AirLLM 70B inference with single 4GB GPU

Claude Code 的开源替代方案。Muti Agent AI 编程助手，CLI & Web UI 双入口。自托管，随处部署——手机浏览器也能完整操控。支持任意 LLM，原生浏览器自动化，90+ 命令。技能、插件与持久记忆。企业级安全，零锁定。Docker 一键部署。

为中文大模型定制的 OpenAI SDK 增强库，系统性优化接口适配、响应解析和批量处理等能力，无缝协作 OpenAI 生态内 LangChain、LlamaIndex、LiteLLM 等机器学习应用框架。支持作为 Skill 部署，让 Agent 通过 CNLLM 来调用中文大模型。

A research fork of opencode demonstrating Language Anchoring — making LLMs think consistently in your language. Verified: 95%+ Chinese thinking compliance.

re!think it. System prompt teaching LLMs to execute two core tasks: complex answers without hallucinations, and creative ideas without clichés. Written in math-like logic, which LLMs parse better than plain language. Built for mid-to-high complexity tasks, featuring a Bypass branch to execute simple prompts directly without added cognitive overhead

This repo introduces MagicData-CLAM, a Chinese SFT dataset, and provides to the community two relevant models that we finetuned. Contact business@magicdatatech.com for more information.

🦞 Curated OpenClaw config templates for Chinese LLM providers, multi-channel setups, automation & more | OpenClaw 配置模板大全

🔌 让 OpenAI Codex CLI 接入 GLM (智谱 AI) | Local proxy enabling Codex CLI to work with GLM models - 流式响应 & 工具调用 / Streaming & Tool Calling

基于户晨风直播语料微调的 AI 对话模型

Chinese Reasoning Language Model with Step-by-Step trajectories.

✨ XingLing (星灵): A lightweight 0.68B Chinese Chat LLM built from scratch (Pretraining + SFT)

🚀 Optimize memory for large language models, enabling 70B models on a 4GB GPU and 405B Llama3.1 on 8GB VRAM without compression techniques.

🎯 Fine-tuning LLMs using LlamaFactory for financial intent understanding | Evaluating open-source models on OpenFinData benchmark | Full implementation with multiple models (Qwen2.5/ChatGLM3/Baichuan2/Llama3)

大语言模型高效微调

搜集和分享个人喜欢的大语言模型（LLM）相关资源的在线百科全书。涵盖 LLM 的基础知识、研究进展、技术应用、工具和最佳实践。

Community-maintained multilingual resource hub for DeepSeek V4 — recipes, benchmarks, deployment, and migration guides in 7 languages

心核: Delta Rule 联想记忆 + LoRA，persona 驱动统一分布训练。短期 W 矩阵 + 未来长期 Memory MLP 双层记忆，小 transformer 涌现个性。Not RAG, not longer context.

国产大模型API Chat Demo - One API for DeepSeek, Qwen, GLM, Kimi. OpenAI-compatible gateway.

Exploring the Frontier of Chinese LLM Writing

中文长篇网文 LLM 续写框架。