Stars
🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
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、…
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
1 min voice data can also be used to train a good TTS model! (few shot voice cloning)
A Gradio web UI for Large Language Models with support for multiple inference backends.
Finetune Qwen3, Llama 4, TTS, DeepSeek-R1 & Gemma 3 LLMs 2x faster with 70% less memory! 🦥
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
基于大模型搭建的聊天机器人，同时支持 微信公众号、企业微信应用、飞书、钉钉 等接入，可选择GPT4.1/GPT-4o/GPT-o1/ DeepSeek/Claude/文心一言/讯飞星火/通义千问/ Gemini/GLM-4/Kimi/LinkAI，能处理文本、语音和图片，访问操作系统和互联网，支持基于自有知识库进行定制企业智能客服。
A generative speech model for daily dialogue.
A modular graph-based Retrieval-Augmented Generation (RAG) system
小红书笔记 | 评论爬虫、抖音视频 | 评论爬虫、快手视频 | 评论爬虫、B 站视频 ｜ 评论爬虫、微博帖子 ｜ 评论爬虫、百度贴吧帖子 ｜ 百度贴吧评论回复爬虫 | 知乎问答文章｜评论爬虫
The official repo of Qwen (通义千问) chat & pretrained large language model proposed by Alibaba Cloud.
Letta (formerly MemGPT) is the stateful agents framework with memory, reasoning, and context management.
Faster Whisper transcription with CTranslate2
🤖 可 DIY 的 多模态 AI 聊天机器人 | 🚀 快速接入 微信、 QQ、Telegram、等聊天平台 | 🦈支持DeepSeek、Grok、Claude、Ollama、Gemini、OpenAI | 工作流系统、网页搜索、AI画图、人设调教、虚拟女仆、语音对话 |
Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.
ChatGLM3 series: Open Bilingual Chat LLMs | 开源双语对话语言模型
🤩 Easy-to-use global IM bot platform designed for the LLM era / 简单易用的大模型即时通信机器人平台 ⚡️ Bots for QQ / Discord / WeChat（企业微信、个人微信）/ Telegram / 飞书 / 钉钉 / Slack 🧩 Integrated with ChatGPT、DeepSeek、Dify、n8…
A Fundamental End-to-End Speech Recognition Toolkit and Open Source SOTA Pretrained Models, Supporting Speech Recognition, Voice Activity Detection, Text Post-processing etc.
A framework for training and evaluating AI models on a variety of openly available dialogue datasets.
Retrieval and Retrieval-augmented LLMs
Moshi is a speech-text foundation model and full-duplex spoken dialogue framework. It uses Mimi, a state-of-the-art streaming neural audio codec.
[CVPR 2024 Oral] InternVL Family: A Pioneering Open-Source Alternative to GPT-4o. 接近GPT-4o表现的开源多模态对话模型
Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 500+ LLMs (Qwen3, Qwen3-MoE, Llama4, InternLM3, DeepSeek-R1, ...) and 200+ MLLMs (Qwen2.5-VL, Qwen2.5-Omni, Qwen2-Audio, Ovis2, InternVL3, Llava, GLM4…
Official release of InternLM series (InternLM, InternLM2, InternLM2.5, InternLM3).
GLM-4 series: Open Multilingual Multimodal Chat LMs | 开源多语言多模态对话模型
Firefly: 大模型训练工具，支持训练Qwen2.5、Qwen2、Yi1.5、Phi-3、Llama3、Gemma、MiniCPM、Yi、Deepseek、Orion、Xverse、Mixtral-8x7B、Zephyr、Mistral、Baichuan2、Llma2、Llama、Qwen、Baichuan、ChatGLM2、InternLM、Ziya2、Vicuna、Bloom等大模型
Real time interactive streaming digital human
Solve Visual Understanding with Reinforced VLMs