Typos and potential clarification on the use of Colossal OSCAR

README.md

@@ -48,7 +48,7 @@ language:
 > 
 > The weights will be promptly updated as soon as the training process is complete. 
 
-# Salmandra ALIA-40b Model Card
+# Salamandra ALIA-40b Model Card
 
 ALIA-40b is a highly multilingual model pre-trained from scratch that will come with its respective base and instruction-tuned variants. This model card corresponds to the 40B base version.
 
@@ -282,10 +282,10 @@ for output in outputs:
 ### Pretraining Data
 
 The pre-training corpus comprises data from 35 European languages and 92 programming languages, with detailed data sources provided below. 
-The initial 1.5 training epochs used 2.4 trillion tokens, obtained by manually adjusting data proportion to balance the representation 
+The initial 1.5 training epochs used 2.4 trillion tokens from Colossal OSCAR, obtained by manually adjusting data proportion to balance the representation 
 and give more importance to Spain’s co-official (Spanish, Catalan, Galician, and Basque). This way, we downsampled code and English data to half, 
 Spanish co-official languages were oversampled by 2x, and the remaining languages were kept in their original proportions.
-Following, during the following epochs (still training), the Colossal OSCAR dataset was replaced with the FineWebEdu dataset. 
+During the following epochs (still training), the Colossal OSCAR dataset was replaced with the FineWeb-Edu dataset. 
 This adjustment resulted in a total of 2.68 trillion tokens, distributed as outlined below:
 
 ![lang distrib](./images/corpus_languages.png)