geenrate.py

import torch
from transformers import GPT2Tokenizer, GPT2LMHeadModel

# Load the tokenizer and model
tokenizer = GPT2Tokenizer.from_pretrained('gpt2')
model = GPT2LMHeadModel.from_pretrained('./results')

# Set the device to GPU if available, otherwise use CPU
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
model.to(device)

# Generate some text
prompt = 'Once upon a time'
input_ids = tokenizer.encode(prompt, return_tensors='pt').to(device)
output = model.generate(input_ids=input_ids, max_length=100, do_sample=True, temperature=0.7)
generated_text = tokenizer.decode(output[0], skip_special_tokens=True)

print(generated_text)