LFM2.5-VL-450M-Extract

pip install "transformers>=5.1.0" pillow torch accelerate

from transformers import AutoModelForImageTextToText, AutoProcessor
from transformers.image_utils import load_image

model_id = "LiquidAI/LFM2.5-VL-450M-Extract"
model = AutoModelForImageTextToText.from_pretrained(
    model_id,
    device_map="auto",
    dtype="bfloat16",
    trust_remote_code=True,
)
processor = AutoProcessor.from_pretrained(model_id, trust_remote_code=True)

image = load_image("https://huggingface.co/LiquidAI/LFM2.5-VL-450M-Extract/resolve/main/sample_image.png")
fields_yaml = """wood_color: The overall coloration of the wood surface
wood_texture: The tactile quality of the wood surface
wood_pattern: The pattern types visible on the wood surface"""

system_prompt = f"""Extract the following from the image:

{fields_yaml}

Respond with only a JSON object. Do not include any text outside the JSON."""

conversation = [
    {"role": "system", "content": system_prompt},
    {"role": "user", "content": [{"type": "image", "image": image}]},
]

inputs = processor.apply_chat_template(
    conversation,
    add_generation_prompt=True,
    return_tensors="pt",
    return_dict=True,
    tokenize=True,
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=512, do_sample=False)
response = processor.batch_decode(
    outputs[:, inputs["input_ids"].shape[1]:],
    skip_special_tokens=True,
)[0]
print(response)