AI Vtuber是一个由 【ChatterBot/ChatGPT/claude/langchain/chatglm/text-gen-webui/闻达/千问/kimi/ollama】 驱动的虚拟主播【Live2D/UE/xuniren】，可以在 【Bilibili/抖音/快手/微信视频号/拼多多/斗鱼/YouTube/twitch/TikTok】 直播中与观众实时互动 或 直接在本地进行聊…

Align Anything: Training All-modality Model with Feedback

半成品

Dify is an open-source LLM app development platform. Dify's intuitive interface combines AI workflow, RAG pipeline, agent capabilities, model management, observability features and more, letting yo…

Implementation for MatMul-free LM.

Implementation for MatMul-free LM.

Kolmogorov Arnold Networks

🚂 12306 购票助手，支持集群，多账号，多任务购票以及 Web 页面管理

Openai style api for open large language models, using LLMs just as chatgpt! Support for LLaMA, LLaMA-2, BLOOM, Falcon, Baichuan, Qwen, Xverse, SqlCoder, CodeLLaMA, ChatGLM, ChatGLM2, ChatGLM3 etc.…

Crawl a site to generate knowledge files to create your own custom GPT from a URL

Pytorch model for NSFW classification with usage example

此项目是机器学习(Machine Learning)、深度学习(Deep Learning)、NLP面试中常考到的知识点和代码实现，也是作为一个算法工程师必会的理论基础知识。

《Hello 算法》：动画图解、一键运行的数据结构与算法教程。支持 Python, Java, C++, C, C#, JS, Go, Swift, Rust, Ruby, Kotlin, TS, Dart 代码。简体版和繁体版同步更新，English version ongoing

Approaching (Almost) Any Machine Learning Problem中译版，在线文档地址：https://ytzfhqs.github.io/AAAMLP-CN/

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

Code and models for NExT-GPT: Any-to-Any Multimodal Large Language Model

An efficient, flexible and full-featured toolkit for fine-tuning LLM (InternLM2, Llama3, Phi3, Qwen, Mistral, ...)

Ongoing research training transformer models at scale

Graph Neural Network Library for PyTorch

Fast and memory-efficient exact attention

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

The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

The Mojo Programming Language

[NeurIPS 22] [AAAI 24] Recurrent Transformer-based long-context architecture.

High-Resolution Image Synthesis with Latent Diffusion Models

Inpaint anything using Segment Anything and inpainting models.

AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

Grounded SAM: Marrying Grounding DINO with Segment Anything & Stable Diffusion & Recognize Anything - Automatically Detect , Segment and Generate Anything