Popular repositories Loading

1. synthetic-questions-generation synthetic-questions-generation Public

   Python 77 9

2. grpo-llm-evaluator grpo-llm-evaluator Public

   Fine-tunes a student LLM using teacher feedback for improved reasoning and answer quality. Implements GRPO with teacher-provided evaluations.

   Python 47 4

3. ReasonFlow ReasonFlow Public

   ReasonFlow is a novel framework designed to implement o1-like reasoning capabilities in large language models.

   Python 17 5

4. mcts-pytorch mcts-pytorch Public

   A flexible Monte Carlo Tree Search framework with PyTorch for decision-making in language models.

   Jupyter Notebook 10 1

5. blurred-thoughts-SFT blurred-thoughts-SFT Public

   Blurred-Thoughts Supervised-Finetuning (BT-SFT) is a new approach to fine-tuning language models, focusing on enhancing response diversity and creativity.

   Python 6 1

6. jepa-llm jepa-llm Public

   Fine-tuning causal language models with an additional JEPA-style representation regularisation loss as well as a plain Hugging Face trainer

   Python 3