Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Buckets new
  • Docs
  • Enterprise
  • Pricing
    • Website
      • Tasks
      • HuggingChat
      • Collections
      • Languages
      • Organizations
    • Community
      • Blog
      • Posts
      • Daily Papers
      • Learn
      • Discord
      • Forum
      • GitHub
    • Solutions
      • Team & Enterprise
      • Hugging Face PRO
      • Enterprise Support
      • Inference Providers
      • Inference Endpoints
      • Storage Buckets

  • Log In
  • Sign Up

Pritosh
/
odia-ocr-rft-v1

Image-Text-to-Text
PEFT
Safetensors
Oriya
ocr
odia
qwen3
qlora
rft
rejection-sampling
conversational
Model card Files Files and versions
xet
Community

Instructions to use Pritosh/odia-ocr-rft-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

  • Libraries
  • PEFT

    How to use Pritosh/odia-ocr-rft-v1 with PEFT:

    from peft import PeftModel
    from transformers import AutoModelForCausalLM
    
    base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3.5-4B")
    model = PeftModel.from_pretrained(base_model, "Pritosh/odia-ocr-rft-v1")
  • Notebooks
  • Google Colab
  • Kaggle
odia-ocr-rft-v1
62.5 MB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 2 commits
Pritosh's picture
Pritosh
RFT-v1 β€” rejection sampling fine-tuned from V5 (154 filtered outputs, CER<0.60)
f878eff verified about 2 months ago
  • .gitattributes
    1.57 kB
    RFT-v1 β€” rejection sampling fine-tuned from V5 (154 filtered outputs, CER<0.60) about 2 months ago
  • README.md
    1.67 kB
    RFT-v1 β€” rejection sampling fine-tuned from V5 (154 filtered outputs, CER<0.60) about 2 months ago
  • adapter_config.json
    1.05 kB
    RFT-v1 β€” rejection sampling fine-tuned from V5 (154 filtered outputs, CER<0.60) about 2 months ago
  • adapter_model.safetensors
    42.5 MB
    xet
    RFT-v1 β€” rejection sampling fine-tuned from V5 (154 filtered outputs, CER<0.60) about 2 months ago
  • chat_template.jinja
    7.76 kB
    RFT-v1 β€” rejection sampling fine-tuned from V5 (154 filtered outputs, CER<0.60) about 2 months ago
  • tokenizer.json
    20 MB
    xet
    RFT-v1 β€” rejection sampling fine-tuned from V5 (154 filtered outputs, CER<0.60) about 2 months ago
  • tokenizer_config.json
    1.1 kB
    RFT-v1 β€” rejection sampling fine-tuned from V5 (154 filtered outputs, CER<0.60) about 2 months ago