Stars
Your self-hosted, globally interconnected microblogging community
KernelBench: Can LLMs Write GPU Kernels? - Benchmark with Torch -> CUDA (+ more DSLs)
State-of-the-art audio codec with 90x compression factor. Supports 44.1kHz, 24kHz, and 16kHz mono/stereo audio.
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]
RWKV (pronounced RwaKuv) is an RNN with great LLM performance, which can also be directly trained like a GPT transformer (parallelizable). We are at RWKV-7 "Goose". So it's combining the best of RN…
A web app for ranking computer science departments according to their research output in selective venues, and for finding active faculty across a wide range of areas.
A framework for few-shot evaluation of language models.
Code to enable layer-level steering in LLMs using sparse auto encoders
Source code for the X Recommendation Algorithm
Ingest, parse, and optimize any data format ➡️ from documents to multimedia ➡️ for enhanced compatibility with GenAI frameworks
AIHawk aims to easy job hunt process by automating the job application process. Utilizing artificial intelligence, it enables users to apply for multiple jobs in a tailored way.
Retrieve author and publication information from Google Scholar in a friendly, Pythonic way without having to worry about CAPTCHAs!
The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery 🧑🔬
Reverse Engineering the Abstraction and Reasoning Corpus
MiniHack the Planet: A Sandbox for Open-Ended Reinforcement Learning Research
🔍 AI search engine - self-host with local or cloud LLMs
Solve puzzles. Improve your pytorch.
Multiversal tree writing interface for human-AI collaboration
a highly efficient compression algorithm for the n1 implant (neuralink's compression challenge)