0% found this document useful (0 votes)
7 views2 pages

GPT-2 Text Generation Python Script

Uploaded by

jyothikaa2006
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
0% found this document useful (0 votes)
7 views2 pages

GPT-2 Text Generation Python Script

Uploaded by

jyothikaa2006
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd

Program :

# Install transformers if not already installed


# !pip install transformers

from transformers import GPT2LMHeadModel, GPT2Tokenizer


import torch

# Load pre-trained GPT-2 model and tokenizer


model_name = "gpt2" # small GPT-2
tokenizer = GPT2Tokenizer.from_pretrained(model_name)
model = GPT2LMHeadModel.from_pretrained(model_name)

# Set padding token to eos_token to avoid warnings


tokenizer.pad_token = tokenizer.eos_token

# Function to generate text


def generate_text(prompt, max_length=100):
# Encode prompt
input_ids = [Link](prompt, return_tensors='pt')

# Generate text with proper padding and attention mask


output = [Link](
input_ids,
max_length=max_length,
num_return_sequences=1,
do_sample=True,
top_k=50,
top_p=0.95,
temperature=0.7,
pad_token_id=tokenizer.eos_token_id, # avoids warning
attention_mask=torch.ones_like(input_ids) # correct attention mask
)

# Decode generated text


generated_text = [Link](output[0], skip_special_tokens=True)
return generated_text
# --- User Interaction ---
print("=== Generative AI Text Generator ===")
user_prompt = input("Enter a prompt: ")
generated = generate_text(user_prompt, max_length=100)

# Display output
print("\nPrompt:", user_prompt)
print("Generated Text:\n", generated)

Output:

=== Generative AI Text Generator ===


Enter a prompt: Artificial Intelligence is transforming

Prompt: Artificial Intelligence is transforming


Generated Text:
Artificial Intelligence is transforming the way we work, and it is doing so with the help of
some of the most promising AI technologies in the business.

This year's conference saw the creation of two new AI technologies, and the world's first 'Real-
Time Machine' to learn from real-time data.

The AI program is called 'Reverse Recursion', which uses a machine learning algorithm to
build a simple algorithm to extract information about a specific event in real time.

You might also like