Train transformer language models with reinforcement learning.

CodeRAG-Bench: Can Retrieval Augment Code Generation?

SGLang is yet another fast serving framework for large language models and vision language models.

A library with extensible implementations of DPO, KTO, PPO, ORPO, and other human-aware loss functions (HALOs).

Code at the speed of thought – Zed is a high-performance, multiplayer code editor from the creators of Atom and Tree-sitter.

计图大模型推理库，具有高性能、配置要求低、中文支持好、可移植等特点

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.

Efficiently Fine-Tune 100+ LLMs in WebUI (ACL 2024)

The official Python library for the OpenAI API

Dataflow-guided retrieval augmentation for repository-level code completion, ACL 2024 (main)

Fast and memory-efficient exact attention

Source codes for paper ”ReACC: A Retrieval-Augmented Code Completion Framework“

Retrieval and Retrieval-augmented LLMs

Fast, indexed regexp search over large file trees

official repository of aiXcoder-7B Code Large Language Model

CodeQwen1.5 is the code version of Qwen, the large language model series developed by Qwen team, Alibaba Cloud.

Qwen2 is the large language model series developed by Qwen team, Alibaba Cloud.

RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding.

Code Assistance/ Developer Productivity suite of Models

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

🙌 OpenHands: Code Less, Make More

《构筑大语言模型应用：应用开发与架构设计》一本关于 LLM 在真实世界应用的开源电子书，介绍了大语言模型的基础知识和应用，以及如何构建自己的模型。其中包括Prompt的编写、开发和管理，探索最好的大语言模型能带来什么，以及LLM应用开发的模式和架构设计。

Large Language Models for Software Engineering

Sweep: open-source AI-powered Software Developer for small features and bug fixes.

Home of StarCoder2!