Update app.py

app.py

@@ -8,8 +8,8 @@ from threading import Thread
 
 tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2-0.5B-Instruct")
 model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2-0.5B-Instruct")
-device = "cuda"
-model.to(device)
+# device = "cuda"
+# model.to(device)
 def chat(message, history):
     prompt = [
         {"role": "system", "content": "You are a helpful assistant."},
@@ -27,7 +27,8 @@ def chat(message, history):
     add_generation_prompt=True
     )   
 
-    model_inputs = tokenizer([text], return_tensors="pt").to("cuda")
+    # model_inputs = tokenizer([text], return_tensors="pt").to("cuda")
+    model_inputs = tokenizer([text], return_tensors="pt")
     streamer = TextIteratorStreamer(tokenizer, timeout=10., skip_prompt=True, skip_special_tokens=True)
     generate_kwargs = dict(
         model_inputs,