ahmadmirza17/medical_finetuned_qna

Uploaded model

• Developed by: ahmadmirza17
• License: apache-2.0
• Finetuned from model : merged_model

This mistral model was trained 2x faster with Unsloth and Huggingface's TRL library.

Model was intially a Mistral 7b, conducted continual pre-training on medical-specific pdf content and then QnA finetuned for more defined conversation response.