AirLLM 70B inference with single 4GB GPU

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 [email protected] for more information.

基于户晨风直播语料微调的 AI 对话模型

🦞 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

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

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

🎯 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)

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

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。

中文大模型适配库，将 API 响应封装为 OpenAI 标准，无缝协作 LangChain、LlamaIndex、LiteLLM 等机器学习框架

Exploring the Frontier of Chinese LLM Writing

Transform probabilistic LLMs into deterministic state machines to improve logic, prevent context loss, and generate unique, reliable responses.