app.py

import gradio as gr
from transformers import pipeline, GPT2LMHeadModel, GPT2Tokenizer
import os

# Define your model details
HF_TOKEN = os.getenv("HF_TOKEN")
model_name = "Jonathanmann/GPT2-medium-SADnov21"

# Load tokenizer and model from Hugging Face with error handling
try:
    tokenizer = GPT2Tokenizer.from_pretrained(model_name, use_auth_token=HF_TOKEN)
    model = GPT2LMHeadModel.from_pretrained(model_name, use_auth_token=HF_TOKEN)
except Exception as e:
    raise RuntimeError(f"Error loading model or tokenizer: {e}")

# Define the text generation pipeline with error handling
try:
    generator = pipeline("text-generation", model=model, tokenizer=tokenizer)
except Exception as e:
    raise RuntimeError(f"Error creating text generation pipeline: {e}")

# Define a function for generating text with error handling
def generate_text(prompt, max_length, temperature, top_k, top_p):
    try:
        response = generator(
            prompt,
            max_length=max_length,
            temperature=temperature,
            top_k=top_k,
            top_p=top_p,
            num_return_sequences=1
        )
        return response[0]["generated_text"]
    except Exception as e:
        return f"An error occurred during text generation: {str(e)}"

# Create the Gradio interface
demo = gr.Interface(
    fn=generate_text,
    inputs=[
        gr.Textbox(lines=2, placeholder="Enter your prompt here..."),
        gr.Slider(minimum=20, maximum=200, value=50, label="Max Length"),
        gr.Slider(minimum=0.1, maximum=1.0, value=0.7, label="Temperature"),
        gr.Slider(minimum=1, maximum=100, value=50, label="Top-k"),
        gr.Slider(minimum=0.1, maximum=1.0, value=0.9, label="Top-p")
    ],
    outputs="text",
    title="GPT-2 Text Generation",
    description="A demo of Jonathanmann/GPT2-medium-SADnov21 with adjustable generation parameters."
)

# Launch the app with error handling
try:
    demo.launch()
except Exception as e:
    print(f"An error occurred while launching the Gradio interface: {str(e)}")