Pinned Loading

1. xjdr-alt/entropix xjdr-alt/entropix Public

   Entropy Based Sampling and Parallel CoT Decoding

   Python 3.4k 324

2. minp_paper minp_paper Public

   Code Implementation, Evaluations, Documentation, Links and Resources for Min P paper

   Jupyter Notebook 44 3

3. Moneybench/moneybench Moneybench/moneybench Public

   (WIP) A benchmark to see how well AI agents autonomously make money.

   Python 14

4. RAGEN RAGEN Public

   Forked from mll-lab-nu/RAGEN

   RAGEN is the first open-source reproduction of DeepSeek-R1 on AGENT training.

   Python

5. self_explaining_features self_explaining_features Public

   Minh's implementation of Self-Explaining Features

   Jupyter Notebook

6. natural_language_rl natural_language_rl Public

   Some attempts at applying Mech Interp for RL.

   Jupyter Notebook