A modular graph-based Retrieval-Augmented Generation (RAG) system

Train transformer language models with reinforcement learning.

Notes and commented code for RLHF (PPO)

🤗 Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch and FLAX.

Materials for the Hugging Face Diffusion Models Course

Stable Diffusion implemented from scratch in PyTorch

A series of large language models developed by Baichuan Intelligent Technology

Official inference library for Mistral models

Get up and running with Llama 3.2, Mistral, Gemma 2, and other large language models.

Reference implementation of Mistral AI 7B v0.1 model.

AppAgent: Multimodal Agents as Smartphone Users, an LLM-based multimodal agent framework designed to operate smartphone apps.

A code-first agent framework for seamlessly planning and executing data analytics tasks.

Inference code for LLaMA models

A repository that contains models, datasets, and fine-tuning techniques for DB-GPT, with the purpose of enhancing model performance in Text-to-SQL

Curated tutorials and resources for Large Language Models, Text2SQL, Text2DSL、Text2API、Text2Vis and more.

OpenLLMWiki: Docs of OpenLLMAI. Survey, reproduction and domain/task adaptation of open source chatgpt alternatives/implementations. PiXiu-貔貅 means fortune.

OpenAI 接口管理 & 分发系统，支持 Azure、Anthropic Claude、Google PaLM 2 & Gemini、智谱 ChatGLM、百度文心一言、讯飞星火认知、阿里通义千问、360 智脑以及腾讯混元，可用于二次分发管理 key，仅单可执行文件，已打包好 Docker 镜像，一键部署，开箱即用. OpenAI key management & redistributi…

Inference code for Llama models

[ICLR 2024] Efficient Streaming Language Models with Attention Sinks

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

An Open-source Framework for Data-centric, Self-evolving Autonomous Language Agents

The paper list of the 86-page paper "The Rise and Potential of Large Language Model Based Agents: A Survey" by Zhiheng Xi et al.

A 13B large language model developed by Baichuan Intelligent Technology

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。

studio for commune/chatbot based on Laravel Framework.

Making large AI models cheaper, faster and more accessible