Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Core deep-learning frameworks and libraries for pretraining and distributed training.
Signals: deep-learning, neural-network, pytorch, tensorflow, jax, distributed-training, training, deepspeed
2,663 results
Reinforcement learning library(framework) designed for PyTorch, implements DQN, DDPG, A2C, PPO, SAC, MADDPG, A3C, APEX, IMPALA ...
Drift: DLM Reinforcement Learning Training Framework
PyTorch + HuggingFace code for RetoMaton: "Neuro-Symbolic Language Modeling with Automaton-augmented Retrieval" (ICML 2022), including an implementation of kNN-LM and kNN-MT
GRPO training code which scales to 32xH100s for long horizon terminal/coding tasks. Base agent is now the top Qwen3 agent on Stanford's TerminalBench leaderboard.
A customisable 2D platform for agent-based AI research
DeepSeek CLI, a command-line AI coding assistant that leverages the powerful DeepSeek Coder models
Minimal library to train LLMs on TPU in JAX with pjit().
Federated Learning for LLMs.
Effortless plugin and play Optimizer to cut model training costs by 50%. New optimizer that is 2x faster than Adam on LLMs.
Repo for Rho-1: Token-level Data Selection & Selective Pretraining of LLMs.
Pytorch Library for Relational Table Learning with LLMs.
该系列的目的是让读者可以在基础的pytorch上，不依赖任何其他现成的外部库，从零开始理解并实现一个大语言模型的所有组成部分，以及训练微调代码，因此读者仅需python，pytorch和最基础深度学习背景知识即可。
Awesome LLM pre-training resources, including data, frameworks, and methods.
Accelerating your LLM training to full speed! Made with ❤️ by ServiceNow Research
LLM-And-More is a professional, plug-and-play, llm trainer and application builder that guides you through the complete LLM workflow from data to evaluation, from training to deployment, from idea to sevice. / LLM-And-More 是一个专业、开箱即用的大模型训练及应用构建一站式解决方案，包含从数据到评估、从训练到部署、从想法到服务的全流程最佳实践。
No description
Build a ChatGPT like LLM from scratch in PyTorch, explained step by step.
Latency and Memory Analysis of Transformer Models for Training and Inference
CINO: Pre-trained Language Models for Chinese Minority (少数民族语言预训练模型)
Physics of Language Models: Part 4.2, Canon Layers at Scale where Synthetic Pretraining Resonates in Reality
A minimalistic framework for transparently training language models and storing comprehensive checkpoints for in-depth learning dynamics research.
Pytorch implementation of R-BERT: "Enriching Pre-trained Language Model with Entity Information for Relation Classification"
Empower Sequence Labeling with Task-Aware Neural Language Model | a PyTorch Tutorial to Sequence Labeling
Homepage for ProLong (Princeton long-context language models) and paper "How to Train Long-Context Language Models (Effectively)"
24,545 repositories in the index in total.
