Fal-2-500M

Name: Fal-2-500M
Author: SVECTOR-CORPORATION

54.9K

license:mit

SVECTOR-CORPORATION

Code Model

OTHER

Fair

55K downloads

Community-tested

Try on Hugging Face Add to Compare

Edge AI:

Mobile

Laptop

Server

Unknown

Mobile

Laptop

Server

Quick Summary

Fal-2-500M is a compact vision-language model designed for image understanding and captioning tasks.

Code Examples

Generatepythontransformers

import torch
from PIL import Image
from transformers import AutoTokenizer, AutoModelForCausalLM

MID = "SVECTOR-CORPORATION/Fal-2-500M"
IMAGE_TOKEN_INDEX = -200
tok = AutoTokenizer.from_pretrained(MID, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
    MID,
    torch_dtype=torch.float16 if torch.cuda.is_available() else torch.float32,
    device_map="auto",
    trust_remote_code=True,
)
messages = [
    {"role": "user", "content": "<image>\nDescribe me this image."}
]
rendered = tok.apply_chat_template(
    messages, add_generation_prompt=True, tokenize=False
)

pre, post = rendered.split("<image>", 1)
pre_ids  = tok(pre,  return_tensors="pt", add_special_tokens=False).input_ids
post_ids = tok(post, return_tensors="pt", add_special_tokens=False).input_ids

img_tok = torch.tensor([[IMAGE_TOKEN_INDEX]], dtype=pre_ids.dtype)
input_ids = torch.cat([pre_ids, img_tok, post_ids], dim=1).to(model.device)
attention_mask = torch.ones_like(input_ids, device=model.device)

img = Image.open("photo.jpg").convert("RGB")
px = model.get_vision_tower().image_processor(images=img, return_tensors="pt")["pixel_values"]
px = px.to(model.device, dtype=model.dtype)

# Generate
with torch.no_grad():
    out = model.generate(
        inputs=input_ids,
        attention_mask=attention_mask,
        images=px,
        max_new_tokens=128,
    )

print(tok.decode(out[0], skip_special_tokens=True))

Generatepythontransformers

import torch
from PIL import Image
from transformers import AutoTokenizer, AutoModelForCausalLM

MID = "SVECTOR-CORPORATION/Fal-2-500M"
IMAGE_TOKEN_INDEX = -200
tok = AutoTokenizer.from_pretrained(MID, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
    MID,
    torch_dtype=torch.float16 if torch.cuda.is_available() else torch.float32,
    device_map="auto",
    trust_remote_code=True,
)
messages = [
    {"role": "user", "content": "<image>\nDescribe me this image."}
]
rendered = tok.apply_chat_template(
    messages, add_generation_prompt=True, tokenize=False
)

pre, post = rendered.split("<image>", 1)
pre_ids  = tok(pre,  return_tensors="pt", add_special_tokens=False).input_ids
post_ids = tok(post, return_tensors="pt", add_special_tokens=False).input_ids

img_tok = torch.tensor([[IMAGE_TOKEN_INDEX]], dtype=pre_ids.dtype)
input_ids = torch.cat([pre_ids, img_tok, post_ids], dim=1).to(model.device)
attention_mask = torch.ones_like(input_ids, device=model.device)

img = Image.open("photo.jpg").convert("RGB")
px = model.get_vision_tower().image_processor(images=img, return_tensors="pt")["pixel_values"]
px = px.to(model.device, dtype=model.dtype)

# Generate
with torch.no_grad():
    out = model.generate(
        inputs=input_ids,
        attention_mask=attention_mask,
        images=px,
        max_new_tokens=128,
    )

print(tok.decode(out[0], skip_special_tokens=True))

Generatepythontransformers

import torch
from PIL import Image
from transformers import AutoTokenizer, AutoModelForCausalLM

MID = "SVECTOR-CORPORATION/Fal-2-500M"
IMAGE_TOKEN_INDEX = -200
tok = AutoTokenizer.from_pretrained(MID, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
    MID,
    torch_dtype=torch.float16 if torch.cuda.is_available() else torch.float32,
    device_map="auto",
    trust_remote_code=True,
)
messages = [
    {"role": "user", "content": "<image>\nDescribe me this image."}
]
rendered = tok.apply_chat_template(
    messages, add_generation_prompt=True, tokenize=False
)

pre, post = rendered.split("<image>", 1)
pre_ids  = tok(pre,  return_tensors="pt", add_special_tokens=False).input_ids
post_ids = tok(post, return_tensors="pt", add_special_tokens=False).input_ids

img_tok = torch.tensor([[IMAGE_TOKEN_INDEX]], dtype=pre_ids.dtype)
input_ids = torch.cat([pre_ids, img_tok, post_ids], dim=1).to(model.device)
attention_mask = torch.ones_like(input_ids, device=model.device)

img = Image.open("photo.jpg").convert("RGB")
px = model.get_vision_tower().image_processor(images=img, return_tensors="pt")["pixel_values"]
px = px.to(model.device, dtype=model.dtype)

# Generate
with torch.no_grad():
    out = model.generate(
        inputs=input_ids,
        attention_mask=attention_mask,
        images=px,
        max_new_tokens=128,
    )

print(tok.decode(out[0], skip_special_tokens=True))

Generatepythontransformers

import torch
from PIL import Image
from transformers import AutoTokenizer, AutoModelForCausalLM

MID = "SVECTOR-CORPORATION/Fal-2-500M"
IMAGE_TOKEN_INDEX = -200
tok = AutoTokenizer.from_pretrained(MID, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
    MID,
    torch_dtype=torch.float16 if torch.cuda.is_available() else torch.float32,
    device_map="auto",
    trust_remote_code=True,
)
messages = [
    {"role": "user", "content": "<image>\nDescribe me this image."}
]
rendered = tok.apply_chat_template(
    messages, add_generation_prompt=True, tokenize=False
)

pre, post = rendered.split("<image>", 1)
pre_ids  = tok(pre,  return_tensors="pt", add_special_tokens=False).input_ids
post_ids = tok(post, return_tensors="pt", add_special_tokens=False).input_ids

img_tok = torch.tensor([[IMAGE_TOKEN_INDEX]], dtype=pre_ids.dtype)
input_ids = torch.cat([pre_ids, img_tok, post_ids], dim=1).to(model.device)
attention_mask = torch.ones_like(input_ids, device=model.device)

img = Image.open("photo.jpg").convert("RGB")
px = model.get_vision_tower().image_processor(images=img, return_tensors="pt")["pixel_values"]
px = px.to(model.device, dtype=model.dtype)

# Generate
with torch.no_grad():
    out = model.generate(
        inputs=input_ids,
        attention_mask=attention_mask,
        images=px,
        max_new_tokens=128,
    )

print(tok.decode(out[0], skip_special_tokens=True))

Generatepythontransformers

import torch
from PIL import Image
from transformers import AutoTokenizer, AutoModelForCausalLM

MID = "SVECTOR-CORPORATION/Fal-2-500M"
IMAGE_TOKEN_INDEX = -200
tok = AutoTokenizer.from_pretrained(MID, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
    MID,
    torch_dtype=torch.float16 if torch.cuda.is_available() else torch.float32,
    device_map="auto",
    trust_remote_code=True,
)
messages = [
    {"role": "user", "content": "<image>\nDescribe me this image."}
]
rendered = tok.apply_chat_template(
    messages, add_generation_prompt=True, tokenize=False
)

pre, post = rendered.split("<image>", 1)
pre_ids  = tok(pre,  return_tensors="pt", add_special_tokens=False).input_ids
post_ids = tok(post, return_tensors="pt", add_special_tokens=False).input_ids

img_tok = torch.tensor([[IMAGE_TOKEN_INDEX]], dtype=pre_ids.dtype)
input_ids = torch.cat([pre_ids, img_tok, post_ids], dim=1).to(model.device)
attention_mask = torch.ones_like(input_ids, device=model.device)

img = Image.open("photo.jpg").convert("RGB")
px = model.get_vision_tower().image_processor(images=img, return_tensors="pt")["pixel_values"]
px = px.to(model.device, dtype=model.dtype)

# Generate
with torch.no_grad():
    out = model.generate(
        inputs=input_ids,
        attention_mask=attention_mask,
        images=px,
        max_new_tokens=128,
    )

print(tok.decode(out[0], skip_special_tokens=True))

Generatepythontransformers

import torch
from PIL import Image
from transformers import AutoTokenizer, AutoModelForCausalLM

MID = "SVECTOR-CORPORATION/Fal-2-500M"
IMAGE_TOKEN_INDEX = -200
tok = AutoTokenizer.from_pretrained(MID, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
    MID,
    torch_dtype=torch.float16 if torch.cuda.is_available() else torch.float32,
    device_map="auto",
    trust_remote_code=True,
)
messages = [
    {"role": "user", "content": "<image>\nDescribe me this image."}
]
rendered = tok.apply_chat_template(
    messages, add_generation_prompt=True, tokenize=False
)

pre, post = rendered.split("<image>", 1)
pre_ids  = tok(pre,  return_tensors="pt", add_special_tokens=False).input_ids
post_ids = tok(post, return_tensors="pt", add_special_tokens=False).input_ids

img_tok = torch.tensor([[IMAGE_TOKEN_INDEX]], dtype=pre_ids.dtype)
input_ids = torch.cat([pre_ids, img_tok, post_ids], dim=1).to(model.device)
attention_mask = torch.ones_like(input_ids, device=model.device)

img = Image.open("photo.jpg").convert("RGB")
px = model.get_vision_tower().image_processor(images=img, return_tensors="pt")["pixel_values"]
px = px.to(model.device, dtype=model.dtype)

# Generate
with torch.no_grad():
    out = model.generate(
        inputs=input_ids,
        attention_mask=attention_mask,
        images=px,
        max_new_tokens=128,
    )

print(tok.decode(out[0], skip_special_tokens=True))

Generatepythontransformers

import torch
from PIL import Image
from transformers import AutoTokenizer, AutoModelForCausalLM

MID = "SVECTOR-CORPORATION/Fal-2-500M"
IMAGE_TOKEN_INDEX = -200
tok = AutoTokenizer.from_pretrained(MID, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
    MID,
    torch_dtype=torch.float16 if torch.cuda.is_available() else torch.float32,
    device_map="auto",
    trust_remote_code=True,
)
messages = [
    {"role": "user", "content": "<image>\nDescribe me this image."}
]
rendered = tok.apply_chat_template(
    messages, add_generation_prompt=True, tokenize=False
)

pre, post = rendered.split("<image>", 1)
pre_ids  = tok(pre,  return_tensors="pt", add_special_tokens=False).input_ids
post_ids = tok(post, return_tensors="pt", add_special_tokens=False).input_ids

img_tok = torch.tensor([[IMAGE_TOKEN_INDEX]], dtype=pre_ids.dtype)
input_ids = torch.cat([pre_ids, img_tok, post_ids], dim=1).to(model.device)
attention_mask = torch.ones_like(input_ids, device=model.device)

img = Image.open("photo.jpg").convert("RGB")
px = model.get_vision_tower().image_processor(images=img, return_tensors="pt")["pixel_values"]
px = px.to(model.device, dtype=model.dtype)

# Generate
with torch.no_grad():
    out = model.generate(
        inputs=input_ids,
        attention_mask=attention_mask,
        images=px,
        max_new_tokens=128,
    )

print(tok.decode(out[0], skip_special_tokens=True))

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.