blank10111/medibot

This model is fine-tuned on the Wiki Medical Terms dataset using QLoRA.

Model Details

• Base Model: Llama 2 (aboonaji/llama2finetune-v2)
• Fine-Tuning Method: QLoRA (8-bit quantization with Low-Rank Adaptation)
• Dataset: Wiki Medical Terms
• Training Epochs: 3
• Evaluation Loss: ~0.94
• Perplexity: ~2.57

Intended Use

This model is designed for generating and explaining medical terms. It may be useful for educational purposes or as a starting point for domain-specific applications.