This repository provides a GGUF quantized version of a Qwen2-based coding assistant model for local inference. It is intended to support code-focused questions in a repository-grounded setting.

This repository contains a quantized GGUF model for inference. The corresponding LoRA adapter repository contains the adapter weights and configuration used during fine-tuning. The adapter was built on top of Qwen/Qwen2.5-Coder-7B-Instruct with LoRA rank 16, alpha 16, dropout 0.05, targeting q_proj, k_proj, v_proj, and o_proj.