|
|
--- |
|
|
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 |
|
|
--- |
|
|
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
|
|
# 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 |
|
|
|
|
|
```markdown |
|
|
### Human: If you are a doctor, please answer the medical questions based on the patient's description. |
|
|
|
|
|
### Patient's Description: {symptoms} |
|
|
### Assistant: "" |
|
|
|
