Glccampos/llm_qween

Qwen Q&A LoRA Adapter

This repository contains a LoRA adapter fine-tuned for question answering.

Base Model

Qwen/Qwen2.5-0.5B-Instruct

Training Data

squad formatted as context-question-answer chat examples.

MLflow

The adapter files and Hugging Face repo URL are also logged in MLflow under experiment qwen_qa_lora_cpu.

Usage

Load this adapter with peft.PeftModel.from_pretrained on top of the base model.