---
library_name: transformers
tags: []
---

# Model Card for Gemma Pharmacy💊

<!-- Provide a quick summary of what the model is/does. -->



## Model Details

### Model Description

<!-- Provide a longer summary of what this model is. -->

Gemma Pharmacy helps users find the best OTC medication for common symptoms such as headaches, indigestion, and more. The model was fine-tuned on a dataset that includes detailed medication information, making it an effective tool for anyone looking to manage their health by selecting the right medication. Users benefit from quick access to critical medication details, including side effects and dosage guidelines. 🤗 

- **Developed by:** Sooyeon Jang, Noa Jeong
- **Shared by:** Sooyeon Jang, Noa Jeong
- **Model type:** Transformer-based model for symptom-to-medication recommendation
- **Language(s) (NLP):** Korean
- **Finetuned from model:** Hugging Face Gemma model

### Model Sources [optional]

<!-- Provide the basic links for the model. -->

- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]

## Uses

<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->

### Direct Use

<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->

This model can be used directly by users looking to identify OTC medications based on their symptoms.

### Downstream Use

<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->

Fine-tuning on specific symptoms, expanding to more languages, or integrating into health applications.

### Out-of-Scope Use

<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->

Not intended for use in critical medical diagnoses or treatment suggestions where professional healthcare advice is necessary.

## Bias, Risks, and Limitations

<!-- This section is meant to convey both technical and sociotechnical limitations. -->

This model was fine-tuned on a Korean medication dataset and may not generalize well to non-Korean OTC medications or medical contexts. Additionally, the model’s recommendations should not be considered as professional medical advice, and users should always consult a healthcare provider.

### Recommendations

<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->

Users should cross-check the recommendations provided by the model with certified medical professionals, especially in cases of serious symptoms or chronic conditions.

## How to Get Started with the Model

Use the code below to get started with the model.

```
from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline

model_name = "gemmagemma/gemma-pharmacy"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name)
```

## Training Details

### Training Data

<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->

The 'e약은요' dataset contains information on OTC medications, including their efficacy, usage methods, and side effects. This dataset was used to fine-tune the Gemma Pharmacy model.
- **Dataset:** https://www.data.go.kr/data/15075057/openapi.do#/tab_layer_detail_function


### Training Procedure

<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->


#### Training Hyperparameters

- **Training regime:** fp16 mixed precision <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->


## Evaluation

<!-- This section describes the evaluation protocols and provides the results. -->


### Results

The model achieves strong performance in predicting correct medications based on symptoms, particularly for common conditions such as headaches and indigestion.



## Environmental Impact

<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->

Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).

- **Hardware Type:** Nvidia GPU

## Technical Specifications

### Model Architecture and Objective

The model is based on a transformer architecture with the objective of symptom-to-medication recommendation.