Update app.py

app.py

@@ -59,7 +59,6 @@ if not torch.cuda.is_available():
 
 if torch.cuda.is_available():
     device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
-    print(device)
 
 HF_TOKEN = os.environ.get("HF_TOKEN", None)
 CHECKPOINT_URL = "Salesforce/codegen-350M-mono"
@@ -184,7 +183,7 @@ def generate(
     # model.to(device)
     input_ids = tokenizer(prompt, return_tensors="pt").to(model.device)
     # generated_ids = model.generate(**input_ids
-    generated_ids = model.generate(**input_ids, **generate_kwargs)
+    generated_ids = model.generate(**input_ids)#, **generate_kwargs)
     
     return tokenizer.decode(generated_ids[0][input_ids["input_ids"].shape[1]:], skip_special_tokens=True).strip()