Update README.md

README.md

@@ -41,15 +41,16 @@ It has different versions that were trained for different variants of Portuguese
 namely the European variant from Portugal (**PT-PT**) and the American variant from Brazil (**PT-BR**), 
 and it is distributed free of charge and under a most permissible license.
 
-**Albertina PT-BR** is the version for American **Portuguese** from **Brazil**, 
-and to the best of our knowledge, at the time of its initial distribution,
-it is an encoder specifically for this language and variant 
+**Albertina PT-BR No-brWaC** is a version for American **Portuguese** from **Brazil** trained on 
+data sets other than brWaC, and thus with a most permissive license. 
+
+You may be interested also in [**Albertina PT-BR**](https://huggingface.co/PORTULAN/albertina-ptbr), trained on brWaC.
+To the best of our knowledge, these are encoders specifically for this language and variant 
 that sets a new state of the art for it, and is made publicly available 
 and distributed for reuse.
 
 
-
-It is developed by a joint team from the University of Lisbon and the University of Porto, Portugal. 
+**Albertina PT-BR No-brWaC** is developed by a joint team from the University of Lisbon and the University of Porto, Portugal. 
 For further details, check the respective [publication](https://arxiv.org/abs/2305.06721):
 
 ``` latex
@@ -101,7 +102,7 @@ We skipped the default filtering of stopwords since it would disrupt the syntact
 
 As codebase, we resorted to the [DeBERTa V2 XLarge](https://huggingface.co/microsoft/deberta-v2-xlarge), for English.
 
-To train [**Albertina PT-PT No-brWac**](https://huggingface.co/PORTULAN/albertina-ptpt-nobrwac), the data set was tokenized with the original DeBERTa tokenizer with a 128 token sequence truncation and dynamic padding.
+To train [**Albertina PT-PT No-brWac**](https://huggingface.co/PORTULAN/albertina-ptbr-nobrwac), the data set was tokenized with the original DeBERTa tokenizer with a 128 token sequence truncation and dynamic padding.
 The model was trained using the maximum available memory capacity resulting in a batch size of 896 samples (56 samples per GPU).
 We chose a learning rate of 1e-5 with linear decay and 10k warm-up steps. 
 In total, around 200k training steps were taken across 50 epochs.