《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

Firefly: 大模型训练工具，支持训练Qwen2.5、Qwen2、Yi1.5、Phi-3、Llama3、Gemma、MiniCPM、Yi、Deepseek、Orion、Xverse、Mixtral-8x7B、Zephyr、Mistral、Baichuan2、Llma2、Llama、Qwen、Baichuan、ChatGLM2、InternLM、Ziya2、Vicuna、Bloom等大模型

A course of learning LLM inference serving on Apple Silicon for systems engineers: build a tiny vLLM + Qwen.

快速提取音视频内容，整理成一份结构化的markdown笔记

A series of math-specific large language models of our Qwen2 series.

[ICLR 2025] Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing. Your efficient and high-quality synthetic data generation pipeline!

🐋MindChat（漫谈）——心理大模型：漫谈人生路, 笑对风霜途

校招、秋招、春招、实习好项目，带你从零动手实现支持LLama2/3和Qwen2.5的大模型推理框架。

A fine-tuned model from Qwen2-1.5B-Instruct, capable of handling sensitive topics like violence, explicit content. / 从 Qwen2-1.5B-Instruct 微调，能处理各类敏感话题

[ICCV2025] CAD-Recode: Reverse Engineering CAD Code from Point Clouds

Higher performance OpenAI LLM service than vLLM serve: A pure C++ high-performance OpenAI LLM service implemented with GPRS+TensorRT-LLM+Tokenizers.cpp, supporting chat and function call, AI agents, distributed multi-GPU inference, multimodal capabilities, and a Gradio chat interface.

Explore LLM model deployment based on AXera's AI chips

🧘🏻‍♂️KarmaVLM (相生)：A family of high efficiency and powerful visual language model.

AskTube - An AI-powered YouTube video summarizer and QA assistant powered by Retrieval Augmented Generation (RAG) 🤖. Run it entirely on your local machine with Ollama, or cloud-based models like Claude, OpenAI, Gemini, Mistral, and more.

✨🦋 illufly - 【幻蝶】基于记忆蒸馏、资料检索的自我进化智能体

[ACL 2025] We introduce ScaleQuest, a scalable, novel and cost-effective data synthesis method to unleash the reasoning capability of LLMs.

视频理解：千问视频多模态模型 & Dify

qwen2 and llama3 cpp implementation

Make SGLang go brrr

Visual Instruction Tuning for Qwen2 Base Model