Starred repositories
AI agents running research on single-GPU nanochat training automatically
MMaDA - Open-Sourced Multimodal Large Diffusion Language Models (dLLMs with block diffusion, mixed-CoT, unified RL)
Robust Speech Recognition via Large-Scale Weak Supervision
中文语音识别; Mandarin Automatic Speech Recognition;
Easy-to-use Speech Toolkit including Self-Supervised Learning model, SOTA/Streaming ASR with punctuation, Streaming TTS with text frontend, Speaker Verification System, End-to-End Speech Translatio…
This tool has been deprecated. Use Agentic Document Extraction instead.
Lightweight justice for your single-board computer!
Port of Funasr's Sense-voice model in C/C++
A great looking and easy-to-use photo-management-system you can run on your server, to manage and share photos.
Photo gallery for self-hosted personal servers
A lightweight test input generator for Android. Similar to Monkey, but with more intelligence and cool features!
Open source alternative to OpenAI o1 reasoning model
g1: Using Llama-3.1 70b on Groq to create o1-like reasoning chains
This is the repo for the paper Multi-Agent Collaborative Data Selection for Efficient LLM Pretraining.
[ICLR 2025] SuperCorrect: Advancing Small LLM Reasoning with Thought Template Distillation and Self-Correction
Validation classes for a wide range of domains, and the ability to chain validators to create complex validation criteria
High-performance GPGPU inference of OpenAI's Whisper automatic speech recognition (ASR) model
An open-source RAG-based tool for chatting with your documents.
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。
The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery 🧑🔬
llama.cpp fork with additional SOTA quants and improved performance
AIHawk aims to easy job hunt process by automating the job application process. Utilizing artificial intelligence, it enables users to apply for multiple jobs in a tailored way.
主要记录大语言大模型（LLMs） 算法（应用）工程师相关的知识及面试题