pacman100

open-interpreter

A natural language interface for computers

grok-1

Grok open release

gym

A toolkit for developing and comparing reinforcement learning algorithms.

Open-Sora

Open-Sora: Democratizing Efficient Video Production for All

devika

Devika is an Agentic AI Software Engineer that can understand high-level human instructions, break them down into steps, research relevant information, and write code to achieve the given objective. Devika aims to be a competitive open-source alternative to Devin by Cognition AI.

SWE-agent

SWE-agent takes a GitHub issue and tries to automatically fix it, using GPT-4, or your LM of choice. It solves 12.47% of bugs in the SWE-bench evaluation set and takes just 1 minute to run.

Open-Sora-Plan

This project aim to reproduce Sora (Open AI T2V model), we wish the open source community contribute to this project.

spinningup

An educational resource to help anyone learn deep reinforcement learning.

minbpe

Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.

LLocalSearch

LLocalSearch is a completely locally running search aggregator using LLM Agents. The user can ask a question and the system will use a chain of LLMs to find the answer. The user can see the progress of the agents and the final answer. No OpenAI or Google API keys are needed.

hugo-theme-stack

Card-style Hugo theme designed for bloggers

distil-whisper

Distilled variant of Whisper for speech recognition. 6x faster, 50% smaller, within 1% word error rate.

KeyBERT

Minimal keyword extraction with BERT

DeepSeek-V2

DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model

ThunderKittens

Tile primitives for speedy kernels

torchtitan

A native PyTorch Library for large model training

functionary

Chat language model that can use tools and interpret the results

awesome-local-ai

An awesome repository of local AI tools

pyreft

ReFT: Representation Finetuning for Language Models

JetMoE

Reaching LLaMA2 Performance with 0.1M Dollars

quanto

A pytorch Quantization Toolkit

veScale

A PyTorch Native LLM Training Framework

gritlm

Generative Representational Instruction Tuning

contrastors

Train Models Contrastively in Pytorch

annotated-mamba

Annotated version of the Mamba paper

mergoo

A library for easily merging multiple LLM experts, and efficiently train the merged LLM.

cuda-checkpoint

CUDA checkpoint and restore utility

MarathiNLP

Marathi NLP - is a repository dedicated to development of tools and resources for Marathi language.

scaling_sentemb

Scaling Sentence Embeddings with Large Language Models

inference-optimization-blog-post