Update README.md

README.md

@@ -29,6 +29,7 @@ license: other
 
 Here is an example of multi-modal ICL (in-context learning) with 🦦 Otter. We provide two demo images with corresponding instructions and answers, then we ask the model to generate an answer given our instruct. You may change your instruction and see how the model responds.
 
+Please first clone [Otter](https://github.com/Luodian/Otter) to your local disk. Place following script inside the Otter folder to make sure it has the access to otter/modeling_otter.py.
 ``` python
 import mimetypes
 import os
@@ -162,7 +163,7 @@ def get_response(image_list, prompt: str, model=None, image_processor=None, in_c
 
 if __name__ == "__main__":
     model = OtterForConditionalGeneration.from_pretrained(
-        "luodian/otter-9b-hf", device_map="auto"
+        "luodian/OTTER-9B-LA-InContext", device_map="auto"
     )
     model.text_tokenizer.padding_side = "left"
     tokenizer = model.text_tokenizer