firslov

video-compress

Compress video by 90% without losing much quality, similar to what Pied Piper achieves.

mem0

The memory layer for Personalized AI

lobe-chat

🤯 Lobe Chat - an open-source, modern-design LLMs/AI chat framework. Supports Multi AI Providers( OpenAI / Claude 3 / Gemini / Ollama / Bedrock / Azure / Mistral / Perplexity ), Multi-Modals (Vision/TTS) and plugin system. One-click FREE deployment of your private ChatGPT chat application.

releases

lm-evaluation-harness

A framework for few-shot evaluation of language models.

glm4v-assistant

Sample GLM4V + ChatTTS AI assistant

ChatTTS

A generative speech model for daily dialogue.

earthworm

Learning English through the method of constructing sentences with conjunctions

chinese-llm-benchmark

中文大模型能力评测榜单：目前已囊括106个大模型，覆盖chatgpt、gpt4o、百度文心一言、阿里通义千问、讯飞星火、商汤senseChat、minimax等商用模型， 以及百川、qwen2、glm4、yi、书生internLM2、llama3等开源大模型，多维度能力评测。不仅提供能力评分排行榜，也提供所有模型的原始输出结果！

ChatGPT-Next-Web

A cross-platform ChatGPT/Gemini UI (Web / PWA / Linux / Win / MacOS). 一键拥有你自己的跨平台 ChatGPT/Gemini 应用。

tuning_playbook

A playbook for systematically maximizing the performance of deep learning models.

awesome-pretrained-chinese-nlp-models

Awesome Pretrained Chinese NLP Models，高质量中文预训练模型&大模型&多模态模型&大语言模型集合

onenav

使用PHP + SQLite 3开发的书签管理系统，将浏览器书签集中式管理，做到一处部署，随处访问。

gpt-crawler

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

clash-verge-rev

Continuation of Clash Verge - A Clash Meta GUI based on Tauri (Windows, MacOS, Linux)

UninstallMAU

An easy way to uninstall Microsoft AutoUpdate on macOS.

CLUEDatasetSearch

搜索所有中文NLP数据集，附常用英文NLP数据集

ChatGPT

OpenAI API Free Reverse Proxy

CogVLM

a state-of-the-art-level open visual language model | 多模态预训练模型

FlagEmbedding

Retrieval and Retrieval-augmented LLMs

codeshell-vscode

An intelligent coding assistant plugin for Visual Studio Code, developed based on CodeShell

codeshell

A series of code large language models developed by PKU-KCL

vllm

A high-throughput and memory-efficient inference and serving engine for LLMs

petals

🌸 Run LLMs at home, BitTorrent-style. Fine-tuning and inference up to 10x faster than offloading

Linly

Chinese-LLaMA 1&2、Chinese-Falcon 基础模型；ChatFlow中文对话模型；中文OpenLLaMA模型；NLP预训练/指令微调数据集

LLaMA-Factory

A WebUI for Efficient Fine-Tuning of 100+ LLMs (ACL 2024)

gptel

A simple LLM client for Emacs

mlc-llm

Universal LLM Deployment Engine with ML Compilation

ChatGLM-6B

ChatGLM-6B: An Open Bilingual Dialogue Language Model | 开源双语对话语言模型

RWKV-LM

RWKV is an RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best of RNN and transformer - great performance, fast inference, saves VRAM, fast training, "infinite" ctx_len, and free sentence embedding.