Get your documents ready for gen AI

Your Next Store: Modern Commerce with Next.js and Stripe as the backend.

The open source, local-first Figma for React. Design directly in your live React app and publish your changes to code.

🚀 Next Generation AI One-Stop Internationalization Solution. 🚀 下一代 AI 一站式 B/C 端解决方案，支持 OpenAI，Midjourney，Claude，讯飞星火，Stable Diffusion，DALL·E，ChatGLM，通义千问，腾讯混元，360 智脑，百川 AI，火山方舟，新必应，Gemini，Moonshot …

Meta's fleetwide profiler framework

🐳Dockerfile for 🎨ComfyUI. | 容器镜像与启动脚本

🚀 Efficiently (pre)training foundation models with native PyTorch features, including FSDP for training and SDPA implementation of Flash attention v2.

LlaMA3-SFT, Meta-Llama-3-8B/Meta-Llama-3-8B-Instruct微调(transformers)/LORA(peft)/推理, 支持中文(chinese, zh)

The complete training code of the open-source high-performance Llama model, including the full process from pre-training to RLHF.

Unofficial implementation of https://arxiv.org/pdf/2407.14679

Llama中文社区，Llama3在线体验和微调模型已开放，实时汇总最新Llama3学习资料，已将所有代码更新适配Llama3，构建最好的中文Llama大模型，完全开源可商用

The simplest, fastest repository for training/finetuning medium-sized GPTs.

A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training

Use PEFT or Full-parameter to finetune 400+ LLMs or 100+ MLLMs. (LLM: Qwen2.5, Llama3.2, GLM4, Internlm2.5, Yi1.5, Mistral, Baichuan2, DeepSeek, Gemma2, ...; MLLM: Qwen2-VL, Qwen2-Audio, Llama3.2-V…

PatrickStar enables Larger, Faster, Greener Pretrained Models for NLP and democratizes AI for everyone.

DLRover: An Automatic Distributed Deep Learning System

制作懂人情世故的大语言模型 | 提示词工程、RAG、Agent、微调全流程教程

The official repo of Pai-Megatron-Patch for LLM & VLM large scale training developed by Alibaba Cloud.

Best practice for training LLaMA models in Megatron-LM

中文LLaMA-2 & Alpaca-2大模型二期项目 + 64K超长上下文模型 (Chinese LLaMA-2 & Alpaca-2 LLMs with 64K long context models)

🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production

Code and documentation to train Stanford's Alpaca models, and generate the data.

Aligning pretrained language models with instruction data generated by themselves.

FauxPilot - an open-source alternative to GitHub Copilot server

交易模块

Semantic Search on Wikipedia with Upstash Vector

Retrieval Augmented Generation (RAG) chatbot powered by Weaviate

xDiT: A Scalable Inference Engine for Diffusion Transformers (DiTs) with Massive Parallelism