Pinned Loading

1. Code for paper "The Markovian Thinker: Architecture-Agnostic Linear Scaling of Reasoning"

   Python 347 27

2. Code for the paper "VinePPO: Unlocking RL Potential For LLM Reasoning Through Refined Credit Assignment"

   Python 192 23

3. Code for the paper "The Impact of Positional Encoding on Length Generalization in Transformers", NeurIPS 2023

   Python 139 7

4. Single File, Single GPU, From Scratch, Efficient, Full Parameter Tuning library for "RL for LLMs"

   Jupyter Notebook 630 58

5. Forked from tensorflow/addons

   Useful extra functionality for TensorFlow 2.0 maintained by SIG-addons

   Python

6. The official Genbench Collaborative Benchmarking Task repository 2023 (Archived)

   Python 14 17