Make minor updates to docs (#3285)

Author: tomaarsen

docs/cross_encoder/usage/usage.rst

@@ -18,7 +18,7 @@ Once you have `installed <../../installation.html>`_ Sentence Transformers, you
    3. :meth:`CrossEncoder.rank <sentence_transformers.cross_encoder.CrossEncoder.rank>`
 
    .. note::
-      MS Marco models return logits rather than scores between 0 and 1. Load the :class:`~sentence_transformers.cross_encoder.CrossEncoder` with ``default_activation_function=torch.nn.Sigmoid()`` to get scores between 0 and 1. This does not affect the ranking.
+      MS Marco models return logits rather than scores between 0 and 1. Load the :class:`~sentence_transformers.cross_encoder.CrossEncoder` with ``activation_fn=torch.nn.Sigmoid()`` to get scores between 0 and 1. This does not affect the ranking.
 
 ::
 
@@ -72,4 +72,5 @@ Once you have `installed <../../installation.html>`_ Sentence Transformers, you
    :maxdepth: 1
    :caption: Tasks
 
-   ../../../examples/sentence_transformer/applications/retrieve_rerank/README
+   Cross-Encoder vs Bi-Encoder <../../../examples/cross_encoder/applications/README>
+   ../../../examples/sentence_transformer/applications/retrieve_rerank/README

examples/cross_encoder/applications/README.md

@@ -2,7 +2,7 @@
 SentenceTransformers also supports to load Cross-Encoders for sentence pair scoring and sentence pair classification tasks.
 
 
-## Bi-Encoder vs. Cross-Encoder
+## Cross-Encoder vs. Bi-Encoder
 
 First, it is important to understand the difference between Bi- and Cross-Encoder.
 
@@ -33,13 +33,13 @@ Using Cross-Encoders is quite easy:
 ```python
 from sentence_transformers.cross_encoder import CrossEncoder
 
-model = CrossEncoder("model_name_or_path")
+model = CrossEncoder("cross-encoder/ms-marco-MiniLM-L6-v2")
 scores = model.predict([["My first", "sentence pair"], ["Second text", "pair"]])
 ```
 
 You pass to `model.predict` a list of sentence **pairs**. Note, Cross-Encoder do not work on individual sentence, you have to pass sentence pairs.
 
-As model name, you can pass any model or path that is compatible with Hugging Face [AutoModel](https://huggingface.co/transformers/model_doc/auto.html) class
+As model name, you can pass any model or path that is compatible with Hugging Face [AutoModel](https://huggingface.co/transformers/model_doc/auto.html) class.
 
 
 For a full example, to score a query with all possible sentences in a corpus see [cross-encoder_usage.py](cross-encoder_usage.py).

examples/cross_encoder/training/ms_marco/README.md

@@ -5,7 +5,7 @@ If you are interested in how to use these models, see [Application - Retrieve &
 
 ## Cross Encoder
 ```{eval-rst}
-A `Cross Encoder <../../applications/README.md>`_ accepts both a query and a possible relevant passage and returns a score denoting how relevant the passage is for the given query. Often times, a :class:`torch.nn.Sigmoid` is applied over the raw output prediction, casting it to a value between 0 and 1.
+A `Cross Encoder <../../applications/README.html>`_ accepts both a query and a possible relevant passage and returns a score denoting how relevant the passage is for the given query. Often times, a :class:`torch.nn.Sigmoid` is applied over the raw output prediction, casting it to a value between 0 and 1.
 ```
 
 ![CrossEncoder](https://raw.githubusercontent.com/UKPLab/sentence-transformers/master/docs/img/CrossEncoder.png)