Stars
Compare multiple optimization methods on triton to imporve model service performance
Data processing for and with foundation models! 🍎 🍋 🌽 ➡️ ➡️🍸 🍹 🍷
A comprehensive list of papers using large language/multi-modal models for Robotics/RL, including papers, codes, and related websites
A Survey of Reinforcement Learning for Large Reasoning Models
Aix-DB 基于 LangChain/LangGraph 框架，结合 MCP Skills 多智能体协作架构，实现自然语言到数据洞察的端到端转换。
Memory for 24/7 proactive agents like openclaw (moltbot, clawdbot).
《开源大模型食用指南》针对中国宝宝量身打造的基于Linux环境快速微调（全参数/Lora）、部署国内外开源大模型（LLM）/多模态大模型（MLLM）教程
BISHENG is an open LLM devops platform for next generation Enterprise AI applications. Powerful and comprehensive features include: GenAI workflow, RAG, Agent, Unified model management, Evaluation,…
No fortress, purely open ground. OpenManus is Coming.
Easy-to-Use RAG Framework; CCF AIOps International Challenge 2024 Top3 Solution; CCF AIOps 国际挑战赛 2024 季军方案
Retrieval and Retrieval-augmented LLMs
Train a 1B LLM with 1T tokens from scratch by personal
State-of-the-Art Text Embeddings
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。
Flexible and powerful framework for managing multiple AI agents and handling complex conversations
🪄 Auto-generate Streamlit UI from Pydantic Models and Dataclasses.
Build and run agents you can see, understand and trust.
LangGPT: Empowering everyone to become a prompt expert! 🚀 📌 结构化提示词（Structured Prompt）提出者 📌 元提示词（Meta-Prompt）发起者 📌 最流行的提示词落地范式 | Language of GPT The pioneering framework for structured & meta-prompt…
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
中文LLaMA&Alpaca大语言模型+本地CPU/GPU训练部署 (Chinese LLaMA & Alpaca LLMs)
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）
⭐️ NLP Algorithms with transformers lib. Supporting Text-Classification, Text-Generation, Information-Extraction, Text-Matching, RLHF, SFT etc.
[CVPR 2024] Real-Time Open-Vocabulary Object Detection
This mmengine comments out the part about torch.distributed in mmengine/mmengine/dist/utils.py and mmengine/mmengine/dist/dist.py, which is used to solve the cannot import name 'ProcessGroup' after…