Stars
《开源大模型食用指南》针对中国宝宝量身打造的基于Linux环境快速微调（全参数/Lora）、部署国内外开源大模型（LLM）/多模态大模型（MLLM）教程
Lightweight coding agent that runs in your terminal
📚 《从零开始构建智能体》——从零开始的智能体原理与实践教程
The agent that grows with you
Kronos: A Foundation Model for the Language of Financial Markets
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
AIInfra（AI 基础设施）指AI系统从底层芯片等硬件，到上层软件栈支持AI大模型训练和推理。
TradingAgents: Multi-Agents LLM Financial Trading Framework
Build local voice agents with open-source models
收录NLP竞赛策略实现、各任务baseline、相关竞赛经验贴（当前赛事、往期赛事、训练赛）、NLP会议时间、常用自媒体、GPU推荐等，持续更新中
JingMatrix / LSPatch
Forked from LSPosed/LSPatchA non-root Xposed framework extending from LSPosed
哔哩漫游，解除B站客户端番剧区域限制的Xposed模块，并且提供其他小功能。An Xposed module that unblocks bangumi area limit of BILIBILI with miscellaneous features.
Llama中文社区，实时汇总最新Llama学习资料，构建最好的中文Llama大模型开源生态，完全开源可商用
GPT4V-level open-source multi-modal model based on Llama3-8B
a state-of-the-art-level open visual language model | 多模态预训练模型
Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.6, DeepSeek-V4, GLM-5.1, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM4.5v, Gemma4, Llava, …