Downloads · 30 days
40
1% of all-time downloads
xlnet-base-cased-squad-quoref
ggoggam/xlnet-base-cased-squad-quoref
xlnet-base-cased-squad-quoref is a question answering model from ggoggam. Use it when the input is a question plus a passage. It is set up for transformers.
XLNet jointly developed by Google and CMU and fine-tuned on SQuAD / SQuAD 2.0 and Quoref for question answering down-stream task.
All-time downloads
2.8K
Public
Repo size
953 MB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.bin476 MB · 100%
At a glance
- Task
- Question Answering
- Library
- transformers
- Model type
- xlnet
- Access
- Public
- Created
- Mar 2, 2022
- Updated
- Jan 28, 2021
- SHA
- 1ab9e659
Try a prompt
Model card
From the Hugging Face model README
XLNet Fine-tuned on SQuAD / Quoref Dataset
XLNet jointly developed by Google and CMU and fine-tuned on SQuAD / SQuAD 2.0 and Quoref for question answering down-stream task.
Evaluation Result on Quoref
{
"exact_match": 73.65591397848462,
"f1": 77.9981532789881
}
Results Comparison on Quoref
| Metric | XLNet Base Line | Model FT on SQuAD |
|---|---|---|
| EM | 61.88 | 73.66 (+11.78) |
| F1 | 70.51 | 78.00 (+7.49) |
How to Use
from transformers import XLNetForQuestionAnswering, XLNetTokenizerFast
model = XLNetForQuestionAnswering.from_pretrained('jkgrad/xlnet-base-cased-squad-quoref)
tokenizer = XLNetTokenizerFast.from_pretrained('jkgrad/xlnet-base-cased-squad-quoref')
- Task
- Question Answering
- Library
- transformers
- Type
- xlnet
- Created
- Mar 2, 2022
- Updated
- Jan 28, 2021