Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Buckets new
  • Docs
  • Enterprise
  • Pricing

  • Log In
  • Sign Up

thejaminator
/
grpo-feature-vector-step-1

PEFT
Safetensors
English
verl
grpo
math
reasoning
rl
lora
Model card Files Files and versions
xet
Community

Instructions to use thejaminator/grpo-feature-vector-step-1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

  • Libraries
  • PEFT

    How to use thejaminator/grpo-feature-vector-step-1 with PEFT:

    from peft import PeftModel
    from transformers import AutoModelForCausalLM
    
    base_model = AutoModelForCausalLM.from_pretrained("thejaminator/gemma-introspection-20250821-merged")
    model = PeftModel.from_pretrained(base_model, "thejaminator/grpo-feature-vector-step-1")
  • Notebooks
  • Google Colab
  • Kaggle
grpo-feature-vector-step-1
864 MB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 3 commits
thejaminator's picture
thejaminator
verl GRPO trained model at step 1
ade0533 verified 9 months ago
  • .gitattributes
    1.52 kB
    initial commit 9 months ago
  • README.md
    735 Bytes
    verl GRPO trained model at step 1 9 months ago
  • adapter_config.json
    1.13 kB
    verl GRPO trained model at step 1 9 months ago
  • adapter_model.safetensors
    864 MB
    xet
    verl GRPO trained model at step 1 9 months ago