app.py

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

# Load fine-tuned model from Hugging Face
model_name = "syedmoinms/MoinRomanticBot"  # ✅ Tumhara sahi model path

try:
    tokenizer = AutoTokenizer.from_pretrained(model_name)
    model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.float16, device_map="auto")
except Exception as e:
    print(f"❌ Error loading model: {e}")
    exit()

# Function to generate response
def chatbot(input_text):
    inputs = tokenizer(input_text, return_tensors="pt").to("cuda" if torch.cuda.is_available() else "cpu")
    
    with torch.no_grad():
        outputs = model.generate(**inputs, max_length=150)
    
    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
    
    return response

# Gradio interface
iface = gr.Interface(fn=chatbot, inputs="text", outputs="text", title="Moin Romantic Bot")

# Launch app
if __name__ == "__main__":
    iface.launch(server_name="0.0.0.0", server_port=7860)