Update app.py

app.py

@@ -10,11 +10,10 @@ print("Loading tokenizer & model…")
 tokenizer = AutoTokenizer.from_pretrained(MODEL_ID)
 # model = AutoModelForCausalLM.from_pretrained(MODEL_ID, torch_dtype=torch.bfloat16).to(DEVICE)
 
-model = AutoModelForCausalLM.from_pretrained(
-    MODEL_ID,
-    # load_in_8bit=True,  # or try load_in_4bit=True
-    # device_map=DEVICE
-)
+model =\
+        AutoModelForCausalLM\
+                .from_pretrained(MODEL_ID, torch_dtype=torch.bfloat16)\
+                .to(DEVICE)
 
 #########
 
@@ -68,7 +67,7 @@ def chat_fn(history, enable_thinking, temperature, top_p, top_k, repetition_pena
         add_generation_prompt=True,
         # xml_tools=TOOLS
     )
-    inputs = tokenizer(text, return_tensors="pt").to(DEVICE)
+    inputs = tokenizer(text, return_tensors="pt")
     with torch.inference_mode():
         streamer = model.generate(
             **inputs,