Update app.py

app.py

@@ -16,7 +16,7 @@ modelName = "bartowski/Mistral-Nemo-Instruct-2407-GGUF"
 modelId = "Mistral-Nemo-Instruct-2407-Q2_K.gguf"
 tokenizer = AutoTokenizer.from_pretrained(modelName,gguf_file=modelId)
 
-model = AutoModel.from_pretrained(modelName,gguf_file=modelId)
+model = AutoModel.from_pretrained(modelName,gguf_file=modelId,torch_dtype=torch.float16)
 #model = AutoModelForCausalLM.from_pretrained("google/gemma-2-2b-it", torch_dtype=torch.float16 )
 #stvlynn/Gemma-2-2b-Chinese-it
 #tokenizer = AutoTokenizer.from_pretrained("microsoft/DialoGPT-large")