qwen

An 18 notebook course that isolates and measures each component of agentic loop engineering on real, industry standard software datasets.

Visual Instruction Tuning for Qwen2 Base Model

Collection of Basic Prompt Templates for Various Chat LLMs (Chat LLM 的基础提示模板集合)

给 DeepSeek 补上「眼睛和耳朵」的多模态视觉插件：看图 / OCR / 物体检测 / 视频理解 / 语音转写 / 截图直读，一键安装（DSH 插件）。

Native Windows vLLM 0.27.1 wheels: Python 3.13, PyTorch 2.13 + CUDA 13.0, SM 7.5-12.0 for RTX 20/30/40/50, OpenAI-compatible serving, FlashAttention/Rust, 10 KV formats, Multi-TurboQuant, and experimental CPU/RAM/NVMe prompt-KV offload - no WSL or Docker.

AMG-RAG (Agentic Medical Graph-RAG) is a comprehensive framework that automates the construction and continuous updating of Medical Knowledge Graphs (MKGs), integrates reasoning, and retrieves current external evidence for medical Question Answering (QA).

Build & prompt Qwen3.x agents in their native dialect — extracted from qwen-code & Qwen-Agent

An AI-powered solution designed to enhance mobility for visually impaired individuals by combining real-time video analysis with voice-guided navigation. Also features a built-in Multi-Agent AI Assistant — users can speak naturally to complete map navigation, adjust system settings, send messages to family.

Synthetic medical VQA pipeline: 119K images annotated by frontier VLMs, cross-validated at 93% agreement, fine-tuned on 3 model families (2-3B params)

Local-first Model Context Protocol (MCP) memory layer for Codex CLI/Desktop, Claude Code, Gemini CLI, Qwen/DeepSeek/Ollama and agent workflows. SQLite + FTS5 compact context packs, token savings, read-only mode, no external memory server.

A Chat Client for LLMs, written in Compose Multiplatform.

Train YOLO + VLM with one command. Auto-generate vision-language training data from YOLO labels - no extra labeling needed.

From-scratch C++23/CUDA inference engine for the NVIDIA RTX 5090 (sm_120a). The best single-GPU backend for agentic AI: tool calling, long-context loops, reasoning and concurrent sub-agents. Decode beats llama.cpp b9976 by 42-48% on dense GGUF (measured 2026-07-12), at-or-ahead of vLLM on NVFP4. 100% written by Claude Code.

Private, on-device AI desktop app — GGUF (llama.cpp) & MLX, with Qwen3.8's native reasoning-effort ladder wired in as a real control. Local coding agent, RAG knowledge base, Deep Research, vision and voice. 100% offline, no account, no telemetry. Windows & macOS.

[ICLR 2026] AgilePruner: An Empirical Study of Attention and Diversity for Adaptive Visual Token Pruning in Large Vision-Language Models

ComfyUI custom nodes for DeepSeek, Qwen, GPT, and other OpenAI-compatible LLM APIs, with tools for chat, translation, vision, and JSON workflows.

Multimodal AI studio powered by Qwen3.6-35B-A3B. End-to-end web app exposing visual reasoning, image captioning, and document understanding tools from a single model with side-by-side output across versions.

A web-based memory usage and performance calculator for Huggingface GGUF models

a simple lightweight large language model pipeline framework.

A lightweight and intuitive Node.js client for the Paxsenix AI API.