JulianZhu's starred repositories
Phi2-mini-Chinese
Phi2-Chinese-0.2B 从0开始训练自己的Phi2中文小模型,支持接入langchain加载本地知识库做检索增强生成RAG。Training your own Phi2 small chat model from scratch.
direct-preference-optimization
Reference implementation for DPO (Direct Preference Optimization)
lm-human-preferences
Code for the paper Fine-Tuning Language Models from Human Preferences
summarize-from-feedback
Code for "Learning to summarize from human feedback"
ppo-implementation-details
The source code for the blog post The 37 Implementation Details of Proximal Policy Optimization
KwaiAgents
A generalized information-seeking agent system with Large Language Models (LLMs).
VRoidChinese
VRoidStudio汉化插件
langchainjs
🦜🔗 Build context-aware reasoning applications 🦜🔗
SwiftInfer
Efficient AI Inference & Serving
mobile-aloha
Mobile ALOHA: Learning Bimanual Mobile Manipulation with Low-Cost Whole-Body Teleoperation
stripedhyena
Repository for StripedHyena, a state-of-the-art beyond Transformer architecture
taro-color-ui
基于 ColorUI 封装的 TaroUI 组件库
colorui-react
ColorUI 组件库—React版本