Stars
The original local LLM interface. Text, vision, tool-calling, training, and more. 100% offline.
Train transformer language models with reinforcement learning.
Streamlink is a CLI utility which pipes video streams from various services into a video player
Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.5, DeepSeek-R1, GLM-5, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM4.5v, Llava, Phi4, ...)…
Real-time video and audio processing on Streamlit
🚀🚀 「大模型」2小时完全从0训练64M的小参数GPT！🌏 Train a 64M-parameter GPT from scratch in just 2h!
🚀 「大模型」1小时从0训练67M参数的视觉多模态VLM！🌏 Train a 67M-parameter VLM from scratch in just 1 hours!
Cross-platform, customizable ML solutions for live and streaming media.
Universal LLM Deployment Engine with ML Compilation
A community-maintained Python framework for creating mathematical animations.
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
The official Python SDK for the ElevenLabs API.
vits2 backbone with multilingual-bert
Create Epic Math and Physics Animations & Study Notes From Text and Images.
Use Microsoft Edge's online text-to-speech service from Python WITHOUT needing Microsoft Edge or Windows or an API key
AIdea 是一款支持 GPT 以及国产大语言模型通义千问、文心一言等，支持 Stable Diffusion 文生图、图生图、 SDXL1.0、超分辨率、图片上色的全能型 APP。
A Production-ready Reinforcement Learning AI Agent Library brought by the Applied Reinforcement Learning team at Meta.
A robust, efficient, low-latency speech-to-text library with advanced voice activity detection, wake word activation and instant transcription.
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）
a Fast Fourier Transform (FFT) library that tries to Keep it Simple, Stupid
TurboDiffusion: 100–200× Acceleration for Video Diffusion Models
Crack LeetCode, not only how, but also why.
AI 助手全套开源解决方案，自带运营管理后台，开箱即用。集成了 ChatGPT, Azure, ChatGLM,讯飞星火，文心一言等多个平台的大语言模型。支持 MJ AI 绘画，Stable Diffusion AI 绘画，微博热搜等插件工具。采用 Go + Vue3 + element-plus 实现。
Digital Avatar Conversational System - Linly-Talker. 😄✨ Linly-Talker is an intelligent AI system that combines large language models (LLMs) with visual models to create a novel human-AI interaction…
Qihoo360 / 360-LLaMA-Factory
Forked from hiyouga/LlamaFactoryadds Sequence Parallelism into LLaMA-Factory