Implementation of Toolformer, Language Models That Can Use Tools, by MetaAI

FlagAI (Fast LArge-scale General AI models) is a fast, easy-to-use and extensible toolkit for large-scale model.

An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.

OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamically to do so.

🧠 AI-powered enterprise search engine 🔎

ChatGPT 中文调教指南。各种场景使用指南。学习怎么让它听你的话。

🐙 Guides, papers, lessons, notebooks and resources for prompt engineering, context engineering, RAG, and AI Agents.

🚀 Accelerate inference and training of 🤗 Transformers, Diffusers, TIMM and Sentence Transformers with easy to use hardware optimization tools

LlamaIndex is the leading document agent and OCR platform

The implementation of "Prismer: A Vision-Language Model with Multi-Task Experts".

Invoke is a leading creative engine for Stable Diffusion models, empowering professionals, artists, and enthusiasts to generate and create visual media using the latest AI-driven technologies. The …

ChatLLaMA 📢 Open source implementation for LLaMA-based ChatGPT runnable in a single GPU. 15x faster training process than ChatGPT

Aligning pretrained language models with instruction data generated by themselves.

[CVPR'23] Universal Instance Perception as Object Discovery and Retrieval

ChatGLM-6B: An Open Bilingual Dialogue Language Model | 开源双语对话语言模型

LAVIS - A One-stop Library for Language-Vision Intelligence

Resources for Multiple Object Tracking (MOT)

Leaderboard, taxonomy, and curated list of few-shot object detection papers.

Official implementation of the CVPR 2022 paper "DETReg: Unsupervised Pretraining with Region Priors for Object Detection".

A Transfer Learning System in Object Detection

[CVPR 2022] Official code for "RegionCLIP: Region-based Language-Image Pretraining"

A practice for million-scale multi-domain universal object detection

Code release for "Detecting Twenty-thousand Classes using Image-level Supervision".

Easy Parallel Library (EPL) is a general and efficient deep learning framework for distributed model training.

Chinese version of CLIP which achieves Chinese cross-modal retrieval and representation generation.

🏕️ Reproducible development environment for humans and agents

FeatureHub - cloud native feature flags, A/B testing and remote configuration service. Real-time streaming feature updates. Provided with Java, JavaScript, React, Python, Go, .Net, Ruby, Android, S…