Downloads · 30 days
6
1% of all-time downloads
roberta-base-squad2-boolq-baseline
shahrukhx01/roberta-base-squad2-boolq-baseline
roberta-base-squad2-boolq-baseline is a question answering model from shahrukhx01. Use it when the input is a question plus a passage. It is set up for transformers.
ExtractiveQA Head Three Class Classification Head, classes = (yes, no, extraqa) to answer binary questions or direct to ExtractiveQA Head
All-time downloads
1.1K
Public
Repo size
1.5 GB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.bin499 MB · 99%
At a glance
- Task
- Question Answering
- Library
- transformers
- Model type
- roberta
- Access
- Public
- Created
- Mar 2, 2022
- Updated
- Sep 28, 2021
- SHA
- ad3bde67
Try a prompt
Model card
From the Hugging Face model README
Multiple Prediction Heads
- ExtractiveQA Head
- Three Class Classification Head, classes => (yes, no, extra_qa) to answer binary questions or direct to ExtractiveQA Head
BoolQ Validation dataset Evaluation: <br/>
support => 3270 <br/> accuracy => 0.73 <br/> macro f1 => 0.71
SQuAD Validation dataset Evaluation: <br/>
eval_HasAns_exact = 78.0196 <br/> eval_HasAns_f1 = 84.0327 <br/> eval_HasAns_total = 5928 <br/> eval_NoAns_exact = 81.8167 <br/> eval_NoAns_f1 = 81.8167 <br/> eval_NoAns_total = 5945 <br/> eval_best_exact = 79.9208 <br/> eval_best_f1 = 82.9231 <br/> eval_exact = 79.9208 <br/> eval_f1 = 82.9231 <br/> eval_samples = 12165 <br/> eval_total = 11873
Uasge in transformers
Import the script from here
from multitask_model import RobertaForMultitaskQA
from transformers import RobertaTokenizerFast
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
model = RobertaForMultitaskQA.from_pretrained(
"shahrukhx01/roberta-base-squad2-boolq-baseline",
task_labels_map={"squad_v2": 2, "boolq": 3},
).to(device)
tokenizer = RobertaTokenizerFast.from_pretrained("shahrukhx01/roberta-base-squad2-boolq-baseline")
- Task
- Question Answering
- Library
- transformers
- Type
- roberta
- Created
- Mar 2, 2022
- Updated
- Sep 28, 2021