Update app.py

app.py

@@ -12,14 +12,14 @@ def get_device():
 model_name = "microsoft/Phi-3-mini-128k-instruct"
 
 tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
-model = AutoModelForCausalLM.from_pretrained(model_name, trust_remote_code=True)
+model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, trust_remote_code=True)
 
 # Obtener el dispositivo adecuado según la disponibilidad de GPU
 device = get_device()
 model.to(device)
-model = torch.quantization.quantize_dynamic(
-    model, {torch.nn.Linear}, dtype=torch.qint8
-)
+#model = torch.quantization.quantize_dynamic(
+#    model, {torch.nn.Linear}, dtype=torch.qint8
+#)
 
 pipeline = transformers.pipeline(
     "text-generation",