Downloads · 30 days
15
1% of all-time downloads
distilbert-base-uncased-squadv1.1-sparse-80-1X4-block
Intel/distilbert-base-uncased-squadv1.1-sparse-80-1X4-block
distilbert-base-uncased-squadv1.1-sparse-80-1X4-block is a question answering model from Intel. Use it when the input is a question plus a passage. It is set up for transformers. The card lists the license as apache-2.0.
Finetuned model pruned to 1:4 structured sparsity.
All-time downloads
1.2K
Public
Repo size
808 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin404 MB · 74%
At a glance
- Task
- Question Answering
- Library
- transformers
- License
- apache-2.0
- Model type
- distilbert
- Access
- Public
- Created
- Nov 23, 2022
- Updated
- Nov 23, 2022
- SHA
- 6ceffc48
Try a prompt
Model card
From the Hugging Face model README
Sparse DISTILBERT model (uncased)
Finetuned model pruned to 1:4 structured sparsity.
Intended Use
The model can be used for inference with sparsity optimization. For further details on the model and its usage will be soon available.
Evaluation Results
We get the following results on the SQuADv1.1 tasks development set:
| Task | SQuADv1.1 (F1) |
|---|---|
| 87.00 |
- Task
- Question Answering
- Library
- transformers
- Type
- distilbert
- License
- apache-2.0
- Created
- Nov 23, 2022
- Updated
- Nov 23, 2022