Image-to-Text
PEFT
Safetensors
Oriya
odia
ocr
vision-language
qwen2-vl
lora
optical-character-recognition
Instructions to use shantipriya/odia-ocr-qwen-finetuned_v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use shantipriya/odia-ocr-qwen-finetuned_v2 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, "shantipriya/odia-ocr-qwen-finetuned_v2") - Notebooks
- Google Colab
- Kaggle

- Xet hash:
- 7f7cb22ab4dc10df0b765adfc021c74d496d140c05def169ecd0129788beba41
- Size of remote file:
- 612 kB
- SHA256:
- 0c88cd89885c637ccd07af1457698ffd04b63eeadfaff5d0fd9a419bd8478f71
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.