google
/
tapas-base-finetuned-wikisql-supervised
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Update README

This commit is contained in:
Niels Rogge 2020-12-15 17:57:17 +00:00 committed by huggingface-web
parent bf726de15e
commit 42d7f9c0ce
1 changed files with 4 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
README.md
View File

@ -10,14 +10,11 @@ datasets:
# TAPAS base model fine-tuned on WikiSQL (in a supervised fashion)
This model has 4 versions which can be used. The latest version, which is the default one, corresponds to the `tapas_wikisql_sqa_inter_masklm_base_reset` checkpoint of the [original Github repository](https://github.com/google-research/tapas).
This model was pre-trained on MLM and an additional step which the authors call intermediate pre-training, and then fine-tuned on [SQA](https://www.microsoft.com/en-us/download/details.aspx?id=54253) and
[WikiSQL](https://github.com/salesforce/WikiSQL). It uses relative position embeddings by default (i.e. resetting the position index at every cell of the table).
his model has 2 versions which can be used. The default version corresponds to the `tapas_wikisql_sqa_inter_masklm_base_reset` checkpoint of the [original Github repository](https://github.com/google-research/tapas).
This model was pre-trained on MLM and an additional step which the authors call intermediate pre-training, and then fine-tuned in a chain on [SQA](https://www.microsoft.com/en-us/download/details.aspx?id=54253), and [WikiSQL](https://github.com/salesforce/WikiSQL). It uses relative position embeddings (i.e. resetting the position index at every cell of the table).
The other (non-default) versions which can be used are:
- `revision="v3"`, which corresponds to `tapas_wikisql_sqa_inter_masklm_base` (intermediate pre-training, absolute position embeddings)
- `revision="v2"`, which corresponds to `tapas_wikisql_sqa_masklm_base_reset` (no intermediate pre-training, relative position embeddings)
- `revision="v1"`, which corresponds to `tapas_wikisql_sqa_masklm_base` (no intermediate pre-training, absolute position embeddings)
The other (non-default) version which can be used is:
- `no_reset`, which corresponds to `tapas_wikisql_sqa_inter_masklm_base_reset` (intermediate pre-training, absolute position embeddings).
Disclaimer: The team releasing TAPAS did not write a model card for this model so this model card has been written by
the Hugging Face team and contributors.