metadata

license: apache-2.0
version: 0.0.2
base_model: Mistral-7B-Instruct-v0.1
tags:
  - fine-tuned
  - healthcare
model-index:
  - name: WellnessWhiz
    results: []
language:
  - en
library_name: transformers

Model Card Description

Model Description

The model is designed to generate a line of treatment and diagnosis in response to a given prompt of symptoms. It essentially serves as a tool to assist in medical scenario simulations or provide initial guidance based on presented symptoms.

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 0.0002
train_batch_size: 8
eval_batch_size: 8
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
training_steps: 8000
mixed_precision_training: Native AMP

Framework versions

Transformers 4.35.0.dev0
Pytorch 2.1.0+cu118
Datasets 2.14.6
Tokenizers 0.14.1

Prompt Template

### Human: If you are a doctor, please answer the medical questions based on the patient's description.

### Patient's Description: {symptoms}
### Assistant: ""