app.py

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

# Nome do modelo carregado no Hugging Face
MODEL_NAME = "mistralai/Mixtral-8x7B-v0.1"

# Carregar o tokenizer e o modelo Mixtral
tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)
model = AutoModelForCausalLM.from_pretrained(
    MODEL_NAME, torch_dtype=torch.float16, device_map="auto"
)

# Função para processar as mensagens do usuário
def chat(input_text):
    inputs = tokenizer(input_text, return_tensors="pt").to("cuda")
    outputs = model.generate(**inputs, max_new_tokens=200)
    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
    return response

# Criar interface no Gradio
iface = gr.Interface(
    fn=chat,
    inputs="text",
    outputs="text",
    title="Assistente Virtual Mixtral",
    description="Converse com o assistente baseado no modelo Mixtral 8x7B",
)

# Executar o chatbot
iface.launch()