User-friendly AI Interface (Supports Ollama, OpenAI API, ...)

MuseTalk: Real-Time High Quality Lip Synchorization with Latent Space Inpainting

Retrieval and Retrieval-augmented LLMs

SGLang is a fast serving framework for large language models and vision language models.

Robust Speech Recognition via Large-Scale Weak Supervision

✨✨Latest Advances on Multimodal Large Language Models

Large-scale, Informative, and Diverse Multi-round Chat Data (and Models)

Qwen3 is the large language model series developed by Qwen team, Alibaba Cloud.

A generative speech model for daily dialogue.

Python & Command-line tool to gather text and metadata on the Web: Crawling, scraping, extraction, output as CSV, JSON, HTML, MD, TXT, XML

LLM training in simple, raw C/CUDA

OpenCompass is an LLM evaluation platform, supporting a wide range of models (Llama3, Mistral, InternLM2,GPT-4,LLaMa2, Qwen,GLM, Claude, etc) over 100+ datasets.

LLM Group Chat Framework: chat with multiple LLMs at the same time. 大模型群聊框架：同时与多个大语言模型聊天。

A Next-Generation Training Engine Built for Ultra-Large MoE Models

整理开源的中文大语言模型，以规模较小、可私有化部署、训练成本较低的模型为主，包括底座模型，垂直领域微调及应用，数据集与教程等。

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

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

A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)

C++ implementation of ChatGLM-6B & ChatGLM2-6B & ChatGLM3 & GLM4(V)

Official github repo for C-Eval, a Chinese evaluation suite for foundation models [NeurIPS 2023]

fastllm是后端无依赖的高性能大模型推理库。同时支持张量并行推理稠密模型和混合模式推理MOE模型，任意10G以上显卡即可推理满血DeepSeek。双路9004/9005服务器+单显卡部署DeepSeek满血满精度原版模型，单并发20tps；INT4量化模型单并发30tps，多并发可达60+。

中英文敏感词、语言检测、中外手机/电话归属地/运营商查询、名字推断性别、手机号抽取、身份证抽取、邮箱抽取、中日文人名库、中文缩写库、拆字词典、词汇情感值、停用词、反动词表、暴恐词表、繁简体转换、英文模拟中文发音、汪峰歌词生成器、职业名称词库、同义词库、反义词库、否定词库、汽车品牌词库、汽车零件词库、连续英文切割、各种中文词向量、公司名字大全、古诗词库、IT词库、财经词库、成语词库、地名词库、…

中文公开聊天语料库

(ෆ`꒳´ෆ) A Survey on Text-to-Image Generation/Synthesis.

Awesome LLM compression research papers and tools.

A 13B large language model developed by Baichuan Intelligent Technology

The ChatGPT Retrieval Plugin lets you easily find personal or work documents by asking questions in natural language.

RWKV (pronounced RwaKuv) is an RNN with great LLM performance, which can also be directly trained like a GPT transformer (parallelizable). We are at RWKV-7 "Goose". So it's combining the best of RN…

Large-scale Pre-training Corpus for Chinese 100G 中文预训练语料

搜索所有中文NLP数据集，附常用英文NLP数据集