gpt_server是一个用于生产级部署LLMs、Embedding、Reranker、ASR、TTS、文生图、图片编辑和文生视频的开源框架。

EasyR1: An Efficient, Scalable, Multi-Modality RL Training Framework based on veRL

Tongyi Deep Research, the Leading Open-source Deep Research Agent

This repository is the official implementation of the ECAI 2024 conference paper SUBLLM: A Novel Efficient Architecture with Token Sequence Subsampling for LLM

MTEB: Massive Text Embedding Benchmark

Question and Answer based on Anything.

Production-ready platform for agentic workflow development.

Generating fake data for the JVM (Java, Kotlin, Groovy) has never been easier!

从0到1构建一个MiniLLM (pretrain+sft+dpo实践中)

ChatPilot: Chat Agent Web UI，实现Chat对话前端，支持Google搜索、文件网址对话（RAG）、代码解释器功能，复现了Kimi Chat(文件，拖进来；网址，发出来)。

1 min voice data can also be used to train a good TTS model! (few shot voice cloning)

HuatuoGPT2, One-stage Training for Medical Adaption of LLMs. (An Open Medical GPT)

Code and documents of LongLoRA and LongAlpaca (ICLR 2024 Oral)

文本相似度，语义向量，文本向量，text-similarity，similarity, sentence-similarity，BERT，SimCSE，BERT-Whitening，Sentence-BERT, PromCSE, SBERT

中文 NLP 预处理、解析工具包，准确、高效、易用 A Chinese NLP Preprocessing & Parsing Package www.jionlp.com

RAG for Local LLM, chat with PDF/doc/txt files, ChatPDF. 纯原生实现RAG功能，基于本地LLM、embedding模型、reranker模型实现，支持GraphRAG，无须安装任何第三方agent库。

RAG for Local LLM, chat with PDF/doc/txt files, ChatPDF

LlamaIndex is the leading framework for building LLM-powered agents over your data.

Openai style api for open large language models, using LLMs just as chatgpt! Support for LLaMA, LLaMA-2, BLOOM, Falcon, Baichuan, Qwen, Xverse, SqlCoder, CodeLLaMA, ChatGLM, ChatGLM2, ChatGLM3 etc.…

比Sentence-BERT更有效的句向量方案

《ChatGPT原理与实战：大型语言模型的算法、技术和私有化》

Code for the paper "Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer"

Retrieval and Retrieval-augmented LLMs

Similarities: a toolkit for similarity calculation and semantic search. 相似度计算、匹配搜索工具包，支持亿级数据文搜文、文搜图、图搜图，python3开发，开箱即用。

tiktoken is a fast BPE tokeniser for use with OpenAI's models.

Llama中文社区，实时汇总最新Llama学习资料，构建最好的中文Llama大模型开源生态，完全开源可商用

A series of large language models developed by Baichuan Intelligent Technology

Firefly: 大模型训练工具，支持训练Qwen2.5、Qwen2、Yi1.5、Phi-3、Llama3、Gemma、MiniCPM、Yi、Deepseek、Orion、Xverse、Mixtral-8x7B、Zephyr、Mistral、Baichuan2、Llma2、Llama、Qwen、Baichuan、ChatGLM2、InternLM、Ziya2、Vicuna、Bloom等大模型

MedicalGPT: Training Your Own Medical GPT Model with ChatGPT Training Pipeline. 训练医疗大模型，实现了包括增量预训练(PT)、有监督微调(SFT)、RLHF、DPO、ORPO、GRPO。

用于从头预训练+SFT一个小参数量的中文LLaMa2的仓库；24G单卡即可运行得到一个具备简单中文问答能力的chat-llama2.