UVA-MSBA/M4-Team12-2024

widget: - text: "I never imagined a pill could cause so much pain. It started with a dull ache, then my muscles felt like they were on fire. Breathing became a struggle, each breath felt like a battle. It's terrifying how quickly things can change when you least expect it."

This model takes text (narrative of reasctions to medications) as input and returns a predicted severity score for the reaction (LABEL_1 is severe reaction). Please do NOT use for medical diagnosis. Example usage:

import torch
import tensorflow as tf
from transformers import RobertaTokenizer, RobertaModel
from transformers import AutoModelForSequenceClassification
from transformers import TFAutoModelForSequenceClassification
from transformers import AutoTokenizer

tokenizer = AutoTokenizer.from_pretrained("UVA-MSBA/Mod4_T12")  
model = AutoModelForSequenceClassification.from_pretrained("UVA-MSBA/Mod4_T12")

def adr_predict(x):
    encoded_input = tokenizer(x, return_tensors='pt')
    output = model(**encoded_input)
    scores = output[0][0].detach().numpy()
    scores = tf.nn.softmax(scores)
    return scores.numpy()[1]

sentence = "I have an extremely bad headache."

adr_predict(sentence)