sleepy-panda21/Llama_fine_tuned

Fine-Tuned AI Counseling Assistant

This repository contains the LoRA adapter weights fine-tuned on top of Qwen2.5-7B-Instruct.

Model Description

This model has been specifically fine-tuned to act as a supportive, empathetic, and non-judgmental conversational assistant. It focuses on validating emotions, processing stress or academic overwhelm, and maintaining supportive therapeutic pacing.

• Trained with: Unsloth & PEFT
• Framework: QLoRA (4-bit quantization)
• Language: English