1 min voice data can also be used to train a good TTS model! (few shot voice cloning)

Python scraper based on AI

Building a quick conversation-based search demo with Lepton AI.

🏠 将小爱音箱接入 ChatGPT 和豆包，改造成你的专属语音助手。

MiniCPM3-4B: An edge-side LLM that surpasses GPT-3.5-Turbo.

The open source platform for AI-native application development.

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

Curated list of chatgpt prompts from the top-rated GPTs in the GPTs Store. Prompt Engineering, prompt attack & prompt protect. Advanced Prompt Engineering papers.

Start building LLM-empowered multi-agent applications in an easier way.

Crawlee—A web scraping and browser automation library for Python to build reliable crawlers. Extract data for AI, LLMs, RAG, or GPTs. Download HTML, PDF, JPG, PNG, and other files from websites. Works with BeautifulSoup, Playwright, and raw HTTP. Both headful and headless mode. With proxy rotation.

AIOS: LLM Agent Operating System

Build AI assistants that interact with your systems

Parse files for optimal RAG

Mobile-Agent: The Powerful Mobile Device Operation Assistant Family

Neo4j graph construction from unstructured data using LLMs

[ICML 2024] Mastering Text-to-Image Diffusion: Recaptioning, Planning, and Generating with Multimodal LLMs (RPG)

[ICLR 2024] Official implementation of " 🦙 Time-LLM: Time Series Forecasting by Reprogramming Large Language Models"

Training LLMs with QLoRA + FSDP

收集GPTS的prompt / Collect the prompt of GPTS

Implementation of the training framework proposed in Self-Rewarding Language Model, from MetaAI

GPT based autonomous agent designed to create personalized newspapers tailored to user preferences.

Summarize existing representative LLMs text datasets.

A family of lightweight multimodal models.

LLM powered fuzzing via OSS-Fuzz.

A reading list for large models safety, security, and privacy (including Awesome LLM Security, Safety, etc.).

✨ ChatGemini 是一个基于 Google Gemini 的网页客户端，对标 ChatGPT 3.5，操作逻辑同 ChatGPT 3.5 一致，同时支持在聊天中上传图片，应用会自动调用 Gemini-Pro-Vision 模型进行识图。

心理健康大模型、LLM、The Big Model of Mental Health、Finetune、InternLM2、InternLM2.5、Qwen、ChatGLM、Baichuan、DeepSeek、Mixtral、LLama3、GLM4、Qwen2、LLama3.1

AI-Powered Automated Penetration Testing Tool

Examples and guides for using the GLM APIs

Lighteval is your all-in-one toolkit for evaluating LLMs across multiple backends

Control Any Computer Using LLMs

Nodes for better inpainting with ComfyUI: Fooocus inpaint model for SDXL, LaMa, MAT, and various other tools for pre-filling inpaint & outpaint areas.

AlwaysReddy is a LLM voice assistant that is always just a hotkey away.

Large Language Model based Multi-Agents: A Survey of Progress and Challenges

[ICML'24 Spotlight] LLM Maybe LongLM: Self-Extend LLM Context Window Without Tuning

structured extraction for llms

Automatically evaluate your LLMs in Google Colab

Train Models Contrastively in Pytorch

A personal wearable AI that runs locally

csghub-server is the backend server for CSGHub which helps user to manage datasets, modes, and also run Model Inference, Finetune and Application Spaces.

Here are the Top 100 prompts on GPTStore, which we can use to learn and improve prompt engineering.

A library for making RepE control vectors

[ACL 2024] Progressive LLaMA with Block Expansion.

Efficient AI Inference & Serving