LFM2.5-VL-3B Specialist

Transformers · unknown

publisher-documented, not executed source

import torch
from transformers import AutoModelForImageTextToText, AutoProcessor

model_id = "LiquidAI/LFM2.5-VL-3B"

model = AutoModelForImageTextToText.from_pretrained(model_id, dtype=torch.bfloat16)
processor = AutoProcessor.from_pretrained(model_id)

messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://placecats.com/300/200"},
            {"type": "text", "text": "Describe this image."},
        ],
    }
]

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

with torch.inference_mode():
    output_ids = model.generate(
        **inputs,
        do_sample=True,
        temperature=0.2,
        top_k=50,
        repetition_penalty=1.0,
        max_new_tokens=256,
    )

generated_ids = output_ids[:, inputs["input_ids"].shape[1] :]
print(processor.batch_decode(generated_ids, skip_special_tokens=True)[0])

Prerequisites: See source setup/dependencies; these snippets were inspected, not executed.

• Use multimodal processor and image-text loader; image token count and encoder workspace affect fit.
• Grounding/document extraction prompts are task-specific.

MLX-VLM · AppleSilicon unifiedmemory

publisher/backend-documented, not executed source

python -m mlx_vlm.generate \
  --model LiquidAI/LFM2.5-VL-3B \
  --draft-model LiquidAI/LFM2.5-VL-3B-DSpark \
  --draft-block-size 8 \
  --image /path/to/image.jpg \
  --prompt "Describe this image." \
  --max-tokens 256 \
  --temperature 0

Prerequisites: See linked source for backend installation/version requirements.

• DSpark is a separate draft checkpoint; do not count it as another chat model.
• Draft block 8 and additional memory are source configuration; no guaranteed speed multiplier.