Update README.md

README.md

@@ -144,23 +144,19 @@ We directly adapted this mechanism from Graves ([2016](#graves-2016)). At each i
 The architecture is not yet directly included in the Transformers library. The code used for pre-training is available in the following [github repository](https://github.com/AntoineSimoulin/adaptive-depth-transformers). So you should install the code implementation first:
 
 ```bash
-pip install git+https://github.com/AntoineSimoulin/adaptive-depth-transformers
+!pip install git+https://github.com/AntoineSimoulin/adaptive-depth-transformers$
 ```
 
 Then you can use the model directly.
 
 ```python
-import sys
-sys.path.append('adaptative-depth-transformers')
-
-from modeling_albert_act_tf import TFAlbertActModel
-from modeling_albert_act import AlbertActModel
-from configuration_albert_act import AlbertActConfig
+from act import AlbertActConfig, AlbertActModel, TFAlbertActModel
 from transformers import AlbertTokenizer
 
-model = AlbertActModel.from_pretrained('asi/albert-act-base/')
+tokenizer = AlbertTokenizer.from_pretrained('asi/albert-act-base')
+model = AlbertActModel.from_pretrained('asi/albert-act-base')
 _ = model.eval()
-tokenizer = AlbertTokenizer.from_pretrained('asi/albert-act-base/')
+
 inputs = tokenizer("a lump in the middle of the monkeys stirred and then fell quiet .", return_tensors="pt")
 outputs = model(**inputs)
 outputs.updates