Update app.py

app.py

@@ -6,11 +6,11 @@ import os
 IS_SPACES_ZERO = os.environ.get("SPACES_ZERO_GPU", "0") == "1"
 IS_SPACE = os.environ.get("SPACE_ID", None) is not None
 
-#device = "cuda" if torch.cuda.is_available() else "cpu"
+device = "cuda" if torch.cuda.is_available() else "cpu"
 #device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
 #dtype = torch.float16
 LOW_MEMORY = os.getenv("LOW_MEMORY", "0") == "1"
-#print(f"Using device: {device}")
+print(f"Using device: {device}")
 #print(f"Using dtype: {dtype}")
 print(f"low memory: {LOW_MEMORY}")
 
@@ -18,7 +18,7 @@ device = "cuda"
 model_name = "ruslanmv/Medical-Llama3-8B"
 # Move model and tokenizer to the CUDA device
 model = AutoModelForCausalLM.from_pretrained(model_name).to(device)
-tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True).to(device)
+tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
 tokenizer.pad_token = tokenizer.eos_token
 
 @spaces.GPU