nielsr HF staff commited on
Commit
2483517
1 Parent(s): 6630123

Update README

Browse files
Files changed (1) hide show
  1. README.md +1 -3
README.md CHANGED
@@ -19,7 +19,7 @@ The other (non-default) version which can be used is:
19
  Disclaimer: The team releasing TAPAS did not write a model card for this model so this model card has been written by
20
  the Hugging Face team and contributors.
21
 
22
- # Results on SQA - Dev Accuracy
23
 
24
  Size | Reset | Dev Accuracy | Link
25
  -------- | --------| -------- | ----
@@ -38,8 +38,6 @@ TINY | reset | 0.2375 | [tapas-tiny-finetuned-sqa](https://huggingface.co/google
38
 
39
  ## Model description
40
 
41
- ## Model description
42
-
43
  TAPAS is a BERT-like transformers model pretrained on a large corpus of English data from Wikipedia in a self-supervised fashion.
44
  This means it was pretrained on the raw tables and associated texts only, with no humans labelling them in any way (which is why it
45
  can use lots of publicly available data) with an automatic process to generate inputs and labels from those texts. More precisely, it
 
19
  Disclaimer: The team releasing TAPAS did not write a model card for this model so this model card has been written by
20
  the Hugging Face team and contributors.
21
 
22
+ ## Results on SQA - Dev Accuracy
23
 
24
  Size | Reset | Dev Accuracy | Link
25
  -------- | --------| -------- | ----
 
38
 
39
  ## Model description
40
 
 
 
41
  TAPAS is a BERT-like transformers model pretrained on a large corpus of English data from Wikipedia in a self-supervised fashion.
42
  This means it was pretrained on the raw tables and associated texts only, with no humans labelling them in any way (which is why it
43
  can use lots of publicly available data) with an automatic process to generate inputs and labels from those texts. More precisely, it