melisar2/pharmassist-flan-t5-small

Model Card for Model ID

Model Details

Model Description

This model is a fine-tuned version of google/flan-t5-small designed for medication-related question answering. The model was fine-tuned using a medication details dataset formatted as instruction-response examples. The goal of the model is to generate short educational responses to medication questions, such as what a medication is used for or what side effects may be associated with it.

This model was created for an academic final project and is intended for educational demonstration only. It should not be used as medical advice or as a replacement for a pharmacist, physician, or official drug information source.

This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.

• Developed by: [More Information Needed]
• Funded by [optional]: [More Information Needed]
• Shared by [optional]: [More Information Needed]
• Model type: [More Information Needed]
• Language(s) (NLP): [More Information Needed]
• License: [More Information Needed]
• Finetuned from model [optional]: [More Information Needed]

Model Sources [optional]

• Repository: [More Information Needed]
• Paper [optional]: [More Information Needed]
• Demo [optional]: [More Information Needed]

Uses

This model can be used to generate short educational answers to basic medication-related questions. Example questions include:

• What is Metformin used for?
• What are the side effects of Ibuprofen?
• What is Atorvastatin used for?

The model is intended for demonstration and learning purposes.

Direct Use

[More Information Needed]

Downstream Use [optional]

[More Information Needed]

Out-of-Scope Use

This model should not be used for diagnosis, treatment decisions, medication selection, dosing recommendations, emergency medical questions, or professional clinical decision-making. It should not replace official drug references or advice from licensed healthcare professionals.

[More Information Needed]

Bias, Risks, and Limitations

This model has several limitations. It was fine-tuned on a limited medication dataset and may generate incomplete, outdated, or incorrect information. The model does not verify answers against current clinical guidelines, drug databases, patient-specific information, allergies, medical history, or drug interactions. Users should verify all medication information with a pharmacist, physician, or official drug reference.

[More Information Needed]

Recommendations

Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.

How to Get Started with the Model

from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

model_id = "melisar2/pharmassist-flan-t5-small"

tokenizer = AutoTokenizer.from_pretrained(model_id) model = AutoModelForSeq2SeqLM.from_pretrained(model_id)

question = "What is Metformin used for?"

inputs = tokenizer(question, return_tensors="pt", truncation=True) outputs = model.generate( **inputs, max_new_tokens=80, num_beams=4 )

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

[More Information Needed]

Training Details

Training Data

The model was fine-tuned using the Medicine_Details.csv dataset. The dataset contains medication-related information and was formatted into instruction-response examples for training. The project used fields such as medication name, uses, and side effects to create medication question-answering prompts. https://www.kaggle.com/datasets/swathigunti/medicine-details-csv [More Information Needed]

Training Procedure

Preprocessing [optional]

[More Information Needed]

Training Hyperparameters

• Training regime: [More Information Needed]

Speeds, Sizes, Times [optional]

[More Information Needed]

Evaluation

ROUGE scores were used to compare the model-generated answers with the expected reference answers. ROUGE is appropriate for this project because the task is text generation, and the evaluation compares generated text to target medication-related responses. ROUGE Scores: ROUGE1: F-measure: 0.4037 Precision: 0.4806 Recall: 0.3996 ROUGE2: F-measure: 0.2646 Precision: 0.3011 Recall: 0.2684 ROUGEL: F-measure: 0.3837 Precision: 0.4520 Recall: 0.3815

Testing Data, Factors & Metrics

Testing Data

[More Information Needed]

Factors

[More Information Needed]

Metrics

[More Information Needed]

Results

[More Information Needed]

Summary

Model Examination [optional]

[More Information Needed]

Environmental Impact

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

• Hardware Type: [More Information Needed]
• Hours used: [More Information Needed]
• Cloud Provider: [More Information Needed]
• Compute Region: [More Information Needed]
• Carbon Emitted: [More Information Needed]

Technical Specifications [optional]

Model Architecture and Objective

[More Information Needed]

Compute Infrastructure

[More Information Needed]

Hardware

[More Information Needed]

Software

[More Information Needed]

Citation [optional]

BibTeX:

[More Information Needed]

APA:

[More Information Needed]

Glossary [optional]

[More Information Needed]

More Information [optional]

[More Information Needed]

Model Card Authors [optional]

[More Information Needed]

Model Card Contact

[More Information Needed]