qwen

[ACL 2024] User-friendly evaluation framework: Eval Suite & Benchmarks: UHGEval, HaluEval, HalluQA, etc.

为 Claude Code 赋能多模态视觉能力，支持豆包、通义千问、GPT-4o 等模型，用于截图 / UI / 图表分析；适配 DeepSeek 等无视觉底座，搭配 browser-harness 可做前端布局自动化检查。

A native Python agent CLI built on DeepAgents CLI, featuring an independent memory Agent that captures learnings after each task and delivers efficient AI coding assistance through hierarchical memory management.

all ComfyUI http/ws APIs. support NodeJS / Browser environments. and advanced programmable workflow.

A Complete Guide to Fine-tuning Qwen2.5-Coder for Chinese Sentiment Analysis

SNDR Core Engine (Genesis) — vLLM runtime patch-overlay for Qwen3.6 + Gemma4 on consumer NVIDIA (Ampere sm_86, 2× A5000/3090). Qwen3.6-35B-A3B FP8 ~240 tok/s, 27B-int4 hybrid GDN+Mamba, Gemma4 26B/31B AWQ, 256K ctx. 321 patches: TurboQuant k8v4 KV, MTP/DFlash spec-decode, FULL cudagraph, hybrid GDN. vLLM pin dev424 + Control Center GUI.

nano-vllm是开源的一个gpu推理项目，基于开源版本弄的一个ascend npu版本推理小demo，旨在帮助初学者了解推理的整体流程，区别于vllm，nano-vllm体量更小，麻雀虽小五脏俱全，更有助于初学者学习。

Practical local LLM recipes and benchmarks for RTX 5060 Ti setups

Local-first Telegram AI bot with Ollama tool calling, voice transcription, MinIO storage, SearchApi web search, and readiness checks

Real-time two-way voice translator for VRChat — LLM-based, VR subtitle overlay & OSC

Real-time speech-to-text WebSocket server with pluggable ASR backends, energy-based VAD, streaming partial results, and Prometheus observability.

A private Claude-Code-style coding agent for Apple Silicon — run chat, code, and local model workflows on-device. MLX-native, Ollama/OpenAI API compatible, zero API keys.

Local Qwen 3.8 27B uncensored Q4_K_M + harvested SYSTEM pack. Official 3.8 weights, not a 3.6 retitle.

An LLM training framework built from the ground up, featuring a custom BumbleBee architecture and end-to-end support for multiple open-source models across Pretraining → SFT → RLHF/DPO.

顺便一提，我们支持 RWKV | 「Intel 2025 人工智能创新大赛」🚀AutoOPS: Provide the chaos brought by language models to the operation and maintenance industry! 🏆使用 LLM 提供的动力实现全自动运维，支持 Windows Server/Linux/macOS/Cisco IOS，可进行全网自动管理，让我们颠覆运维行业【带外管理/自动运维/IoT设备管理/WebHook监控/任意平台/全模态Workflow】

🚀 Easy, open-source LLM finetuning with one-line commands, seamless cloud integration, and popular optimization frameworks. ✨

Hand-written NVFP4 W4A16 CUDA kernels for Volta

2026 年编程导航 AI 编程实战新项目，基于 Taro + React + FastAPI + DeepSeek 的 AI 闯关学习小程序，支持一句话 / 文本主题 AI 出题、闯关答题与即时讲解、联网搜索增强、RAG 私有知识库出题、AI 生图配图、微信登录与通关复盘报告。覆盖 LangChain / LangGraph、Chroma 向量库、MySQL、JWT、腾讯云 COS、Tavily 联网搜索、阿里云百炼、微信小程序与云托管。用一套教程掌握 AI 编程全流程，从需求调研到部署上线，不到一周学完，给你的简历增加竞争力

WordNest🎯 是一个基于Flask的个性化英语单词学习系统，专为解决传统背单词软件的痛点而设计。它通过仅收录用户手动添加的生词，告别海量词库的无效重复学习；调用大模型实现AI智能例句生成与记忆技巧辅助，并构建词汇知识图谱，以可视化关联提升记忆效率。

Diktafon is a private, open-source voice memo app that transcribes and summarizes your recordings entirely on your device — organized like cassette tapes.