Netease Youdao's open-source embedding and reranker models for RAG products.

On-device wake word detection powered by deep learning

Implement a ChatGPT-like LLM in PyTorch from scratch, step by step

本项目为书籍《大模型RAG实战》的代码以及资料汇总。

GLM-4-Voice | 端到端中英语音对话模型

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

Speech To Speech: an effort for an open-sourced and modular GPT4-o

Node.js + JavaScript reference client for the Realtime API (beta)

React app for inspecting, building and debugging with the Realtime API

A collection of papers, codes, projects, tutorials ... for Knowledge Graph and other NLP methods

Use PEFT or Full-parameter to finetune 350+ LLMs or 90+ MLLMs. (LLM: Qwen2.5, Llama3.2, GLM4, Internlm2.5, Yi1.5, Mistral, Baichuan2, DeepSeek, Gemma2, ...; MLLM: Qwen2-VL, Qwen2-Audio, Llama3.2-Vi…

LMDeploy is a toolkit for compressing, deploying, and serving LLMs.

Virtual whiteboard for sketching hand-drawn like diagrams

Real time interactive streaming digital human

Open source libraries and APIs to build custom preprocessing pipelines for labeling, training, or production machine learning pipelines.

Official code repo for the O'Reilly Book - "Hands-On Large Language Models"

每个人都能用的数字人

Spising: ⚡️Open-source AI LangChain-like RAG (Retrieval-Augmented Generation) knowledge database with web UI and Enterprise SSO⚡️, supports OpenAI, Azure, LLaMA, Google Gemini, HuggingFace, Claude,…

open-source multimodal large language model that can hear, talk while thinking. Featuring real-time end-to-end speech input and streaming audio output conversational capabilities.

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

DSPy: The framework for programming—not prompting—foundation models

Code for explaining and evaluating late chunking (chunked pooling)

An open source implementation of CLIP.

很多镜像都在国外。比如 gcr 。国内下载很慢，需要加速。致力于提供连接全世界的稳定可靠安全的容器镜像服务。

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

GraphRAG using Local LLMs - Features robust API and multiple apps for Indexing/Prompt Tuning/Query/Chat/Visualizing/Etc. This is meant to be the ultimate GraphRAG/KG local LLM app.

A sound cloning tool with a web interface, using your voice or any sound to record audio / 一个带web界面的声音克隆工具，使用你的音色或任意声音来录制音频

EVA Series: Visual Representation Fantasies from BAAI