AirLLM 70B inference with single 4GB GPU
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
Chinese Reasoning Language Model with Step-by-Step trajectories.
✨ XingLing (星灵): A lightweight 0.68B Chinese Chat LLM built from scratch (Pretraining + SFT)
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
🧠 2026 LLM comparison — DeepSeek V3.2 vs Qwen 3.5 vs Kimi K2.5 vs GLM 5. Pricing, reasoning, coding.
🧠 DeepSeek V3.2 LLM skill — coding, reasoning, analysis. Claude Code & 15+ platforms.
🎯 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)
🧠 Everything about DeepSeek V4 — next-gen coding AI. Architecture analysis, benchmarks, API guides.
🚀 Optimize memory for large language models, enabling 70B models on a 4GB GPU and 405B Llama3.1 on 8GB VRAM without compression techniques.
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。
🔌 Enable OpenAI Codex CLI to work with GLM (智谱 AI) models - Full streaming & tool calling support
Add a description, image, and links to the chinese-llm topic page so that developers can more easily learn about it.
To associate your repository with the chinese-llm topic, visit your repo's landing page and select "manage topics."