vLLM tool parser for Qwen2.5-Coder models using <tools> tag format.
-
Updated
Apr 29, 2026 - Python
#
qwen2-5-coder
Here are 6 public repositories matching this topic...
Fine-tuning Qwen2.5-Coder-0.5B LLM using QLoRA (4-bit quantization + LoRA) to generate clear, concise commit messages from Git diffs by learning to summarize code changes into human-like descriptions.
nlp transformers pytorch lora git-diff peft code-summarization llm qlora commit-message-generation qwen2-5-coder
-
Updated
Feb 22, 2026 - Python
A log parser that use local llm to explain log lines in plain english.
-
Updated
May 23, 2026 - Python
🚀 Tabby server with Vulkan/AMD iGPU acceleration on Docker. Optimized for AMD Ryzen APU (5800H/UMA) with automated model/binary setup. Fixed "Read-only file system" & ICD issues.
docker-compose vulkan self-hosted amdgpu igpu amd-gpu tabby gguf llm-interface ai-coding-assistant qwen2-5-coder tabby-ml tabby-vulkan
-
Updated
Apr 29, 2026
AI-агент для генерации Lua-кода | Ollama + RAG + Sandbox | bogomol team | MTS True Tech Hack 2026
react sqlalchemy docker-compose postgresql fastapi llm langchain chromadb ollama langgraph qwen2-5-coder hackaton2026
-
Updated
Apr 25, 2026 - Python
Minimalist & powerful CLI for local AI programming. Seamlessly interact with Ollama models for code generation, one-shot prompts, and Unix pipes. No fluff, no tool injection—just pure local sovereignty.
python cli automation developer-tools code-generation minimalism local-llm ollama ai-productivity qwen2-5-coder
-
Updated
May 22, 2026 - Python
Improve this page
Add a description, image, and links to the qwen2-5-coder topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the qwen2-5-coder topic, visit your repo's landing page and select "manage topics."