Update use case

README.md

@@ -41,8 +41,8 @@ pip install protobuf transformers==4.30.2 cpm_kernels torch>=2.0 gradio mdtex2ht
 
 ```ipython
 >>> from transformers import AutoTokenizer, AutoModel
->>> tokenizer = AutoTokenizer.from_pretrained("THUDM/chatglm2-6b", trust_remote_code=True)
->>> model = AutoModel.from_pretrained("THUDM/chatglm2-6b", trust_remote_code=True).half().cuda()
+>>> tokenizer = AutoTokenizer.from_pretrained("THUDM/chatglm2-6b-int4", trust_remote_code=True)
+>>> model = AutoModel.from_pretrained("THUDM/chatglm2-6b-int4", trust_remote_code=True).half().cuda()
 >>> model = model.eval()
 >>> response, history = model.chat(tokenizer, "你好", history=[])
 >>> print(response)