Starred repositories
PyHessian is a Pytorch library for second-order based analysis and training of Neural Networks
Calculate perplexity on a text with pre-trained language models. Support MLM (eg. DeBERTa), recurrent LM (eg. GPT3), and encoder-decoder LM (eg. Flan-T5).
This package contains the original 2012 AlexNet code.
Research progress on speech deepfake detection: Relevant datasets aggregated from the review literature and publicly available codes
A simple screen parsing tool towards pure vision based GUI agent
Jan is an open source alternative to ChatGPT that runs 100% offline on your computer
🤖 The free, Open Source alternative to OpenAI, Claude and others. Self-hosted and local-first. Drop-in replacement for OpenAI, running on consumer-grade hardware. No GPU required. Runs gguf, transf…
强化学习中文教程（蘑菇书🍄），在线阅读地址：https://datawhalechina.github.io/easy-rl/
Code and documentation to train Stanford's Alpaca models, and generate the data.
A curated list of awesome LLM agents frameworks.
A powerful framework for building realtime voice AI agents 🤖🎙️📹
Opiniated RAG for integrating GenAI in your apps 🧠 Focus on your product rather than the RAG. Easy integration in existing products with customisation! Any LLM: GPT4, Groq, Llama. Any Vectorstore: …
SuperEasy 100% Local RAG with Ollama + Email RAG
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
A reading list for large models safety, security, and privacy (including Awesome LLM Security, Safety, etc.).
专门用于给图片加水印打码的工具，完全基于浏览器本地API，无任何网络请求（特别适合身份证等敏感证件）
Get up and running with Llama 3.3, DeepSeek-R1, Phi-4, Gemma 3, Mistral Small 3.1 and other large language models.
A curated list of resources for using LLMs to develop more competitive grant applications.
面向开发者的 LLM 入门教程，吴恩达大模型系列课程中文版
A collection of LLM papers, blogs, and projects, with a focus on OpenAI o1 🍓 and reasoning techniques.
Microsoft's GraphRAG + AutoGen + Ollama + Chainlit = Fully Local & Free Multi-Agent RAG Superbot
Transfer Learning Library for Domain Adaptation, Task Adaptation, and Domain Generalization
🐙 Guides, papers, lecture, notebooks and resources for prompt engineering
A continuously updated collection of CodeLLM papers maintained by PurCL group @ Purdue
The AI developer platform. Use Weights & Biases to train and fine-tune models, and manage models from experimentation to production.