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
      • Hardware
      • Learn
      • Discord
      • Forum
      • GitHub
    • Solutions
      • Team & Enterprise
      • Hugging Face PRO
      • Enterprise Support
      • Inference Providers
      • Inference Endpoints
      • Storage Buckets

  • Log In
  • Sign Up

pratimassaravanan
/
clinical-qwen3-4b-sft-lora

Text Generation
PEFT
Safetensors
clinical-trial
reinforcement-learning
REINFORCE
lora
qwen3
openenv
hackathon
theme-2
conversational
Model card Files Files and versions
xet
Community

Instructions to use pratimassaravanan/clinical-qwen3-4b-sft-lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

  • Libraries
  • PEFT

    How to use pratimassaravanan/clinical-qwen3-4b-sft-lora with PEFT:

    from peft import PeftModel
    from transformers import AutoModelForCausalLM
    
    base_model = AutoModelForCausalLM.from_pretrained("unsloth/Qwen3-4B-unsloth-bnb-4bit")
    model = PeftModel.from_pretrained(base_model, "pratimassaravanan/clinical-qwen3-4b-sft-lora")
  • Notebooks
  • Google Colab
  • Kaggle
clinical-qwen3-4b-sft-lora
287 MB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 8 commits
pratimassaravanan's picture
pratimassaravanan
RL v3 adapter (fresh LoRA, REINFORCE, 30 episodes, heuristic override)
bd8699d verified 5 months ago
  • rl_v3_adapter
    RL v3 adapter (fresh LoRA, REINFORCE, 30 episodes, heuristic override) 5 months ago
  • training_evidence
    Debug trial results — verify enrollment works 5 months ago
  • .gitattributes
    1.57 kB
    Upload exploit-aware SFT LoRA adapter (Qwen3-4B, r=16, 3 epochs on L40S) 5 months ago
  • README.md
    4.96 kB
    Update README with real training evidence 5 months ago
  • adapter_config.json
    1.25 kB
    v2: 10K+ diverse traces, heuristic ID eval 5 months ago
  • adapter_model.safetensors
    132 MB
    xet
    v2: 10K+ diverse traces, heuristic ID eval 5 months ago
  • chat_template.jinja
    4.67 kB
    Upload exploit-aware SFT LoRA adapter (Qwen3-4B, r=16, 3 epochs on L40S) 5 months ago
  • eval_results.json
    651 Bytes
    Upload eval_results.json with huggingface_hub 5 months ago
  • tokenizer.json
    11.4 MB
    xet
    Upload exploit-aware SFT LoRA adapter (Qwen3-4B, r=16, 3 epochs on L40S) 5 months ago
  • tokenizer_config.json
    5.28 kB
    Upload exploit-aware SFT LoRA adapter (Qwen3-4B, r=16, 3 epochs on L40S) 5 months ago