Stars
Train transformer language models with reinforcement learning.
An Easy-to-use, Scalable and High-performance RLHF Framework based on Ray (PPO & GRPO & REINFORCE++ & vLLM & Ray & Dynamic Sampling & Async Agent RL)
Implementing DeepSeek R1's GRPO algorithm from scratch
Production-tested AI infrastructure tools for efficient AGI development and community-driven innovation
Minimal reproduction of DeepSeek R1-Zero
Fully open reproduction of DeepSeek-R1
A collection of LLM papers, blogs, and projects, with a focus on OpenAI o1 🍓 and reasoning techniques.
本项目旨在分享大模型相关技术原理以及实战经验（大模型工程化、大模型应用落地）
alibaba / Megatron-LLaMA
Forked from NVIDIA/Megatron-LMBest practice for training LLaMA models in Megatron-LM
ModelScope-Agent: An agent framework connecting models in ModelScope with the world
Unsupervised text tokenizer for Neural Network-based text generation.
Hackable and optimized Transformers building blocks, supporting a composable construction.
A 13B large language model developed by Baichuan Intelligent Technology
A high-throughput and memory-efficient inference and serving engine for LLMs
ChatGLM2-6B: An Open Bilingual Chat LLM | 开源双语对话语言模型
Large Language Model Text Generation Inference
中文LLaMA&Alpaca大语言模型+本地CPU/GPU训练部署 (Chinese LLaMA & Alpaca LLMs)
In Building Systems With The ChatGPT API, you will learn how to automate complex workflows using chain calls to a large language model.
GLM-130B: An Open Bilingual Pre-Trained Model (ICLR 2023)
Examples and guides for using the OpenAI API
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 GPT-4 AI Tutor Prompt for customizable personalized learning experiences.
Tool Learning for Big Models, Open-Source Solutions of ChatGPT-Plugins
Official codes for ACL 2023 paper "WebCPM: Interactive Web Search for Chinese Long-form Question Answering"
The ChatGPT Retrieval Plugin lets you easily find personal or work documents by asking questions in natural language.
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.