liqiongyu

ttt-lm-pytorch

Official PyTorch implementation of Learning to (Learn at Test Time): RNNs with Expressive Hidden States

coq

Coq is a formal proof management system. It provides a formal language to write mathematical definitions, executable algorithms and theorems together with an environment for semi-interactive development of machine-checked proofs.

aider

aider is AI pair programming in your terminal

WeChatTweak-macOS

A dynamic library tweak for WeChat macOS - 首款微信 macOS 客户端撤回拦截与多开 🔨

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.

OpenDevin

🐚 OpenDevin: Code Less, Make More

whisper

Robust Speech Recognition via Large-Scale Weak Supervision

Real-Time-Voice-Cloning

Clone a voice in 5 seconds to generate arbitrary speech in real-time

alphageometry

EMO

[ICLR 2024]EMO: Earth Mover Distance Optimization for Auto-Regressive Language Modeling(https://arxiv.org/abs/2310.04691)

TinyLlama

The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.

torchscale

Foundation Architecture for (M)LLMs

Megatron-LLaMA

Best practice for training LLaMA models in Megatron-LM

trl

Train transformer language models with reinforcement learning.

trlx

A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)

Llama-Chinese

Llama中文社区，Llama3在线体验和微调模型已开放，实时汇总最新Llama3学习资料，已将所有代码更新适配Llama3，构建最好的中文Llama大模型，完全开源可商用

Megatron-DeepSpeed

Ongoing research training transformer language models at scale, including: BERT & GPT-2

Megatron-LM

Ongoing research training transformer models at scale

LLaMA-Factory

A WebUI for Efficient Fine-Tuning of 100+ LLMs (ACL 2024)

codellama

Inference code for CodeLlama models

ColossalAI

Making large AI models cheaper, faster and more accessible

LMFlow

An Extensible Toolkit for Finetuning and Inference of Large Foundation Models. Large Models for All.

MetaGPT

🌟 The Multi-Agent Framework: First AI Software Company, Towards Natural Language Programming

lean3

Lean Theorem Prover

lean

Lean 3 Theorem Prover (community fork)

vllm

A high-throughput and memory-efficient inference and serving engine for LLMs

flash-attention

Fast and memory-efficient exact attention

LeanAide

Tools based on AI for helping with Lean 4

pylean

Python wrapper for lean-gym

RLTF

Accepted by Transactions on Machine Learning Research (TMLR)