henil164/mistral-7b-medlexfin

Mistral 7B Fine-tuned on Medical, Legal & Finance Data

Model Description

This model is a fine-tuned version of Mistral-7B-v0.1 on a combined dataset of:

• 🏥 Medical QA (MedMCQA)
• ⚖️ Legal QA (Legal-QA-v1)
• 💰 Finance Sentiment (FinGPT)

Training Details

• Base model: mistralai/Mistral-7B-v0.1
• Fine-tuning method: QLoRA (4-bit quantization)
• Dataset size: 9,742 samples
• Epochs: 3 (~10 Hours)
• Hardware: Google Colab T4 GPU

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("your-username/mistral-7b-medlexfin")
tokenizer = AutoTokenizer.from_pretrained("your-username/mistral-7b-medlexfin")

Domains

• Medical question answering
• Legal advice and explanation
• Financial sentiment analysis