Update app.py

app.py

@@ -18,7 +18,7 @@ os.environ['PYTORCH_CUDA_ALLOC_CONF'] = 'max_split_size_mb:30'
 device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
 
 tokenizer = AutoTokenizer.from_pretrained('intfloat/e5-mistral-7b-instruct')
-model = AutoModel.from_pretrained('intfloat/e5-mistral-7b-instruct', torch_dtype="auto", device_map=device)
+model = AutoModel.from_pretrained('intfloat/e5-mistral-7b-instruct', torch_dtype=torch.float16, device_map=device)
 # model.half()
 # model.to(device)