Update client.py

client.py

@@ -6,8 +6,8 @@ from database import execute
 
 # Load the model and tokenizer
 model_name = "Qwen/Qwen2.5-3B-Instruct"
-tokenizer = AutoTokenizer.from_pretrained(model_name, use_auth_token=True)
-model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.float16, device_map="auto")
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.float16)
 
 def respond(message, history, system_message, max_tokens, temperature, top_p):
     messages = [{"role": "system", "content": SYSTEM_PROMPT}]