Starred repositories
🧠「大模型」2小时完全从0训练64M的小参数LLM！Train a 64M-parameter LLM from scratch in just 2h!
Fully local web research and report writing assistant
Open Data Platform for analysts, quants and AI agents.
PersonViT: Large-scale Self-supervised Vision Transformer for Person Re-Identification
[SIGGRAPH Asia 2022] VideoReTalking: Audio-based Lip Synchronization for Talking Head Video Editing In the Wild
🙌 OpenHands: AI-Driven Development
Tools for merging pretrained large language models.
The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.
为GPT/GLM等LLM大语言模型提供实用化交互接口，特别优化论文阅读/润色/写作体验，模块化设计，支持自定义快捷按钮&函数插件，支持Python和C++等项目剖析&自译解功能，PDF/LaTex论文翻译&总结功能，支持并行问询多种LLM模型，支持chatglm3等本地模型。接入通义千问, deepseekcoder, 讯飞星火, 文心一言, llama2, rwkv, claude2, m…
[ICLR 2024] Efficient Streaming Language Models with Attention Sinks
Train transformer language models with reinforcement learning.
[ECCV 2024] Official implementation of the paper "Semantic-SAM: Segment and Recognize Anything at Any Granularity"
Source code for the X Recommendation Algorithm
singing voice change based on whisper, and lora for singing voice clone
Open-source desktop app for local LLMs. Text, vision, tool-calling, OpenAI/Anthropic-compatible API. 100% private.
Running large language models on a single GPU for throughput-oriented scenarios.
Making large AI models cheaper, faster and more accessible
EVA Series: Visual Representation Fantasies from BAAI
12 weeks, 26 lessons, 52 quizzes, classic Machine Learning for all
Best Practices on Recommendation Systems
[EMNLP 2021] SimCSE: Simple Contrastive Learning of Sentence Embeddings https://arxiv.org/abs/2104.08821
The lightweight, fault-tolerant database built on SQLite. Designed to keep your data highly available with minimal effort.
A command-line tool to perform health-checks for gRPC applications in Kubernetes and elsewhere