Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Buckets
  • 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

ruby2022
/
NYCU-IAlI-DL2026-LLM3-GRPO

Reinforcement Learning
PEFT
Safetensors
Chinese
lora
grpo
traditional-chinese
multiple-choice
qwen3
Model card Files Files and versions
xet
Community

Instructions to use ruby2022/NYCU-IAlI-DL2026-LLM3-GRPO with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

  • Libraries
  • PEFT

    How to use ruby2022/NYCU-IAlI-DL2026-LLM3-GRPO with PEFT:

    from peft import PeftModel
    from transformers import AutoModelForCausalLM
    
    base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-14B")
    model = PeftModel.from_pretrained(base_model, "ruby2022/NYCU-IAlI-DL2026-LLM3-GRPO")
  • Notebooks
  • Google Colab
  • Kaggle
NYCU-IAlI-DL2026-LLM3-GRPO / data
5.71 MB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 2 commits
ruby2022's picture
ruby2022
Add training data: kaggle_test_set_792.csv
7e91a0a verified 5 months ago
  • kaggle_test_set_792.csv
    129 kB
    Add training data: kaggle_test_set_792.csv 5 months ago
  • train-reasoning-v2.csv
    5.58 MB
    Add training data: train-reasoning-v2.csv 5 months ago