Upload folder using huggingface_hub

README.md

@@ -30,7 +30,7 @@ LMDeploy supports the following NVIDIA GPU for W4A16 inference:
 Before proceeding with the quantization and inference, please ensure that lmdeploy is installed.
 
 ```shell
-pip install lmdeploy[all]
+pip install lmdeploy
 ```
 
 This article comprises the following sections:

tokenizer.json

@@ -174240,4 +174240,4 @@
       "现 今"
     ]
   }
-}
+}