Stars
Democratizing Reinforcement Learning for LLMs
A framework for few-shot evaluation of language models.
Script to monitor PLI partitions of the Princeton clusters
Rigourous evaluation of LLM-synthesized code - NeurIPS 2023 & COLM 2024
SWE-agent takes a GitHub issue and tries to automatically fix it, using your LM of choice. It can also be employed for offensive cybersecurity or competitive coding challenges. [NeurIPS 2024]
A collection of beautifully designed AI interface components that you can copy and paste into your apps. Accessible. Customizable. Open Source.
A simple and elegant Jekyll theme for an academic personal homepage
Ready-to-use OCR with 80+ supported languages and all popular writing scripts including Latin, Chinese, Arabic, Devanagari, Cyrillic and etc.
Triton implementation of FlashAttention2 that adds Custom Masks.
Trainable, memory-efficient, and GPU-friendly PyTorch reproduction of AlphaFold 2
Some preliminary explorations of Mamba's context scaling.
A simple and efficient Mamba implementation in pure PyTorch and MLX.
An original implementation of "Noisy Channel Language Model Prompting for Few-Shot Text Classification"