neulab
/

omnitab-large-finetuned-wtq

Table Question Answering

text2text-generation

Inference Endpoints

Model card Files Files and versions Community

Zhengbao Jiang commited on Nov 29, 2022

Commit

8ec8a47

•

1 Parent(s): 53daa54

updated readme

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -13,7 +13,7 @@ OmniTab is a table-based QA model proposed in [OmniTab: Pretraining with Natural
 ## Description
-`neulab/omnitab-large-finetuned-wtq` (based on BART architecture) is initialized with `microsoft/tapex-large`, continuously pretrained on natural and synthetic data, and fine-tuned on [WikiTableQuestions](https://huggingface.co/datasets/wikitablequestions).
 ## Usage
@@ -49,4 +49,4 @@ print(tokenizer.batch_decode(outputs, skip_special_tokens=True))
   month = jul,
   year = "2022",
 }
-```

 ## Description
+`neulab/omnitab-large-finetuned-wtq` (based on BART architecture) is initialized with `neulab/omnitab-large` and fine-tuned on [WikiTableQuestions](https://huggingface.co/datasets/wikitablequestions).
 ## Usage
   month = jul,
   year = "2022",
 }
+```