Update app.py

app.py

@@ -60,7 +60,7 @@ model = AutoModelForCausalLM.from_pretrained(model_id, token= token,
 
 # Load the model with the inferred device map
 # model = load_checkpoint_and_dispatch(model, model_id, device_map=device_map, no_split_module_classes=["GPTJBlock"])
-model.half()
+# model.half()
 
 
 
@@ -73,7 +73,7 @@ def respond(
     temperature,
     top_p,
 ):
-
+    model= model.to('cuda')
     messages = [{"role": "user", "content": "Hello, how are you?"}]
     input_ids = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt").to('cuda')
 ## <BOS_TOKEN><|START_OF_TURN_TOKEN|><|USER_TOKEN|>Hello, how are you?<|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>