jaqja/HunYuanOCR-SFT

from transformers import AutoProcessor
from transformers import HunYuanVLForConditionalGeneration
from PIL import Image
import torch

model_name_or_path = "jaqja/HunYuanOCR-SFT"
PROMPT = "Extract all information of the document image and represent it in markdown format. Ensure the parsing follows the logical reading order. Do not describe or extract any figures, signatures, or seals."
processor = AutoProcessor.from_pretrained(model_name_or_path, use_fast=False)
img_path = "example.png"
image_inputs = Image.open(img_path)
messages1 = [
    {
        "role": "user",
        "content": [
            {"type": "image", "image": img_path},
            {"type": "text", "text": PROMPT},
        ],
    }
]
messages = [messages1]
texts = [
    processor.apply_chat_template(msg, tokenize=False, add_generation_prompt=True)
    for msg in messages
]
inputs = processor(
    text=texts,
    images=image_inputs,
    padding=True,
    return_tensors="pt",
)
model = HunYuanVLForConditionalGeneration.from_pretrained(
    model_name_or_path,
    attn_implementation="eager",
    dtype=torch.bfloat16,
    device_map="auto"
)
with torch.no_grad():
    device = next(model.parameters()).device
    inputs = inputs.to(device)
    generated_ids = model.generate(**inputs, max_new_tokens=4096, do_sample=False)
if "input_ids" in inputs:
    input_ids = inputs.input_ids
else:
    print("inputs: # fallback", inputs)
    input_ids = inputs.inputs
generated_ids_trimmed = [
    out_ids[len(in_ids):] for in_ids, out_ids in zip(input_ids, generated_ids)
]
output_texts = processor.batch_decode(
    generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False
)
print(output_texts[0])

@software{vonwerra2020trl,
  title   = {{TRL: Transformers Reinforcement Learning}},
  author  = {von Werra, Leandro and Belkada, Younes and Tunstall, Lewis and Beeching, Edward and Thrush, Tristan and Lambert, Nathan and Huang, Shengyi and Rasul, Kashif and Gallouédec, Quentin},
  license = {Apache-2.0},
  url     = {https://github.com/huggingface/trl},
  year    = {2020}
}
@software{tencenthunyuan,
  title   = {{HunyuanOCR}},
  author  = {ManaEstras manayang and memorywxy xingyuwan},
  license = {TENCENT HUNYUAN COMMUNITY LICENSE AGREEMENT},
  url     = {https://github.com/Tencent-Hunyuan/HunyuanOCR},
  year    = {2025}
}