fix a typo

README.md

@@ -16,7 +16,6 @@ language:
 
 ## Inference (Huggingface Version)
 
-### Emu2 & Emu2-Chat
 #### Single GPU
 
 ```python
@@ -182,7 +181,7 @@ device_map["model.decoder.lm.lm_head"] = 0
 
 model = load_checkpoint_and_dispatch(
     model, 
-    'local/path/to/hf/version/Emu2/model',
+    'local/path/to/hf/version/Emu2-Chat/model',
     device_map=device_map).eval()
 
 # `[<IMG_PLH>]` is the image placeholder which will be replaced by image embeddings.