🚀🚀 「大模型」2小时完全从0训练26M的小参数GPT！🌏 Train a 26M-parameter GPT from scratch in just 2h!

Fully local web research and report writing assistant

Financial data platform for analysts, quants and AI agents.

PersonViT: Large-scale Self-supervised Vision Transformer for Person Re-Identification

The official implement of TrackSSM

[SIGGRAPH Asia 2022] VideoReTalking: Audio-based Lip Synchronization for Talking Head Video Editing In the Wild

🙌 OpenHands: Code Less, Make More

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"

LLM inference in C/C++

Source code for the X Recommendation Algorithm

singing voice change based on whisper, and lora for singing voice clone

The definitive Web UI for local AI, with powerful features and easy setup.

Running large language models on a single GPU for throughput-oriented scenarios.

Foundation Architecture for (M)LLMs

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, user-friendly, fault-tolerant database built on SQLite.

A TUI chat application writtten in python

A command-line tool to perform health-checks for gRPC applications in Kubernetes and elsewhere

A command-line tool to perform health-checks for gRPC applications in Kubernetes etc.