기기에 바로 올릴 쪽은 LFM3-Omni-2B입니다

llama serve -hf LiquidAI/LFM3-Omni-2B-GGUF:Q4_K_M --reasoning off --temp 0 --port 8080

llama cli -hf LiquidAI/LFM3-Omni-2B-GGUF:Q4_K_M \
  --image photo.png -p "Describe this image." --temp 0

llama cli -hf LiquidAI/LFM3-Omni-2B-GGUF:Q4_K_M \
  --audio speech.wav -sys "Perform ASR in English." -p "<__media__>" --temp 0

pip install "transformers>=5.20.2" torch torchvision torchcodec accelerate pillow librosa soundfile

import torch
import soundfile as sf

from transformers import AutoModelForMultimodalLM, AutoProcessor

model_id = "LiquidAI/LFM3-Omni-2B"
device = "cuda" if torch.cuda.is_available() else "cpu"
dtype = torch.bfloat16 if device == "cuda" else torch.float32

model = AutoModelForMultimodalLM.from_pretrained(
    model_id, dtype=dtype, device_map=device, trust_remote_code=True
).eval()
processor = AutoProcessor.from_pretrained(model_id, trust_remote_code=True)
codec = processor.audio_tokenizer.to(device=device).eval()

conversation = [
    {"role": "system", "content": "Perform ASR in English."},
    {"role": "user", "content": [{"type": "audio", "audio": "audio.wav"}]},
]

inputs = processor.apply_chat_template(
    conversation,
    add_generation_prompt=True,
    tokenize=True,
    return_dict=True,
    return_tensors="pt",
).to(device)
with torch.no_grad():
    outputs = model.generate(**inputs, max_new_tokens=1024, generation_mode="text")
text = processor.decode(
    outputs.sequences[0, inputs["input_ids"].shape[1]:outputs.sequence_lengths[0]],
    skip_special_tokens=True,
)
print(text)

pip install torch==2.13.0 torchvision pillow transformers==4.52.1 huggingface-hub==0.36.0 \
  tokenizers==0.21.4 addict==2.4.0 einops==0.8.2 easydict==1.13

import torch
from transformers import AutoModel, AutoTokenizer

model_name = "baidu/Unlimited-OCR-2"
tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
model = AutoModel.from_pretrained(model_name, trust_remote_code=True, use_safetensors=True,
                                  torch_dtype=torch.bfloat16).eval().cuda()

# 한 쪽
text = model.infer(tokenizer, image_file="your_doc/page_1.jpg",
                   output_path="output/single", save_results=True)

# 여러 쪽을 한 요청으로(쪽 순서대로)
pages = [f"your_doc/page_{i}.jpg" for i in range(1, 8)]
text, num_tokens = model.infer_multi(tokenizer, image_files=pages,
                                     output_path="output/multi", save_results=True)