omarmomen commited on
Commit
a2ee48c
1 Parent(s): a39e347

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -1
README.md CHANGED
@@ -15,4 +15,6 @@ The paper titled "Increasing The Performance of Cognitively Inspired Data-Effici
15
 
16
  <strong>omarmomen/roberta_base_32k_final</strong> is a baseline RobertaModel.
17
 
18
- The model is pretrained on the BabyLM 10M dataset using a custom pretrained RobertaTokenizer (https://huggingface.co/omarmomen/babylm_tokenizer_32k).
 
 
 
15
 
16
  <strong>omarmomen/roberta_base_32k_final</strong> is a baseline RobertaModel.
17
 
18
+ The model is pretrained on the BabyLM 10M dataset using a custom pretrained RobertaTokenizer (https://huggingface.co/omarmomen/babylm_tokenizer_32k).
19
+
20
+ https://arxiv.org/abs/2310.20589