Sanskrit Ocr LoRA

--- base_model: deepseek-ai/DeepSeek-OCR library_name: peft pipeline_tag: image-to-text tags: - lora - ocr - sanskrit - devanagari language: - sa --- # Sanskrit OCR LoRA LoRA adapter for [DeepSeek-OCR](https://huggingface.co/deepseek-ai/DeepSeek-OCR), fine-tuned on Sanskrit/Devanagari text recognition. ## Training - **Dataset:** [snskrt/Sanskrit_OCR_Parallel_Corpus](https://huggingface.co/datasets/snskrt/Sanskrit_OCR_Parallel_Corpus) (6,265 image-text pairs) - **Epochs:** 2 - **Final train loss:** 4.70 - **LoRA rank:** 16, alpha: 16 - **Target modules:** q/k/v/o/gate/up/down projections - **Precision:** bf16 - **Hardware:** NVIDIA A100 80GB (~2.5 hours) ## Usage ```bash pip install torch transformers==4.45.0 peft accelerate easydict addict matplotlib einops ``` ```python from transformers import AutoModel, AutoProcessor from peft import PeftModel base_model_path = "deepseek_ocr" # local path to DeepSeek-OCR lora_path = "arpitingle/sanskrit-ocr-lora" model = AutoModel.from_pretrained(base_model_path, trust_remote_code=True, torch_dtype="auto", device_map="auto") model = PeftModel.from_pretrained(model, lora_path) model = model.merge_and_unload() model.eval() processor = AutoProcessor.from_pretrained(base_model_path, trust_remote_code=True) result = model.infer(processor, prompt="<image>\nFree OCR. ", image_file="path/to/image.jpg", output_path="./output", base_size=1024, image_size=640, crop_mode=True, save_results=False, test_compress=False, eval_mode=True) print(result) ``` **Note:** `crop_mode=True` is required for good results. ## Files - `adapter_model.safetensors` — LoRA weights - `adapter_config.json` — LoRA config - `inference.py` — inference script - `train.py` — training script ## Known Issues - Base model requires `transformers==4.45.0` (newer versions break custom model code) - `crop_mode=False` produces poor output; always use `crop_mode=True`

Source context: 11 downloads · 4 likes · Pipeline image-to-text · Library peft · Repo arpitingle/sanskrit-ocr-lora