readme updates

Author: dmmiller612

README.md

@@ -10,7 +10,7 @@ the sentences that are closest to the cluster's centroids. This library also use
 https://github.com/huggingface/neuralcoref library to resolve words in summaries that need more context. The greedyness of 
 the neuralcoref library can be tweaked in the CoreferenceHandler class.
 
-As of version 0.4.2, by default, CUDA is used if a gpu is available.
+As of the most recent version of bert-extractive-summarizer, by default, CUDA is used if a gpu is available.
 
 Paper: https://arxiv.org/abs/1906.04165
 
@@ -61,6 +61,17 @@ result = model(body, ratio=0.2)  # Specified with ratio
 result = model(body, num_sentences=3)  # Will return 3 sentences 
 ```
 
+#### Using multiple hidden layers as the embedding output
+
+You can also concat the summarizer embeddings for clustering. A simple example is below.
+
+```python
+from summarizer import Summarizer
+body = 'Text body that you want to summarize with BERT'
+model = Summarizer('distilbert-base-uncased', hidden=[-1,-2], hidden_concat=True)
+result = model(body, num_sentences=3)
+```
+
 ### Use SBert
 One can use Sentence Bert with bert-extractive-summarizer with the newest version. It is based off the paper here:
 https://arxiv.org/abs/1908.10084, and the library here: https://www.sbert.net/. To get started,

summarizer/transformer_embeddings/bert_embedding.py

@@ -100,7 +100,6 @@ def extract_embeddings(
 
         :param text: The text to extract embeddings for.
         :param hidden: The hidden layer(s) to use for a readout handler.
-        :param squeeze: If we should squeeze the outputs (required for some layers).
         :param reduce_option: How we should reduce the items.
         :param hidden_concat: Whether or not to concat multiple hidden layers.
         :return: A torch vector.
@@ -158,7 +157,7 @@ def create_matrix(
     def __call__(
         self,
         content: List[str],
-        hidden: int = -2,
+        hidden: Union[List[int], int] = -2,
         reduce_option: str = 'mean',
         hidden_concat: bool = False,
     ) -> ndarray: