Stars
记录Qwen3-0.6B-Base模型的持续预训练、后训练算法。用于跑通SFT、RLHF流程。此外，应用一些新算子架构做后训练的探索。
🏥 从零基础到面试通关：20节课彻底搞懂MedicalGPT医疗大模型训练全流程 | PT/SFT/LoRA/RLHF/DPO/GRPO | 100+面试高频考点
🔥 MaxKB is an open-source platform for building enterprise-grade agents. 强大易用的开源企业级智能体平台。
RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs
SkillOpt is a text-space optimizer that trains reusable natural-language skills for frozen LLM agents through trajectory-driven edits, validation-gated updates, and deployable best_skill.md artifacts.
🧠「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!
Skills for Real Engineers. Straight from my .claude directory.
A book for Learning the Foundations of LLMs
The awesome collection of OpenClaw skills. 5,400+ skills filtered and categorized from the official OpenClaw Skills Registry.🦞
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
In-depth tutorials on LLMs, RAGs and real-world AI agent applications.
📚 《从零开始构建智能体》——从零开始的智能体原理与实践教程
Kode CLI — Design for post-human workflows. One unit agent for every human & computer task.
Rethinking Multi-Scale Representations in Deep Deraining Transformer
Chinese software copyright application template document
[ICLR 2023 & IJCV 2025] SeaFormer: Squeeze-enhanced Axial Transformer
This is an official implementation for "Contextual Transformer Networks for Visual Recognition".
[NeurIPS23] PromptRestorer: A Prompting Image Restoration Method with Degradation Perception
Towards Unified Deep Image Deraining: A Survey and A New Benchmark (TPAMI 2025)
Learning Rain Location Prior for Nighttime Deraining (ICCV2023)
HRViT ("Multi-Scale High-Resolution Vision Transformer for Semantic Segmentation"), CVPR 2022.
This is the official PyTorch implementation for “OmniPose: A Multi-Scale Framework for Multi-Person Pose Estimation”.