Stars
Finetune Llama 3.3, DeepSeek-R1 & Reasoning LLMs 2x faster with 70% less memory! 🦥
PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.
GitHub Copilot plugin for Typora on both Windows, macOS and Linux, provided through Copilot.vim.
Fully open reproduction of DeepSeek-R1
这是一个从头训练大语言模型的项目,包括预训练、微调和直接偏好优化,模型拥有1B参数,支持中英文。
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GPT3.5/GPT-4o/GPT-o1/ DeepSeek/Claude/文心一言/讯飞星火/通义千问/ Gemini/GLM-4/Claude/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。
基于chatgpt-on-wechat框架,只能运行在Win平台的项目,通过本项目可以将微信或者企业微信个人号接入ChatGpt、文心一言、FastGpt、LinkAI,可以文字对话、语音对话、图片交互、文件交互等。
基于COM通信的微信pc hook应用端,支持Onebot12协议
About Conversational RPA SDK for Chatbot Makers
Large Language Model Text Generation Inference
A fast, user friendly ORM and query builder which supports asyncio.
Chat-Style-Bot是一个聊天风格模仿大语言模型,通过分析和学习微信聊天记录,可模仿你的说话风格(口头禅等),并可接入微信和你的朋友们自动聊天。Chat-Style-Bot is a chat style imitating llm. By analyzing and learning WeChat chat records, it can imitate your speaking…
Learn Low Level Design (LLD) and prepare for interviews using free resources.
Given an existing docker container, prints the command line necessary to run a copy of it.
A tool for generating .pex (Python EXecutable) files, lock files and venvs.
Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.
kaldi-asr/kaldi is the official location of the Kaldi project.
Cross-platform, fast, feature-rich, GPU based terminal
华为商城抢购手机的Python脚本 Python script of Huawei Store snapping up mobile phones
Build resilient language agents as graphs.