PaulD commited on
Commit
2cbb598
1 Parent(s): 4993c4b

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -0
README.md CHANGED
@@ -8,6 +8,7 @@ widget:
8
  ### CosmicRoBERTa
9
 
10
  This model is a further pre-trained version of RoBERTa for space science on a domain-specific corpus, which includes abstracts from the NTRS library, abstracts from SCOPUS, ECSS requirements, and other sources from this domain.
 
11
 
12
  The model performs slightly better on a subset (0.6 of total data set) of the CR task presented in our paper [SpaceTransformers: Language Modeling for Space Systems](https://ieeexplore.ieee.org/document/9548078).
13
 
 
8
  ### CosmicRoBERTa
9
 
10
  This model is a further pre-trained version of RoBERTa for space science on a domain-specific corpus, which includes abstracts from the NTRS library, abstracts from SCOPUS, ECSS requirements, and other sources from this domain.
11
+ This totals to a pre-training corpus of around 75 mio words.
12
 
13
  The model performs slightly better on a subset (0.6 of total data set) of the CR task presented in our paper [SpaceTransformers: Language Modeling for Space Systems](https://ieeexplore.ieee.org/document/9548078).
14