Ecosyste.ms: Awesome

An open API service indexing awesome lists of open source software.

Awesome Lists | Featured Topics | Projects

https://github.com/echosingh/menstrual-health-awareness-model

Menstrual Health Guide Model
https://github.com/echosingh/menstrual-health-awareness-model

chat-model huggingface jupyter-notebook menstrual-health

Last synced: 9 days ago
JSON representation

Menstrual Health Guide Model

Awesome Lists containing this project

README 

        
# Menstrual Health Awareness Model



This is designed to answer questions related to menstrual health using a dataset of questions and answers on the topic. 

## you can use my trained model link :-

[Link](https://huggingface.co/adi2606/Menstrual-Health-Awareness-Chatbot)

## Model Use Guide

```python

from transformers import AutoTokenizer, AutoModelForSeq2SeqLM



# Load the tokenizer and model

tokenizer = AutoTokenizer.from_pretrained("adi2606/Menstrual-Health-Awareness-Chatbot")

model = AutoModelForSeq2SeqLM.from_pretrained("adi2606/Menstrual-Health-Awareness-Chatbot")



# Function to generate a response from the chatbot

def generate_response(input_text):

    # Tokenize the input text

    inputs = tokenizer(input_text, return_tensors="pt")



    # Generate the output (the response)

    outputs = model.generate(**inputs)



    # Decode the output back to text

    response = tokenizer.decode(outputs[0], skip_special_tokens=True)

    return response



# Example usage

input_text = "What are the symptoms of PMS?"

response = generate_response(input_text)

print(response)

```



### Model Description



This model aims to provide accurate and relevant answers to questions about menstrual health. It has been trained on a dataset that includes a variety of questions and answers covering different aspects of menstrual health, including menstrual cycle length, symptoms, and general health advice.



- **Model type:** Sequence-to-sequence language model

- **Language(s) (NLP):** English

- **License:** MIT



## Uses



### Direct Use



The model can be used to answer questions related to menstrual health. Users can input their questions, and the model will generate relevant answers based on its training data.



### Out-of-Scope Use



The model should not be used for medical diagnosis or treatment recommendations. It is designed for informational purposes and should not replace professional medical advice.



## Bias, Risks, and Limitations



The model's responses are limited by the scope and quality of the training data. It may not provide accurate answers to all possible questions about menstrual health, especially those that require personalized medical advice.



### Recommendations



Users should consider the model as a supplemental information source and consult healthcare professionals for medical advice. Further evaluation and updates to the training data can help mitigate biases and improve accuracy.



## Training Details

Training Data

The model was trained on the Menstrual Health Awareness Dataset, which includes questions and answers related to menstrual health.



Training Procedure



Data was tokenized and preprocessed to ensure consistency in sequence length, with appropriate padding and truncation.



Training Hyperparameters

Training regime: fp32 mixed precision

Learning rate: 2e-5

Batch size: 16

Epochs: 3

Weight decay: 0.01



## Evaluation

Testing Data, Factors & Metrics

Testing Data

The model was evaluated on a test split of the Menstrual Health Awareness Dataset.



## Factors

The evaluation considered the accuracy and relevance of the answers generated by the model.



## Metrics

Accuracy: The percentage of correct answers generated by the model.

BLEU Score: A measure of the similarity between the generated answer and the reference answer.

Results

## Summary

The model achieved an accuracy of 85% and a BLEU score of 70 on the test dataset, indicating a high level of relevance and correctness in its responses.

## Environmental Impact

Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).



Hardware Type: NVIDIA Tesla V100

Cloud Provider: Google Cloud

Compute Region: us-central1

Carbon Emitted: 15 kg CO2eq (estimated)

## Compute Infrastructure

Hardware

GPU: NVIDIA Tesla V100

Software

Framework: Transformers library by Hugging Face

Python Version: 3.8