Update app.py

app.py

@@ -1,10 +1,13 @@
 import gradio as gr
 from transformers import pipeline
+import torch
+
+device = 0 if torch.cuda.is_available() else -1
+pipe = pipeline("text-generation", model="TinyLlama/TinyLlama-1.1B-Chat-v1.0", device=device)
 
-pipe = pipeline("text-generation", model="TinyLlama/TinyLlama-1.1B-Chat-v1.0", device=-1)
 
 def responder(prompt):
-    respuesta = pipe(prompt, max_new_tokens=300, do_sample=True, temperature=0.7)[0]['generated_text']
+    respuesta = pipe(prompt, max_new_tokens=80, do_sample=True, temperature=0.7)[0]['generated_text']
     return respuesta
 
 with gr.Blocks() as demo: