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

# Load the tokenizer and model from Hugging Face Model Hub
model_name = "Arielasgas/javahh"

tokenizer = AutoTokenizer.from_pretrained(model_name, use_fast=True)
model = AutoModelForCausalLM.from_pretrained(model_name)

# Define the function to process user input
def generate_response(input_text):
    inputs = tokenizer(input_text, return_tensors="pt")
    
    # Generate a response from the model
    with torch.no_grad():
        outputs = model.generate(inputs['input_ids'], max_length=100, num_return_sequences=1)
    
    # Decode the generated response
    generated_text = tokenizer.decode(outputs[0], skip_special_tokens=True)
    
    return generated_text

# Define the Gradio interface
iface = gr.Interface(
    fn=generate_response,  # Function to be called with user input
    inputs=gr.Textbox(label="Enter your text"),  # Input component (Textbox for user input)
    outputs=gr.Textbox(label="Generated response")  # Output component (Textbox to show response)
)

# Launch the Gradio interface
iface.launch()