app.py

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

# Load Gemma 27B Model
model_name = "gemma-ai/gemma-27b"  # Replace with correct model name from Hugging Face
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name, torch_dtype=torch.float16, device_map="auto"
)

# Function to generate response
def generate_response(prompt):
    inputs = tokenizer(prompt, return_tensors="pt").to("cuda")
    output = model.generate(**inputs, max_length=200)
    return tokenizer.decode(output[0], skip_special_tokens=True)

# Gradio Interface
iface = gr.Interface(
    fn=generate_response,
    inputs=gr.Textbox(label="Enter your prompt"),
    outputs=gr.Textbox(label="Gemma 27B Response"),
    title="Gemma 27B Chatbot",
    description="Ask Gemma anything!"
)

# Launch the app
iface.launch()