Image-to-Text
PEFT
Safetensors
Portuguese
English
vision-language
table-extraction
scientific-figures
markdown-table
qwen2.5-vl
lora
icdar-metric-loss
Instructions to use lucasoc/sci-image-models with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use lucasoc/sci-image-models with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-VL-3B-Instruct") model = PeftModel.from_pretrained(base_model, "lucasoc/sci-image-models") - Notebooks
- Google Colab
- Kaggle
| """ | |
| Data preprocessing and conversation template building. | |
| """ | |
| from typing import Any, Dict, List, Optional | |
| from PIL import Image | |
| def format_qwen_vl_conversation( | |
| image: Image.Image, | |
| target_table: Optional[str] = None, | |
| system_prompt: str = "You are an expert scientific figure analyzer. Extract the plotted quantitative data into a clean Markdown table." | |
| ) -> List[Dict[str, Any]]: | |
| """Formats an image and optional target into Qwen2.5-VL chat template format.""" | |
| messages = [ | |
| { | |
| "role": "system", | |
| "content": system_prompt | |
| }, | |
| { | |
| "role": "user", | |
| "content": [ | |
| {"type": "image", "image": image}, | |
| {"type": "text", "text": "Extract all numerical data points from this scientific figure panel into a Markdown table with clear column headers."} | |
| ] | |
| } | |
| ] | |
| if target_table is not None: | |
| messages.append({ | |
| "role": "assistant", | |
| "content": target_table.strip() | |
| }) | |
| return messages | |