Pinned Loading

1. huggingface/peft huggingface/peft Public

   🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

   Python 21.6k 2.5k

2. deepseek-ai/DeepSpec deepseek-ai/DeepSpec Public

   DeepSpec: a full-stack codebase for training and evaluating speculative decoding algorithms

   Python 7k 659

3. can-i-finetune-this can-i-finetune-this Public

   Estimate whether a Hugging Face model fits and fine-tunes on your local GPU.

   Python 792 107

4. mini-verl mini-verl Public

   Run a documented subset of verl-style OPD on one consumer GPU—typed config, Parquet prompts, and PEFT scale-out artifacts.

   Python 191 50

5. pairjudge pairjudge Public

   Pairwise LLM judges (A/B/tie): budget-aware multi-turn packing, position-bias correction, pseudo-label distillation. Generalized from the 4th-place (gold) solution to Kaggle LMSYS Chatbot Arena.

   Python 170 12

6. tracedistill tracedistill Public

   Distill teacher chains-of-thought into a LoRA adapter via a strict boxed-answer format contract + two-phase Train→Nudge (silver-medal NVIDIA Nemotron reasoning recipe, as a tested library).

   Python 85 17