You can use the transformers library for inference. This method is slower than vLLM but useful for local development or environments without vLLM support.
Note: When using the DotsMOCRParser class, you can pass use_hf=True to switch to Transformers-based inference.
import torch
from transformers import AutoModelForCausalLM, AutoProcessor, AutoTokenizer
from qwen_vl_utils import process_vision_info
from dots_mocr.utils import dict_promptmode_to_prompt
model_path = "./weights/DotsMOCR"
model = AutoModelForCausalLM.from_pretrained(
model_path,
attn_implementation="flash_attention_2",
torch_dtype=torch.bfloat16,
device_map="auto",
trust_remote_code=True
)
processor = AutoProcessor.from_pretrained(model_path, trust_remote_code=True)
image_path = "demo/demo_image1.jpg"
prompt = """Please output the layout information from the PDF image..."""
messages = [
{
"role": "user",
"content": [
{
"type": "image",
"image": image_path
},
{"type": "text", "text": prompt}
]
}
]
# Preparation for inference
text = processor.apply_chat_template(
messages,
tokenize=False,
add_generation_prompt=True
)
image_inputs, video_inputs = process_vision_info(messages)
inputs = processor(
text=[text],
images=image_inputs,
videos=video_inputs,
padding=True,
return_tensors="pt",
)
inputs = inputs.to("cuda")
# Inference
generated_ids = model.generate(**inputs, max_new_tokens=24000)
generated_ids_trimmed = [
out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)
]
output_text = processor.batch_decode(
generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False
)
print(output_text)
