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

DUAL-GPO
/
phi-2-ipo-chatml

PEFT
TensorBoard
Safetensors
phi
alignment-handbook
Generated from Trainer
trl
dpo
custom_code
Model card Files Files and versions
xet
Metrics Training metrics Community

Instructions to use DUAL-GPO/phi-2-ipo-chatml with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

  • Libraries
  • PEFT

    How to use DUAL-GPO/phi-2-ipo-chatml with PEFT:

    from peft import PeftModel
    from transformers import AutoModelForCausalLM
    
    base_model = AutoModelForCausalLM.from_pretrained("DUAL-GPO/phi-2-sft-lora-ultrachat-merged")
    model = PeftModel.from_pretrained(base_model, "DUAL-GPO/phi-2-ipo-chatml")
  • Notebooks
  • Google Colab
  • Kaggle
phi-2-ipo-chatml / runs
127 kB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 19 commits
lole25's picture
lole25
Model save
21f5880 verified about 2 years ago
  • May19_15-00-24_gpu4-119-5
    Model save about 2 years ago