qwen2-5

Local CLI Copilot, powered by Ollama. 💻🦙

Deploy open-source LLMs on AWS in minutes — with OpenAI-compatible APIs and a powerful CLI/SDK toolkit.

Hand-derived memory-efficient VJPs for tuning LLMs on laptops.

Simple RAG system powered by Milvus.

vLLM tool parser for Qwen2.5-Coder models using <tools> tag format.

Distributed Inference with vLLM

ArtSeek: Deep artwork understanding via multimodal in-context reasoning and late interaction retrieval

Чат-бот с LLL + RAG

面向 A 股投研，针对分析时效差、逻辑不全及数据难量化痛点，自主构建以 Qwen2.5-72B-AWQ 为核心的全链路自动化投研系统。利用 LangGraph 编排多智能体协作流，融合 LoRA 垂直微调、MCP 工具链与 CoT+ReAct 架构，实现从行情舆情实时采集、产业链知识图谱多维推演到 Reflexion 反思审核的投研全闭环，每日 9:00 定时产出机构级专业研报推送飞书，显著提升投研决策自动化水平。