Downloads · 30 days
64
2% of all-time downloads
t5base_totto
Barkavi/t5base_totto
t5base_totto is a machine learning model from Barkavi. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for transformers.
All-time downloads
2.8K
Public
Repo size
1.8 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin892 MB · 100%
At a glance
- Library
- transformers
- Model type
- t5
- Access
- Public
- Created
- Mar 2, 2022
- Updated
- Jun 23, 2022
- SHA
- 8b214913
Model card
From the Hugging Face model README
Dataset
ToTTo is an open-domain English Table-to-Text dataset with over 120,000 training examples that proposes a controlled generation task: given a Wikipedia table, a set of highlighted table cells, page title and section title as inputs, it produces a one-sentence description summarising the key details from the inputs. This dataset can be taken from hugging face (https://huggingface.co/datasets/totto).
Model
The pre-trained Text-to-Text "t5-base" model is fine-tuned with the Table-to-Text ToTTo dataset(downstream task) for the complete train dataset split of around 120,761 examples. During the fine-tuning process for this downstream task, BertScore metric was used as an evaluation metric instead of the standard BLEU metric.
- Library
- transformers
- Type
- t5
- Created
- Mar 2, 2022
- Updated
- Jun 23, 2022