app.py

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

# Cargar modelo Qwen2.5
model_name = "Qwen/Qwen1.5-0.5B"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.float32)

# Función de respuesta
def chat(message):
    inputs = tokenizer(message, return_tensors="pt")
    output = model.generate(**inputs, max_new_tokens=50)
    return tokenizer.decode(output[0], skip_special_tokens=True)

# Interfaz Gradio
iface = gr.Interface(fn=chat, inputs="text", outputs="text", title="Chat con Qwen2.5")
iface.launch()