inference_example.py

# Standalone inference example using the Hugging Face adapter
import torch
from PIL import Image
from transformers import AutoProcessor, Qwen2_5_VLForConditionalGeneration, BitsAndBytesConfig
from peft import PeftModel
from qwen_vl_utils import process_vision_info
import sys

def main(image_path: str, adapter_id: str = "."):
    model_id = "Qwen/Qwen2.5-VL-3B-Instruct"
    print(f"Loading processor for {adapter_id}...")
    processor = AutoProcessor.from_pretrained(adapter_id)

    print("Loading base model in 4-bit...")
    bnb_config = BitsAndBytesConfig(
        load_in_4bit=True,
        bnb_4bit_quant_type="nf4",
        bnb_4bit_compute_dtype=torch.float16,
        bnb_4bit_use_double_quant=True,
    )
    base_model = Qwen2_5_VLForConditionalGeneration.from_pretrained(
        model_id,
        quantization_config=bnb_config,
        torch_dtype=torch.float16,
        device_map="auto"
    )

    print("Loading PEFT LoRA adapter...")
    model = PeftModel.from_pretrained(base_model, adapter_id)
    model.eval()

    image = Image.open(image_path).convert("RGB")
    messages = [
        {
            "role": "user",
            "content": [
                {"type": "image", "image": image},
                {"type": "text", "text": "Extract the plotted quantitative data into a clean Markdown table with column headers."}
            ]
        }
    ]

    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
    image_inputs, _ = process_vision_info(messages)
    inputs = processor(text=[text], images=image_inputs, padding=True, return_tensors="pt").to("cuda")

    with torch.inference_mode():
        generated_ids = model.generate(**inputs, max_new_tokens=1024, temperature=0.0)
        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
        )[0]

    print("\n=== Extracted Markdown Table ===\n")
    print(output_text)

if __name__ == "__main__":
    img = sys.argv[1] if len(sys.argv) > 1 else "figure.png"
    main(img)