fine_tune_gpt2_medquad.py

import pandas as pd
from transformers import GPT2LMHeadModel, GPT2Tokenizer, Trainer, TrainingArguments
from datasets import load_dataset

# Load MedQuAD dataset
dataset = load_dataset("marianeft/MedQuAD", split="train")

# Load the GPT-2 model and tokenizer
model_name = "gpt2"  # Or use a medical fine-tuned model
model = GPT2LMHeadModel.from_pretrained(model_name)
tokenizer = GPT2Tokenizer.from_pretrained(model_name)

# Preprocess the dataset
def preprocess(example):
    return {"text": f"{example['question']} {example['answer']}"}

dataset = dataset.map(preprocess)

# Tokenize the dataset
def tokenize_function(examples):
    return tokenizer(examples["text"], padding="max_length", truncation=True, max_length=512)

tokenized_datasets = dataset.map(tokenize_function, batched=True)

# Training arguments
training_args = TrainingArguments(
    output_dir="./results",
    num_train_epochs=1,
    per_device_train_batch_size=4,
    save_steps=10_000,
    save_total_limit=2,
    logging_dir="./logs",
)

# Initialize Trainer
trainer = Trainer(
    model=model,
    args=training_args,
    train_dataset=tokenized_datasets,
)

# Fine-tune the model
trainer.train()

# Save the model to a new directory
model.save_pretrained("fine_tuned_medquad")
tokenizer.save_pretrained("fine_tuned_medquad")