Update README.md

README.md

@@ -39,6 +39,8 @@ output = model(**encoded_input)
 
 ## Variations
 
+CamemBERT has originally been released in base (110M) and large (335M) variations. The following checkpoints prune the base variation by dropping the top 2, 4, 6, 8, and 10 pretrained encoding layers, repsectively.
+
 | Model                                                              | #Params |  Size | Pruning |
 |--------------------------------------------------------------------|:-------:|:-----:|:-------:|
 | [CamemBERT](https://huggingface.co/camembert-base)                 |  110.6M | 445MB |    -    |
@@ -51,6 +53,8 @@ output = model(**encoded_input)
 
 ## Citation
 
+For attribution in academic contexts, please cite this work as:
+
 ```bibtex
 @online{louis2023,
    author    = 'Antoine Louis',