update chatglm_llm.py

chatglm_llm.py

@@ -15,9 +15,6 @@ model = (
     .cuda()
 )
 
-tokenizer = AutoTokenizer.from_pretrained("THUDM/chatglm-6b", trust_remote_code=True)
-model = AutoModel.from_pretrained("THUDM/chatglm-6b", trust_remote_code=True).half().cuda()
-
 class ChatGLM(LLM):
     max_token: int = 10000
     temperature: float = 0.1