Update client.py

client.py

@@ -7,10 +7,12 @@ from database import execute
 # Load the model and tokenizer
 model_name = "Qwen/Qwen2.5-3B-Instruct"
 tokenizer = AutoTokenizer.from_pretrained(model_name)
-model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.float16)
+model = AutoModelForCausalLM.from_pretrained(model_name)
 
+
+messages = [{"role": "system", "content": SYSTEM_PROMPT}]
 def respond(message, history, system_message, max_tokens, temperature, top_p):
-    messages = [{"role": "system", "content": SYSTEM_PROMPT}]
+    
     
     # Process chat history
     for val in history:
@@ -23,7 +25,7 @@ def respond(message, history, system_message, max_tokens, temperature, top_p):
 
     # Tokenize input
     input_text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
-    input_ids = tokenizer.encode(input_text, return_tensors="pt").to(model.device)
+    input_ids = tokenizer.encode(input_text, return_tensors="pt")
 
     # Generate response
     output_ids = model.generate(