app.py

import gradio as gr
from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline

# Load the finetuned model and tokenizer from Hugging Face Model Hub
model_path = "sagar007/phi3.5_finetune"
tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, device_map="auto")

# Create a text-generation pipeline
generator = pipeline("text-generation", model=model, tokenizer=tokenizer)

def generate_text(prompt, max_length=100, temperature=0.7):
    """Generate text based on the input prompt."""
    generated = generator(prompt, max_length=max_length, temperature=temperature, num_return_sequences=1)
    return generated[0]['generated_text']

# Create the Gradio interface
iface = gr.Interface(
    fn=generate_text,
    inputs=[
        gr.Textbox(lines=5, label="Enter your prompt"),
        gr.Slider(minimum=50, maximum=500, value=100, step=10, label="Max Length"),
        gr.Slider(minimum=0.1, maximum=1.0, value=0.7, step=0.1, label="Temperature"),
    ],
    outputs=gr.Textbox(lines=10, label="Generated Text"),
    title="Finetuned Phi-3.5 Text Generation",
    description="Enter a prompt and generate text using the finetuned Phi-3.5 model.",
)

# Launch the app
iface.launch()