vision_task_name>

Vision Taskstextvllm

vllm serve neuralmagic/pixtral-12b-quantized.w8a8 --tensor_parallel_size 1 --max_model_len 25000 --trust_remote_code --max_num_seqs 8 --gpu_memory_utilization 0.9 --dtype float16 --limit_mm_per_prompt image=7

python -m eval.run eval_vllm \
        --model_name neuralmagic/pixtral-12b-quantized.w8a8 \
        --url http://0.0.0.0:8000 \
        --output_dir ~/tmp \
        --eval_name <vision_task_name>

Vision Taskstextvllm

vllm serve neuralmagic/pixtral-12b-quantized.w8a8 --tensor_parallel_size 1 --max_model_len 25000 --trust_remote_code --max_num_seqs 8 --gpu_memory_utilization 0.9 --dtype float16 --limit_mm_per_prompt image=7

python -m eval.run eval_vllm \
        --model_name neuralmagic/pixtral-12b-quantized.w8a8 \
        --url http://0.0.0.0:8000 \
        --output_dir ~/tmp \
        --eval_name <vision_task_name>

Vision Taskstextvllm

vllm serve neuralmagic/pixtral-12b-quantized.w8a8 --tensor_parallel_size 1 --max_model_len 25000 --trust_remote_code --max_num_seqs 8 --gpu_memory_utilization 0.9 --dtype float16 --limit_mm_per_prompt image=7

python -m eval.run eval_vllm \
        --model_name neuralmagic/pixtral-12b-quantized.w8a8 \
        --url http://0.0.0.0:8000 \
        --output_dir ~/tmp \
        --eval_name <vision_task_name>

Vision Taskstextvllm

vllm serve neuralmagic/pixtral-12b-quantized.w8a8 --tensor_parallel_size 1 --max_model_len 25000 --trust_remote_code --max_num_seqs 8 --gpu_memory_utilization 0.9 --dtype float16 --limit_mm_per_prompt image=7

python -m eval.run eval_vllm \
        --model_name neuralmagic/pixtral-12b-quantized.w8a8 \
        --url http://0.0.0.0:8000 \
        --output_dir ~/tmp \
        --eval_name <vision_task_name>

Vision Taskstextvllm

vllm serve neuralmagic/pixtral-12b-quantized.w8a8 --tensor_parallel_size 1 --max_model_len 25000 --trust_remote_code --max_num_seqs 8 --gpu_memory_utilization 0.9 --dtype float16 --limit_mm_per_prompt image=7

python -m eval.run eval_vllm \
        --model_name neuralmagic/pixtral-12b-quantized.w8a8 \
        --url http://0.0.0.0:8000 \
        --output_dir ~/tmp \
        --eval_name <vision_task_name>

Vision Taskstextvllm

vllm serve neuralmagic/pixtral-12b-quantized.w8a8 --tensor_parallel_size 1 --max_model_len 25000 --trust_remote_code --max_num_seqs 8 --gpu_memory_utilization 0.9 --dtype float16 --limit_mm_per_prompt image=7

python -m eval.run eval_vllm \
        --model_name neuralmagic/pixtral-12b-quantized.w8a8 \
        --url http://0.0.0.0:8000 \
        --output_dir ~/tmp \
        --eval_name <vision_task_name>

Vision Taskstextvllm

vllm serve neuralmagic/pixtral-12b-quantized.w8a8 --tensor_parallel_size 1 --max_model_len 25000 --trust_remote_code --max_num_seqs 8 --gpu_memory_utilization 0.9 --dtype float16 --limit_mm_per_prompt image=7

python -m eval.run eval_vllm \
        --model_name neuralmagic/pixtral-12b-quantized.w8a8 \
        --url http://0.0.0.0:8000 \
        --output_dir ~/tmp \
        --eval_name <vision_task_name>

Vision Taskstextvllm

vllm serve neuralmagic/pixtral-12b-quantized.w8a8 --tensor_parallel_size 1 --max_model_len 25000 --trust_remote_code --max_num_seqs 8 --gpu_memory_utilization 0.9 --dtype float16 --limit_mm_per_prompt image=7

python -m eval.run eval_vllm \
        --model_name neuralmagic/pixtral-12b-quantized.w8a8 \
        --url http://0.0.0.0:8000 \
        --output_dir ~/tmp \
        --eval_name <vision_task_name>

Vision Taskstextvllm

vllm serve neuralmagic/pixtral-12b-quantized.w8a8 --tensor_parallel_size 1 --max_model_len 25000 --trust_remote_code --max_num_seqs 8 --gpu_memory_utilization 0.9 --dtype float16 --limit_mm_per_prompt image=7

python -m eval.run eval_vllm \
        --model_name neuralmagic/pixtral-12b-quantized.w8a8 \
        --url http://0.0.0.0:8000 \
        --output_dir ~/tmp \
        --eval_name <vision_task_name>

Vision Taskstextvllm

vllm serve neuralmagic/pixtral-12b-quantized.w8a8 --tensor_parallel_size 1 --max_model_len 25000 --trust_remote_code --max_num_seqs 8 --gpu_memory_utilization 0.9 --dtype float16 --limit_mm_per_prompt image=7

python -m eval.run eval_vllm \
        --model_name neuralmagic/pixtral-12b-quantized.w8a8 \
        --url http://0.0.0.0:8000 \
        --output_dir ~/tmp \
        --eval_name <vision_task_name>

Vision Taskstextvllm

vllm serve neuralmagic/pixtral-12b-quantized.w8a8 --tensor_parallel_size 1 --max_model_len 25000 --trust_remote_code --max_num_seqs 8 --gpu_memory_utilization 0.9 --dtype float16 --limit_mm_per_prompt image=7

python -m eval.run eval_vllm \
        --model_name neuralmagic/pixtral-12b-quantized.w8a8 \
        --url http://0.0.0.0:8000 \
        --output_dir ~/tmp \
        --eval_name <vision_task_name>

Vision Taskstextvllm

vllm serve neuralmagic/pixtral-12b-quantized.w8a8 --tensor_parallel_size 1 --max_model_len 25000 --trust_remote_code --max_num_seqs 8 --gpu_memory_utilization 0.9 --dtype float16 --limit_mm_per_prompt image=7

python -m eval.run eval_vllm \
        --model_name neuralmagic/pixtral-12b-quantized.w8a8 \
        --url http://0.0.0.0:8000 \
        --output_dir ~/tmp \
        --eval_name <vision_task_name>

Vision Taskstextvllm

vllm serve neuralmagic/pixtral-12b-quantized.w8a8 --tensor_parallel_size 1 --max_model_len 25000 --trust_remote_code --max_num_seqs 8 --gpu_memory_utilization 0.9 --dtype float16 --limit_mm_per_prompt image=7

python -m eval.run eval_vllm \
        --model_name neuralmagic/pixtral-12b-quantized.w8a8 \
        --url http://0.0.0.0:8000 \
        --output_dir ~/tmp \
        --eval_name <vision_task_name>

Vision Taskstextvllm

vllm serve neuralmagic/pixtral-12b-quantized.w8a8 --tensor_parallel_size 1 --max_model_len 25000 --trust_remote_code --max_num_seqs 8 --gpu_memory_utilization 0.9 --dtype float16 --limit_mm_per_prompt image=7

python -m eval.run eval_vllm \
        --model_name neuralmagic/pixtral-12b-quantized.w8a8 \
        --url http://0.0.0.0:8000 \
        --output_dir ~/tmp \
        --eval_name <vision_task_name>

Vision Taskstextvllm

vllm serve neuralmagic/pixtral-12b-quantized.w8a8 --tensor_parallel_size 1 --max_model_len 25000 --trust_remote_code --max_num_seqs 8 --gpu_memory_utilization 0.9 --dtype float16 --limit_mm_per_prompt image=7

python -m eval.run eval_vllm \
        --model_name neuralmagic/pixtral-12b-quantized.w8a8 \
        --url http://0.0.0.0:8000 \
        --output_dir ~/tmp \
        --eval_name <vision_task_name>

Vision Taskstextvllm

vllm serve neuralmagic/pixtral-12b-quantized.w8a8 --tensor_parallel_size 1 --max_model_len 25000 --trust_remote_code --max_num_seqs 8 --gpu_memory_utilization 0.9 --dtype float16 --limit_mm_per_prompt image=7

python -m eval.run eval_vllm \
        --model_name neuralmagic/pixtral-12b-quantized.w8a8 \
        --url http://0.0.0.0:8000 \
        --output_dir ~/tmp \
        --eval_name <vision_task_name>

Vision Taskstextvllm

vllm serve neuralmagic/pixtral-12b-quantized.w8a8 --tensor_parallel_size 1 --max_model_len 25000 --trust_remote_code --max_num_seqs 8 --gpu_memory_utilization 0.9 --dtype float16 --limit_mm_per_prompt image=7

python -m eval.run eval_vllm \
        --model_name neuralmagic/pixtral-12b-quantized.w8a8 \
        --url http://0.0.0.0:8000 \
        --output_dir ~/tmp \
        --eval_name <vision_task_name>

Vision Taskstextvllm

vllm serve neuralmagic/pixtral-12b-quantized.w8a8 --tensor_parallel_size 1 --max_model_len 25000 --trust_remote_code --max_num_seqs 8 --gpu_memory_utilization 0.9 --dtype float16 --limit_mm_per_prompt image=7

python -m eval.run eval_vllm \
        --model_name neuralmagic/pixtral-12b-quantized.w8a8 \
        --url http://0.0.0.0:8000 \
        --output_dir ~/tmp \
        --eval_name <vision_task_name>

Vision Taskstextvllm

vllm serve neuralmagic/pixtral-12b-quantized.w8a8 --tensor_parallel_size 1 --max_model_len 25000 --trust_remote_code --max_num_seqs 8 --gpu_memory_utilization 0.9 --dtype float16 --limit_mm_per_prompt image=7

python -m eval.run eval_vllm \
        --model_name neuralmagic/pixtral-12b-quantized.w8a8 \
        --url http://0.0.0.0:8000 \
        --output_dir ~/tmp \
        --eval_name <vision_task_name>

Vision Taskstextvllm

vllm serve neuralmagic/pixtral-12b-quantized.w8a8 --tensor_parallel_size 1 --max_model_len 25000 --trust_remote_code --max_num_seqs 8 --gpu_memory_utilization 0.9 --dtype float16 --limit_mm_per_prompt image=7

python -m eval.run eval_vllm \
        --model_name neuralmagic/pixtral-12b-quantized.w8a8 \
        --url http://0.0.0.0:8000 \
        --output_dir ~/tmp \
        --eval_name <vision_task_name>

Vision Taskstextvllm

vllm serve neuralmagic/pixtral-12b-quantized.w8a8 --tensor_parallel_size 1 --max_model_len 25000 --trust_remote_code --max_num_seqs 8 --gpu_memory_utilization 0.9 --dtype float16 --limit_mm_per_prompt image=7

python -m eval.run eval_vllm \
        --model_name neuralmagic/pixtral-12b-quantized.w8a8 \
        --url http://0.0.0.0:8000 \
        --output_dir ~/tmp \
        --eval_name <vision_task_name>

Vision Taskstextvllm

vllm serve neuralmagic/pixtral-12b-quantized.w8a8 --tensor_parallel_size 1 --max_model_len 25000 --trust_remote_code --max_num_seqs 8 --gpu_memory_utilization 0.9 --dtype float16 --limit_mm_per_prompt image=7

python -m eval.run eval_vllm \
        --model_name neuralmagic/pixtral-12b-quantized.w8a8 \
        --url http://0.0.0.0:8000 \
        --output_dir ~/tmp \
        --eval_name <vision_task_name>

Vision Taskstextvllm

vllm serve neuralmagic/pixtral-12b-quantized.w8a8 --tensor_parallel_size 1 --max_model_len 25000 --trust_remote_code --max_num_seqs 8 --gpu_memory_utilization 0.9 --dtype float16 --limit_mm_per_prompt image=7

python -m eval.run eval_vllm \
        --model_name neuralmagic/pixtral-12b-quantized.w8a8 \
        --url http://0.0.0.0:8000 \
        --output_dir ~/tmp \
        --eval_name <vision_task_name>

Vision Taskstextvllm

vllm serve neuralmagic/pixtral-12b-quantized.w8a8 --tensor_parallel_size 1 --max_model_len 25000 --trust_remote_code --max_num_seqs 8 --gpu_memory_utilization 0.9 --dtype float16 --limit_mm_per_prompt image=7

python -m eval.run eval_vllm \
        --model_name neuralmagic/pixtral-12b-quantized.w8a8 \
        --url http://0.0.0.0:8000 \
        --output_dir ~/tmp \
        --eval_name <vision_task_name>

Vision Taskstextvllm

vllm serve neuralmagic/pixtral-12b-quantized.w8a8 --tensor_parallel_size 1 --max_model_len 25000 --trust_remote_code --max_num_seqs 8 --gpu_memory_utilization 0.9 --dtype float16 --limit_mm_per_prompt image=7

python -m eval.run eval_vllm \
        --model_name neuralmagic/pixtral-12b-quantized.w8a8 \
        --url http://0.0.0.0:8000 \
        --output_dir ~/tmp \
        --eval_name <vision_task_name>

Vision Taskstextvllm

vllm serve neuralmagic/pixtral-12b-quantized.w8a8 --tensor_parallel_size 1 --max_model_len 25000 --trust_remote_code --max_num_seqs 8 --gpu_memory_utilization 0.9 --dtype float16 --limit_mm_per_prompt image=7

python -m eval.run eval_vllm \
        --model_name neuralmagic/pixtral-12b-quantized.w8a8 \
        --url http://0.0.0.0:8000 \
        --output_dir ~/tmp \
        --eval_name <vision_task_name>

Vision Taskstextvllm

vllm serve neuralmagic/pixtral-12b-quantized.w8a8 --tensor_parallel_size 1 --max_model_len 25000 --trust_remote_code --max_num_seqs 8 --gpu_memory_utilization 0.9 --dtype float16 --limit_mm_per_prompt image=7

python -m eval.run eval_vllm \
        --model_name neuralmagic/pixtral-12b-quantized.w8a8 \
        --url http://0.0.0.0:8000 \
        --output_dir ~/tmp \
        --eval_name <vision_task_name>

Vision Taskstextvllm

vllm serve neuralmagic/pixtral-12b-quantized.w8a8 --tensor_parallel_size 1 --max_model_len 25000 --trust_remote_code --max_num_seqs 8 --gpu_memory_utilization 0.9 --dtype float16 --limit_mm_per_prompt image=7

python -m eval.run eval_vllm \
        --model_name neuralmagic/pixtral-12b-quantized.w8a8 \
        --url http://0.0.0.0:8000 \
        --output_dir ~/tmp \
        --eval_name <vision_task_name>

Vision Taskstextvllm

vllm serve neuralmagic/pixtral-12b-quantized.w8a8 --tensor_parallel_size 1 --max_model_len 25000 --trust_remote_code --max_num_seqs 8 --gpu_memory_utilization 0.9 --dtype float16 --limit_mm_per_prompt image=7

python -m eval.run eval_vllm \
        --model_name neuralmagic/pixtral-12b-quantized.w8a8 \
        --url http://0.0.0.0:8000 \
        --output_dir ~/tmp \
        --eval_name <vision_task_name>

Vision Taskstextvllm

vllm serve neuralmagic/pixtral-12b-quantized.w8a8 --tensor_parallel_size 1 --max_model_len 25000 --trust_remote_code --max_num_seqs 8 --gpu_memory_utilization 0.9 --dtype float16 --limit_mm_per_prompt image=7

python -m eval.run eval_vllm \
        --model_name neuralmagic/pixtral-12b-quantized.w8a8 \
        --url http://0.0.0.0:8000 \
        --output_dir ~/tmp \
        --eval_name <vision_task_name>

Vision Taskstextvllm

vllm serve neuralmagic/pixtral-12b-quantized.w8a8 --tensor_parallel_size 1 --max_model_len 25000 --trust_remote_code --max_num_seqs 8 --gpu_memory_utilization 0.9 --dtype float16 --limit_mm_per_prompt image=7

python -m eval.run eval_vllm \
        --model_name neuralmagic/pixtral-12b-quantized.w8a8 \
        --url http://0.0.0.0:8000 \
        --output_dir ~/tmp \
        --eval_name <vision_task_name>

Vision Taskstextvllm

vllm serve neuralmagic/pixtral-12b-quantized.w8a8 --tensor_parallel_size 1 --max_model_len 25000 --trust_remote_code --max_num_seqs 8 --gpu_memory_utilization 0.9 --dtype float16 --limit_mm_per_prompt image=7

python -m eval.run eval_vllm \
        --model_name neuralmagic/pixtral-12b-quantized.w8a8 \
        --url http://0.0.0.0:8000 \
        --output_dir ~/tmp \
        --eval_name <vision_task_name>

Vision Taskstextvllm

vllm serve neuralmagic/pixtral-12b-quantized.w8a8 --tensor_parallel_size 1 --max_model_len 25000 --trust_remote_code --max_num_seqs 8 --gpu_memory_utilization 0.9 --dtype float16 --limit_mm_per_prompt image=7

python -m eval.run eval_vllm \
        --model_name neuralmagic/pixtral-12b-quantized.w8a8 \
        --url http://0.0.0.0:8000 \
        --output_dir ~/tmp \
        --eval_name <vision_task_name>

Vision Taskstextvllm

vllm serve neuralmagic/pixtral-12b-quantized.w8a8 --tensor_parallel_size 1 --max_model_len 25000 --trust_remote_code --max_num_seqs 8 --gpu_memory_utilization 0.9 --dtype float16 --limit_mm_per_prompt image=7

python -m eval.run eval_vllm \
        --model_name neuralmagic/pixtral-12b-quantized.w8a8 \
        --url http://0.0.0.0:8000 \
        --output_dir ~/tmp \
        --eval_name <vision_task_name>

Vision Taskstextvllm

vllm serve neuralmagic/pixtral-12b-quantized.w8a8 --tensor_parallel_size 1 --max_model_len 25000 --trust_remote_code --max_num_seqs 8 --gpu_memory_utilization 0.9 --dtype float16 --limit_mm_per_prompt image=7

python -m eval.run eval_vllm \
        --model_name neuralmagic/pixtral-12b-quantized.w8a8 \
        --url http://0.0.0.0:8000 \
        --output_dir ~/tmp \
        --eval_name <vision_task_name>

Vision Taskstextvllm

vllm serve neuralmagic/pixtral-12b-quantized.w8a8 --tensor_parallel_size 1 --max_model_len 25000 --trust_remote_code --max_num_seqs 8 --gpu_memory_utilization 0.9 --dtype float16 --limit_mm_per_prompt image=7

python -m eval.run eval_vllm \
        --model_name neuralmagic/pixtral-12b-quantized.w8a8 \
        --url http://0.0.0.0:8000 \
        --output_dir ~/tmp \
        --eval_name <vision_task_name>

Vision Taskstextvllm

vllm serve neuralmagic/pixtral-12b-quantized.w8a8 --tensor_parallel_size 1 --max_model_len 25000 --trust_remote_code --max_num_seqs 8 --gpu_memory_utilization 0.9 --dtype float16 --limit_mm_per_prompt image=7

python -m eval.run eval_vllm \
        --model_name neuralmagic/pixtral-12b-quantized.w8a8 \
        --url http://0.0.0.0:8000 \
        --output_dir ~/tmp \
        --eval_name <vision_task_name>

Vision Taskstextvllm

vllm serve neuralmagic/pixtral-12b-quantized.w8a8 --tensor_parallel_size 1 --max_model_len 25000 --trust_remote_code --max_num_seqs 8 --gpu_memory_utilization 0.9 --dtype float16 --limit_mm_per_prompt image=7

python -m eval.run eval_vllm \
        --model_name neuralmagic/pixtral-12b-quantized.w8a8 \
        --url http://0.0.0.0:8000 \
        --output_dir ~/tmp \
        --eval_name <vision_task_name>

Vision Taskstextvllm

vllm serve neuralmagic/pixtral-12b-quantized.w8a8 --tensor_parallel_size 1 --max_model_len 25000 --trust_remote_code --max_num_seqs 8 --gpu_memory_utilization 0.9 --dtype float16 --limit_mm_per_prompt image=7

python -m eval.run eval_vllm \
        --model_name neuralmagic/pixtral-12b-quantized.w8a8 \
        --url http://0.0.0.0:8000 \
        --output_dir ~/tmp \
        --eval_name <vision_task_name>

Text-based Taskstextvllm

lm_eval \
  --model vllm \
  --model_args pretrained="<model_name>",dtype=auto,add_bos_token=True,max_model_len=4096,tensor_parallel_size=<n>,gpu_memory_utilization=0.8,enable_chunked_prefill=True,trust_remote_code=True \
  --tasks mmlu \
  --num_fewshot 5 \
  --batch_size auto \
  --output_path output_dir

Text-based Taskstextvllm

lm_eval \
  --model vllm \
  --model_args pretrained="<model_name>",dtype=auto,add_bos_token=True,max_model_len=4096,tensor_parallel_size=<n>,gpu_memory_utilization=0.8,enable_chunked_prefill=True,trust_remote_code=True \
  --tasks mmlu \
  --num_fewshot 5 \
  --batch_size auto \
  --output_path output_dir

Text-based Taskstextvllm

lm_eval \
  --model vllm \
  --model_args pretrained="<model_name>",dtype=auto,add_bos_token=True,max_model_len=4096,tensor_parallel_size=<n>,gpu_memory_utilization=0.8,enable_chunked_prefill=True,trust_remote_code=True \
  --tasks mmlu \
  --num_fewshot 5 \
  --batch_size auto \
  --output_path output_dir

Text-based Taskstextvllm

lm_eval \
  --model vllm \
  --model_args pretrained="<model_name>",dtype=auto,add_bos_token=True,max_model_len=4096,tensor_parallel_size=<n>,gpu_memory_utilization=0.8,enable_chunked_prefill=True,trust_remote_code=True \
  --tasks mmlu \
  --num_fewshot 5 \
  --batch_size auto \
  --output_path output_dir

Text-based Taskstextvllm

lm_eval \
  --model vllm \
  --model_args pretrained="<model_name>",dtype=auto,add_bos_token=True,max_model_len=4096,tensor_parallel_size=<n>,gpu_memory_utilization=0.8,enable_chunked_prefill=True,trust_remote_code=True \
  --tasks mmlu \
  --num_fewshot 5 \
  --batch_size auto \
  --output_path output_dir

Text-based Taskstextvllm

lm_eval \
  --model vllm \
  --model_args pretrained="<model_name>",dtype=auto,add_bos_token=True,max_model_len=4096,tensor_parallel_size=<n>,gpu_memory_utilization=0.8,enable_chunked_prefill=True,trust_remote_code=True \
  --tasks mmlu \
  --num_fewshot 5 \
  --batch_size auto \
  --output_path output_dir

Text-based Taskstextvllm

lm_eval \
  --model vllm \
  --model_args pretrained="<model_name>",dtype=auto,add_bos_token=True,max_model_len=4096,tensor_parallel_size=<n>,gpu_memory_utilization=0.8,enable_chunked_prefill=True,trust_remote_code=True \
  --tasks mmlu \
  --num_fewshot 5 \
  --batch_size auto \
  --output_path output_dir

Text-based Taskstextvllm

lm_eval \
  --model vllm \
  --model_args pretrained="<model_name>",dtype=auto,add_bos_token=True,max_model_len=4096,tensor_parallel_size=<n>,gpu_memory_utilization=0.8,enable_chunked_prefill=True,trust_remote_code=True \
  --tasks mmlu \
  --num_fewshot 5 \
  --batch_size auto \
  --output_path output_dir

Text-based Taskstextvllm

lm_eval \
  --model vllm \
  --model_args pretrained="<model_name>",dtype=auto,add_bos_token=True,max_model_len=4096,tensor_parallel_size=<n>,gpu_memory_utilization=0.8,enable_chunked_prefill=True,trust_remote_code=True \
  --tasks mmlu \
  --num_fewshot 5 \
  --batch_size auto \
  --output_path output_dir

Text-based Taskstextvllm

lm_eval \
  --model vllm \
  --model_args pretrained="<model_name>",dtype=auto,add_bos_token=True,max_model_len=4096,tensor_parallel_size=<n>,gpu_memory_utilization=0.8,enable_chunked_prefill=True,trust_remote_code=True \
  --tasks mmlu \
  --num_fewshot 5 \
  --batch_size auto \
  --output_path output_dir

Text-based Taskstextvllm

lm_eval \
  --model vllm \
  --model_args pretrained="<model_name>",dtype=auto,add_bos_token=True,max_model_len=4096,tensor_parallel_size=<n>,gpu_memory_utilization=0.8,enable_chunked_prefill=True,trust_remote_code=True \
  --tasks mmlu \
  --num_fewshot 5 \
  --batch_size auto \
  --output_path output_dir

Text-based Taskstextvllm

lm_eval \
  --model vllm \
  --model_args pretrained="<model_name>",dtype=auto,add_bos_token=True,max_model_len=4096,tensor_parallel_size=<n>,gpu_memory_utilization=0.8,enable_chunked_prefill=True,trust_remote_code=True \
  --tasks mmlu \
  --num_fewshot 5 \
  --batch_size auto \
  --output_path output_dir

Text-based Taskstextvllm

lm_eval \
  --model vllm \
  --model_args pretrained="<model_name>",dtype=auto,add_bos_token=True,max_model_len=4096,tensor_parallel_size=<n>,gpu_memory_utilization=0.8,enable_chunked_prefill=True,trust_remote_code=True \
  --tasks mmlu \
  --num_fewshot 5 \
  --batch_size auto \
  --output_path output_dir

Text-based Taskstextvllm

lm_eval \
  --model vllm \
  --model_args pretrained="<model_name>",dtype=auto,add_bos_token=True,max_model_len=4096,tensor_parallel_size=<n>,gpu_memory_utilization=0.8,enable_chunked_prefill=True,trust_remote_code=True \
  --tasks mmlu \
  --num_fewshot 5 \
  --batch_size auto \
  --output_path output_dir

Text-based Taskstextvllm

lm_eval \
  --model vllm \
  --model_args pretrained="<model_name>",dtype=auto,add_bos_token=True,max_model_len=4096,tensor_parallel_size=<n>,gpu_memory_utilization=0.8,enable_chunked_prefill=True,trust_remote_code=True \
  --tasks mmlu \
  --num_fewshot 5 \
  --batch_size auto \
  --output_path output_dir

Text-based Taskstextvllm

lm_eval \
  --model vllm \
  --model_args pretrained="<model_name>",dtype=auto,add_bos_token=True,max_model_len=4096,tensor_parallel_size=<n>,gpu_memory_utilization=0.8,enable_chunked_prefill=True,trust_remote_code=True \
  --tasks mmlu \
  --num_fewshot 5 \
  --batch_size auto \
  --output_path output_dir

Text-based Taskstextvllm

lm_eval \
  --model vllm \
  --model_args pretrained="<model_name>",dtype=auto,add_bos_token=True,max_model_len=4096,tensor_parallel_size=<n>,gpu_memory_utilization=0.8,enable_chunked_prefill=True,trust_remote_code=True \
  --tasks mmlu \
  --num_fewshot 5 \
  --batch_size auto \
  --output_path output_dir

Text-based Taskstextvllm

lm_eval \
  --model vllm \
  --model_args pretrained="<model_name>",dtype=auto,add_bos_token=True,max_model_len=4096,tensor_parallel_size=<n>,gpu_memory_utilization=0.8,enable_chunked_prefill=True,trust_remote_code=True \
  --tasks mmlu \
  --num_fewshot 5 \
  --batch_size auto \
  --output_path output_dir

Text-based Taskstextvllm

lm_eval \
  --model vllm \
  --model_args pretrained="<model_name>",dtype=auto,add_bos_token=True,max_model_len=4096,tensor_parallel_size=<n>,gpu_memory_utilization=0.8,enable_chunked_prefill=True,trust_remote_code=True \
  --tasks mmlu \
  --num_fewshot 5 \
  --batch_size auto \
  --output_path output_dir

Text-based Taskstextvllm

lm_eval \
  --model vllm \
  --model_args pretrained="<model_name>",dtype=auto,add_bos_token=True,max_model_len=4096,tensor_parallel_size=<n>,gpu_memory_utilization=0.8,enable_chunked_prefill=True,trust_remote_code=True \
  --tasks mmlu \
  --num_fewshot 5 \
  --batch_size auto \
  --output_path output_dir

Text-based Taskstextvllm

lm_eval \
  --model vllm \
  --model_args pretrained="<model_name>",dtype=auto,add_bos_token=True,max_model_len=4096,tensor_parallel_size=<n>,gpu_memory_utilization=0.8,enable_chunked_prefill=True,trust_remote_code=True \
  --tasks mmlu \
  --num_fewshot 5 \
  --batch_size auto \
  --output_path output_dir

Text-based Taskstextvllm

lm_eval \
  --model vllm \
  --model_args pretrained="<model_name>",dtype=auto,add_bos_token=True,max_model_len=4096,tensor_parallel_size=<n>,gpu_memory_utilization=0.8,enable_chunked_prefill=True,trust_remote_code=True \
  --tasks mmlu \
  --num_fewshot 5 \
  --batch_size auto \
  --output_path output_dir

Text-based Taskstextvllm

lm_eval \
  --model vllm \
  --model_args pretrained="<model_name>",dtype=auto,add_bos_token=True,max_model_len=4096,tensor_parallel_size=<n>,gpu_memory_utilization=0.8,enable_chunked_prefill=True,trust_remote_code=True \
  --tasks mmlu \
  --num_fewshot 5 \
  --batch_size auto \
  --output_path output_dir

Text-based Taskstextvllm

lm_eval \
  --model vllm \
  --model_args pretrained="<model_name>",dtype=auto,add_bos_token=True,max_model_len=4096,tensor_parallel_size=<n>,gpu_memory_utilization=0.8,enable_chunked_prefill=True,trust_remote_code=True \
  --tasks mmlu \
  --num_fewshot 5 \
  --batch_size auto \
  --output_path output_dir

Text-based Taskstextvllm

lm_eval \
  --model vllm \
  --model_args pretrained="<model_name>",dtype=auto,add_bos_token=True,max_model_len=4096,tensor_parallel_size=<n>,gpu_memory_utilization=0.8,enable_chunked_prefill=True,trust_remote_code=True \
  --tasks mmlu \
  --num_fewshot 5 \
  --batch_size auto \
  --output_path output_dir

Text-based Taskstextvllm

lm_eval \
  --model vllm \
  --model_args pretrained="<model_name>",dtype=auto,add_bos_token=True,max_model_len=4096,tensor_parallel_size=<n>,gpu_memory_utilization=0.8,enable_chunked_prefill=True,trust_remote_code=True \
  --tasks mmlu \
  --num_fewshot 5 \
  --batch_size auto \
  --output_path output_dir

Text-based Taskstextvllm

lm_eval \
  --model vllm \
  --model_args pretrained="<model_name>",dtype=auto,add_bos_token=True,max_model_len=4096,tensor_parallel_size=<n>,gpu_memory_utilization=0.8,enable_chunked_prefill=True,trust_remote_code=True \
  --tasks mmlu \
  --num_fewshot 5 \
  --batch_size auto \
  --output_path output_dir

Text-based Taskstextvllm

lm_eval \
  --model vllm \
  --model_args pretrained="<model_name>",dtype=auto,add_bos_token=True,max_model_len=4096,tensor_parallel_size=<n>,gpu_memory_utilization=0.8,enable_chunked_prefill=True,trust_remote_code=True \
  --tasks mmlu \
  --num_fewshot 5 \
  --batch_size auto \
  --output_path output_dir

Text-based Taskstextvllm

lm_eval \
  --model vllm \
  --model_args pretrained="<model_name>",dtype=auto,add_bos_token=True,max_model_len=4096,tensor_parallel_size=<n>,gpu_memory_utilization=0.8,enable_chunked_prefill=True,trust_remote_code=True \
  --tasks mmlu \
  --num_fewshot 5 \
  --batch_size auto \
  --output_path output_dir

Text-based Taskstextvllm

lm_eval \
  --model vllm \
  --model_args pretrained="<model_name>",dtype=auto,add_bos_token=True,max_model_len=4096,tensor_parallel_size=<n>,gpu_memory_utilization=0.8,enable_chunked_prefill=True,trust_remote_code=True \
  --tasks mmlu \
  --num_fewshot 5 \
  --batch_size auto \
  --output_path output_dir

Text-based Taskstextvllm

lm_eval \
  --model vllm \
  --model_args pretrained="<model_name>",dtype=auto,add_bos_token=True,max_model_len=4096,tensor_parallel_size=<n>,gpu_memory_utilization=0.8,enable_chunked_prefill=True,trust_remote_code=True \
  --tasks mmlu \
  --num_fewshot 5 \
  --batch_size auto \
  --output_path output_dir

Text-based Taskstextvllm

lm_eval \
  --model vllm \
  --model_args pretrained="<model_name>",dtype=auto,add_bos_token=True,max_model_len=4096,tensor_parallel_size=<n>,gpu_memory_utilization=0.8,enable_chunked_prefill=True,trust_remote_code=True \
  --tasks mmlu \
  --num_fewshot 5 \
  --batch_size auto \
  --output_path output_dir

Text-based Taskstextvllm

lm_eval \
  --model vllm \
  --model_args pretrained="<model_name>",dtype=auto,add_bos_token=True,max_model_len=4096,tensor_parallel_size=<n>,gpu_memory_utilization=0.8,enable_chunked_prefill=True,trust_remote_code=True \
  --tasks mmlu \
  --num_fewshot 5 \
  --batch_size auto \
  --output_path output_dir

Text-based Taskstextvllm

lm_eval \
  --model vllm \
  --model_args pretrained="<model_name>",dtype=auto,add_bos_token=True,max_model_len=4096,tensor_parallel_size=<n>,gpu_memory_utilization=0.8,enable_chunked_prefill=True,trust_remote_code=True \
  --tasks mmlu \
  --num_fewshot 5 \
  --batch_size auto \
  --output_path output_dir

Text-based Taskstextvllm

lm_eval \
  --model vllm \
  --model_args pretrained="<model_name>",dtype=auto,add_bos_token=True,max_model_len=4096,tensor_parallel_size=<n>,gpu_memory_utilization=0.8,enable_chunked_prefill=True,trust_remote_code=True \
  --tasks mmlu \
  --num_fewshot 5 \
  --batch_size auto \
  --output_path output_dir

Text-based Taskstextvllm

lm_eval \
  --model vllm \
  --model_args pretrained="<model_name>",dtype=auto,add_bos_token=True,max_model_len=4096,tensor_parallel_size=<n>,gpu_memory_utilization=0.8,enable_chunked_prefill=True,trust_remote_code=True \
  --tasks mmlu \
  --num_fewshot 5 \
  --batch_size auto \
  --output_path output_dir

Text-based Taskstextvllm

lm_eval \
  --model vllm \
  --model_args pretrained="<model_name>",dtype=auto,add_bos_token=True,max_model_len=4096,tensor_parallel_size=<n>,gpu_memory_utilization=0.8,enable_chunked_prefill=True,trust_remote_code=True \
  --tasks mmlu \
  --num_fewshot 5 \
  --batch_size auto \
  --output_path output_dir

Text-based Taskstextvllm

lm_eval \
  --model vllm \
  --model_args pretrained="<model_name>",dtype=auto,add_bos_token=True,max_model_len=4096,tensor_parallel_size=<n>,gpu_memory_utilization=0.8,enable_chunked_prefill=True,trust_remote_code=True \
  --tasks mmlu \
  --num_fewshot 5 \
  --batch_size auto \
  --output_path output_dir

Text-based Taskstextvllm

lm_eval \
  --model vllm \
  --model_args pretrained="<model_name>",dtype=auto,add_bos_token=True,max_model_len=4096,tensor_parallel_size=<n>,gpu_memory_utilization=0.8,enable_chunked_prefill=True,trust_remote_code=True \
  --tasks mmlu \
  --num_fewshot 5 \
  --batch_size auto \
  --output_path output_dir

Text-based Taskstextvllm

lm_eval \
  --model vllm \
  --model_args pretrained="<model_name>",dtype=auto,add_bos_token=True,max_model_len=4096,tensor_parallel_size=<n>,gpu_memory_utilization=0.8,enable_chunked_prefill=True,trust_remote_code=True \
  --tasks mmlu \
  --num_fewshot 5 \
  --batch_size auto \
  --output_path output_dir

Text-based Taskstextvllm

lm_eval \
  --model vllm \
  --model_args pretrained="<model_name>",dtype=auto,add_bos_token=True,max_model_len=4096,tensor_parallel_size=<n>,gpu_memory_utilization=0.8,enable_chunked_prefill=True,trust_remote_code=True \
  --tasks mmlu \
  --num_fewshot 5 \
  --batch_size auto \
  --output_path output_dir

Text-based Taskstextvllm

lm_eval \
  --model vllm \
  --model_args pretrained="<model_name>",dtype=auto,add_bos_token=True,max_model_len=4096,tensor_parallel_size=<n>,gpu_memory_utilization=0.8,enable_chunked_prefill=True,trust_remote_code=True \
  --tasks mmlu \
  --num_fewshot 5 \
  --batch_size auto \
  --output_path output_dir

text

guidellm --model neuralmagic/Qwen2-VL-72B-Instruct-quantized.w4a16 --target "http://localhost:8000/v1" --data-type emulated --data prompt_tokens=<prompt_tokens>,generated_tokens=<generated_tokens>,images=<num_images>,width=<image_width>,height=<image_height> --max seconds 120 --backend aiohttp_server

text

guidellm --model neuralmagic/Qwen2-VL-72B-Instruct-quantized.w4a16 --target "http://localhost:8000/v1" --data-type emulated --data prompt_tokens=<prompt_tokens>,generated_tokens=<generated_tokens>,images=<num_images>,width=<image_width>,height=<image_height> --max seconds 120 --backend aiohttp_server

text

guidellm --model neuralmagic/Qwen2-VL-72B-Instruct-quantized.w4a16 --target "http://localhost:8000/v1" --data-type emulated --data prompt_tokens=<prompt_tokens>,generated_tokens=<generated_tokens>,images=<num_images>,width=<image_width>,height=<image_height> --max seconds 120 --backend aiohttp_server

text

guidellm --model neuralmagic/Qwen2-VL-72B-Instruct-quantized.w4a16 --target "http://localhost:8000/v1" --data-type emulated --data prompt_tokens=<prompt_tokens>,generated_tokens=<generated_tokens>,images=<num_images>,width=<image_width>,height=<image_height> --max seconds 120 --backend aiohttp_server

text

guidellm --model neuralmagic/Qwen2-VL-72B-Instruct-quantized.w4a16 --target "http://localhost:8000/v1" --data-type emulated --data prompt_tokens=<prompt_tokens>,generated_tokens=<generated_tokens>,images=<num_images>,width=<image_width>,height=<image_height> --max seconds 120 --backend aiohttp_server

text

guidellm --model neuralmagic/Qwen2-VL-72B-Instruct-quantized.w4a16 --target "http://localhost:8000/v1" --data-type emulated --data prompt_tokens=<prompt_tokens>,generated_tokens=<generated_tokens>,images=<num_images>,width=<image_width>,height=<image_height> --max seconds 120 --backend aiohttp_server

text

guidellm --model neuralmagic/Qwen2-VL-72B-Instruct-quantized.w4a16 --target "http://localhost:8000/v1" --data-type emulated --data prompt_tokens=<prompt_tokens>,generated_tokens=<generated_tokens>,images=<num_images>,width=<image_width>,height=<image_height> --max seconds 120 --backend aiohttp_server

text

guidellm --model neuralmagic/Qwen2-VL-72B-Instruct-quantized.w4a16 --target "http://localhost:8000/v1" --data-type emulated --data prompt_tokens=<prompt_tokens>,generated_tokens=<generated_tokens>,images=<num_images>,width=<image_width>,height=<image_height> --max seconds 120 --backend aiohttp_server

text

guidellm --model neuralmagic/Qwen2-VL-72B-Instruct-quantized.w4a16 --target "http://localhost:8000/v1" --data-type emulated --data prompt_tokens=<prompt_tokens>,generated_tokens=<generated_tokens>,images=<num_images>,width=<image_width>,height=<image_height> --max seconds 120 --backend aiohttp_server

text

guidellm --model neuralmagic/Qwen2-VL-72B-Instruct-quantized.w4a16 --target "http://localhost:8000/v1" --data-type emulated --data prompt_tokens=<prompt_tokens>,generated_tokens=<generated_tokens>,images=<num_images>,width=<image_width>,height=<image_height> --max seconds 120 --backend aiohttp_server

text

guidellm --model neuralmagic/Qwen2-VL-72B-Instruct-quantized.w4a16 --target "http://localhost:8000/v1" --data-type emulated --data prompt_tokens=<prompt_tokens>,generated_tokens=<generated_tokens>,images=<num_images>,width=<image_width>,height=<image_height> --max seconds 120 --backend aiohttp_server

text

guidellm --model neuralmagic/Qwen2-VL-72B-Instruct-quantized.w4a16 --target "http://localhost:8000/v1" --data-type emulated --data prompt_tokens=<prompt_tokens>,generated_tokens=<generated_tokens>,images=<num_images>,width=<image_width>,height=<image_height> --max seconds 120 --backend aiohttp_server

text

guidellm --model neuralmagic/Qwen2-VL-72B-Instruct-quantized.w4a16 --target "http://localhost:8000/v1" --data-type emulated --data prompt_tokens=<prompt_tokens>,generated_tokens=<generated_tokens>,images=<num_images>,width=<image_width>,height=<image_height> --max seconds 120 --backend aiohttp_server

text

guidellm --model neuralmagic/Qwen2-VL-72B-Instruct-quantized.w4a16 --target "http://localhost:8000/v1" --data-type emulated --data prompt_tokens=<prompt_tokens>,generated_tokens=<generated_tokens>,images=<num_images>,width=<image_width>,height=<image_height> --max seconds 120 --backend aiohttp_server

text

guidellm --model neuralmagic/Qwen2-VL-72B-Instruct-quantized.w4a16 --target "http://localhost:8000/v1" --data-type emulated --data prompt_tokens=<prompt_tokens>,generated_tokens=<generated_tokens>,images=<num_images>,width=<image_width>,height=<image_height> --max seconds 120 --backend aiohttp_server

text

guidellm --model neuralmagic/Qwen2-VL-72B-Instruct-quantized.w4a16 --target "http://localhost:8000/v1" --data-type emulated --data prompt_tokens=<prompt_tokens>,generated_tokens=<generated_tokens>,images=<num_images>,width=<image_width>,height=<image_height> --max seconds 120 --backend aiohttp_server

text

guidellm --model neuralmagic/Qwen2-VL-72B-Instruct-quantized.w4a16 --target "http://localhost:8000/v1" --data-type emulated --data prompt_tokens=<prompt_tokens>,generated_tokens=<generated_tokens>,images=<num_images>,width=<image_width>,height=<image_height> --max seconds 120 --backend aiohttp_server

text

guidellm --model neuralmagic/Qwen2-VL-72B-Instruct-quantized.w4a16 --target "http://localhost:8000/v1" --data-type emulated --data prompt_tokens=<prompt_tokens>,generated_tokens=<generated_tokens>,images=<num_images>,width=<image_width>,height=<image_height> --max seconds 120 --backend aiohttp_server

text

guidellm --model neuralmagic/Qwen2-VL-72B-Instruct-quantized.w4a16 --target "http://localhost:8000/v1" --data-type emulated --data prompt_tokens=<prompt_tokens>,generated_tokens=<generated_tokens>,images=<num_images>,width=<image_width>,height=<image_height> --max seconds 120 --backend aiohttp_server

text

guidellm --model neuralmagic/Qwen2-VL-72B-Instruct-quantized.w4a16 --target "http://localhost:8000/v1" --data-type emulated --data prompt_tokens=<prompt_tokens>,generated_tokens=<generated_tokens>,images=<num_images>,width=<image_width>,height=<image_height> --max seconds 120 --backend aiohttp_server

text

guidellm --model neuralmagic/Qwen2-VL-72B-Instruct-quantized.w4a16 --target "http://localhost:8000/v1" --data-type emulated --data prompt_tokens=<prompt_tokens>,generated_tokens=<generated_tokens>,images=<num_images>,width=<image_width>,height=<image_height> --max seconds 120 --backend aiohttp_server

text

guidellm --model neuralmagic/Qwen2-VL-72B-Instruct-quantized.w4a16 --target "http://localhost:8000/v1" --data-type emulated --data prompt_tokens=<prompt_tokens>,generated_tokens=<generated_tokens>,images=<num_images>,width=<image_width>,height=<image_height> --max seconds 120 --backend aiohttp_server

text

guidellm --model neuralmagic/Qwen2-VL-72B-Instruct-quantized.w4a16 --target "http://localhost:8000/v1" --data-type emulated --data prompt_tokens=<prompt_tokens>,generated_tokens=<generated_tokens>,images=<num_images>,width=<image_width>,height=<image_height> --max seconds 120 --backend aiohttp_server

text

guidellm --model neuralmagic/Qwen2-VL-72B-Instruct-quantized.w4a16 --target "http://localhost:8000/v1" --data-type emulated --data prompt_tokens=<prompt_tokens>,generated_tokens=<generated_tokens>,images=<num_images>,width=<image_width>,height=<image_height> --max seconds 120 --backend aiohttp_server

text

guidellm --model neuralmagic/Qwen2-VL-72B-Instruct-quantized.w4a16 --target "http://localhost:8000/v1" --data-type emulated --data prompt_tokens=<prompt_tokens>,generated_tokens=<generated_tokens>,images=<num_images>,width=<image_width>,height=<image_height> --max seconds 120 --backend aiohttp_server

text

guidellm --model neuralmagic/Qwen2-VL-72B-Instruct-quantized.w4a16 --target "http://localhost:8000/v1" --data-type emulated --data prompt_tokens=<prompt_tokens>,generated_tokens=<generated_tokens>,images=<num_images>,width=<image_width>,height=<image_height> --max seconds 120 --backend aiohttp_server

text

guidellm --model neuralmagic/Qwen2-VL-72B-Instruct-quantized.w4a16 --target "http://localhost:8000/v1" --data-type emulated --data prompt_tokens=<prompt_tokens>,generated_tokens=<generated_tokens>,images=<num_images>,width=<image_width>,height=<image_height> --max seconds 120 --backend aiohttp_server

text

guidellm --model neuralmagic/Qwen2-VL-72B-Instruct-quantized.w4a16 --target "http://localhost:8000/v1" --data-type emulated --data prompt_tokens=<prompt_tokens>,generated_tokens=<generated_tokens>,images=<num_images>,width=<image_width>,height=<image_height> --max seconds 120 --backend aiohttp_server

text

guidellm --model neuralmagic/Qwen2-VL-72B-Instruct-quantized.w4a16 --target "http://localhost:8000/v1" --data-type emulated --data prompt_tokens=<prompt_tokens>,generated_tokens=<generated_tokens>,images=<num_images>,width=<image_width>,height=<image_height> --max seconds 120 --backend aiohttp_server

text

guidellm --model neuralmagic/Qwen2-VL-72B-Instruct-quantized.w4a16 --target "http://localhost:8000/v1" --data-type emulated --data prompt_tokens=<prompt_tokens>,generated_tokens=<generated_tokens>,images=<num_images>,width=<image_width>,height=<image_height> --max seconds 120 --backend aiohttp_server

text

guidellm --model neuralmagic/Qwen2-VL-72B-Instruct-quantized.w4a16 --target "http://localhost:8000/v1" --data-type emulated --data prompt_tokens=<prompt_tokens>,generated_tokens=<generated_tokens>,images=<num_images>,width=<image_width>,height=<image_height> --max seconds 120 --backend aiohttp_server

text

guidellm --model neuralmagic/Qwen2-VL-72B-Instruct-quantized.w4a16 --target "http://localhost:8000/v1" --data-type emulated --data prompt_tokens=<prompt_tokens>,generated_tokens=<generated_tokens>,images=<num_images>,width=<image_width>,height=<image_height> --max seconds 120 --backend aiohttp_server

text

guidellm --model neuralmagic/Qwen2-VL-72B-Instruct-quantized.w4a16 --target "http://localhost:8000/v1" --data-type emulated --data prompt_tokens=<prompt_tokens>,generated_tokens=<generated_tokens>,images=<num_images>,width=<image_width>,height=<image_height> --max seconds 120 --backend aiohttp_server

text

guidellm --model neuralmagic/Qwen2-VL-72B-Instruct-quantized.w4a16 --target "http://localhost:8000/v1" --data-type emulated --data prompt_tokens=<prompt_tokens>,generated_tokens=<generated_tokens>,images=<num_images>,width=<image_width>,height=<image_height> --max seconds 120 --backend aiohttp_server

text

guidellm --model neuralmagic/Qwen2-VL-72B-Instruct-quantized.w4a16 --target "http://localhost:8000/v1" --data-type emulated --data prompt_tokens=<prompt_tokens>,generated_tokens=<generated_tokens>,images=<num_images>,width=<image_width>,height=<image_height> --max seconds 120 --backend aiohttp_server

text

guidellm --model neuralmagic/Qwen2-VL-72B-Instruct-quantized.w4a16 --target "http://localhost:8000/v1" --data-type emulated --data prompt_tokens=<prompt_tokens>,generated_tokens=<generated_tokens>,images=<num_images>,width=<image_width>,height=<image_height> --max seconds 120 --backend aiohttp_server

text

guidellm --model neuralmagic/Qwen2-VL-72B-Instruct-quantized.w4a16 --target "http://localhost:8000/v1" --data-type emulated --data prompt_tokens=<prompt_tokens>,generated_tokens=<generated_tokens>,images=<num_images>,width=<image_width>,height=<image_height> --max seconds 120 --backend aiohttp_server

text

guidellm --model neuralmagic/Qwen2-VL-72B-Instruct-quantized.w4a16 --target "http://localhost:8000/v1" --data-type emulated --data prompt_tokens=<prompt_tokens>,generated_tokens=<generated_tokens>,images=<num_images>,width=<image_width>,height=<image_height> --max seconds 120 --backend aiohttp_server

text

guidellm --model neuralmagic/Qwen2-VL-72B-Instruct-quantized.w4a16 --target "http://localhost:8000/v1" --data-type emulated --data prompt_tokens=<prompt_tokens>,generated_tokens=<generated_tokens>,images=<num_images>,width=<image_width>,height=<image_height> --max seconds 120 --backend aiohttp_server

text

guidellm --model neuralmagic/Qwen2-VL-72B-Instruct-quantized.w4a16 --target "http://localhost:8000/v1" --data-type emulated --data prompt_tokens=<prompt_tokens>,generated_tokens=<generated_tokens>,images=<num_images>,width=<image_width>,height=<image_height> --max seconds 120 --backend aiohttp_server

text

guidellm --model neuralmagic/Qwen2-VL-72B-Instruct-quantized.w4a16 --target "http://localhost:8000/v1" --data-type emulated --data prompt_tokens=<prompt_tokens>,generated_tokens=<generated_tokens>,images=<num_images>,width=<image_width>,height=<image_height> --max seconds 120 --backend aiohttp_server

text

guidellm --model neuralmagic/Qwen2-VL-72B-Instruct-quantized.w4a16 --target "http://localhost:8000/v1" --data-type emulated --data prompt_tokens=<prompt_tokens>,generated_tokens=<generated_tokens>,images=<num_images>,width=<image_width>,height=<image_height> --max seconds 120 --backend aiohttp_server

Deploy This Model

Production-ready deployment in minutes

Together.ai

Instant API access to this model

Fastest API

Production-ready inference API. Start free, scale to millions.

Try Free API

Replicate

One-click model deployment

Easiest Setup

Run models in the cloud with simple API. No DevOps required.

Deploy Now

Disclosure: We may earn a commission from these partners. This helps keep LLMYourWay free.