Stars
LAVIS - A One-stop Library for Language-Vision Intelligence
Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype to production without …
The AI-native database built for LLM applications, providing incredibly fast hybrid search of dense vector, sparse vector, tensor (multi-vector), and full-text.
An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.
User-friendly AI Interface (Supports Ollama, OpenAI API, ...)
Universal LLM Deployment Engine with ML Compilation
End-to-End Object Detection with Transformers
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & VLM & TIS & vLLM & Ray & Async RL)
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。
LlamaIndex is the leading document agent and OCR platform
LLM training code for Databricks foundation models
中文LLaMA&Alpaca大语言模型+本地CPU/GPU训练部署 (Chinese LLaMA & Alpaca LLMs)
GUI for ChatGPT API and many LLMs. Supports agents, file-based QA, GPT finetuning and query with web search. All with a neat UI.
Library for fast text representation and classification.
A library for efficient similarity search and clustering of dense vectors.
Milvus is a high-performance, cloud-native vector database built for scalable vector ANN search
deep learning for image processing including classification and object-detection etc.
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。
SimCLRv2 - Big Self-Supervised Models are Strong Semi-Supervised Learners
🔎 Open source distributed and RESTful search engine.
Open-sourced codes for MiniGPT-4 and MiniGPT-v2 (https://minigpt-4.github.io, https://minigpt-v2.github.io/)
State-of-the-Art Embeddings, Retrieval, and Reranking
CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image
Chinese version of CLIP which achieves Chinese cross-modal retrieval and representation generation.
BELLE: Be Everyone's Large Language model Engine（开源中文对话大模型）
Code and documentation to train Stanford's Alpaca models, and generate the data.
Library for conversion between Traditional and Simplified Chinese