updated readme
This commit is contained in:
parent
53daa54bbc
commit
8ec8a476d9
|
@ -13,7 +13,7 @@ OmniTab is a table-based QA model proposed in [OmniTab: Pretraining with Natural
|
||||||
|
|
||||||
## Description
|
## 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).
|
`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
|
## Usage
|
||||||
|
|
||||||
|
@ -49,4 +49,4 @@ print(tokenizer.batch_decode(outputs, skip_special_tokens=True))
|
||||||
month = jul,
|
month = jul,
|
||||||
year = "2022",
|
year = "2022",
|
||||||
}
|
}
|
||||||
```
|
```
|
||||||
|
|
Loading…
Reference in New Issue