🧾 Qwen2.5-VL Invoice OCR - LoRA Adapter
Fine-tuned LoRA adapter for Qwen2.5-VL-3B-Instruct specialized in extracting structured JSON data from invoice and receipt images.
Performance
- Training Loss: 35.78 → 0.024 (99.3% improvement)
- Eval Loss: 0.010
- Steps: 150+ with engineered prompt
- Dataset: 2,043 samples
Usage
from transformers import AutoModelForVision2Seq, AutoProcessor
from peft import PeftModel
base_model = AutoModelForVision2Seq.from_pretrained("Qwen/Qwen2.5-VL-3B-Instruct")
model = PeftModel.from_pretrained(base_model, "kahua-ml/invoice1")
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support
Model tree for kahua-ml/invoice1
Base model
Qwen/Qwen2.5-VL-3B-Instruct