app.py

import gradio as gr
from transformers import AutoTokenizer, AutoModelForCausalLM
import torch
import spaces
# Load the model and tokenizer
tokenizer = AutoTokenizer.from_pretrained("Yoxas/autotrain-tinyllama-statistical")
model = AutoModelForCausalLM.from_pretrained("Yoxas/autotrain-tinyllama-statistical")
@spaces.GPU(duration=120)
def chatbot_response(input_text, max_length, temperature):
    inputs = tokenizer(input_text, return_tensors="pt", padding=True)
    attention_mask = inputs.attention_mask
    outputs = model.generate(
        inputs['input_ids'],
        attention_mask=attention_mask,
        max_length=max_length,
        temperature=temperature,
        do_sample=True,
        pad_token_id=tokenizer.eos_token_id
    )
    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
    return response

# Create the Gradio interface
inputs = [
    gr.Textbox(lines=2, placeholder="Enter your message here..."),
    gr.Slider(minimum=10, maximum=512, value=50, label="Max Length"),
    gr.Slider(minimum=0.1, maximum=1.0, value=0.7, label="Temperature")
]

outputs = gr.Textbox()

interface = gr.Interface(fn=chatbot_response, inputs=inputs, outputs=outputs, title="Simple Chatbot")

# Launch the interface
interface.launch()