Downloads · 30 days
19
8% of all-time downloads
mobilebert-uncased-squadv1-14blocks-structured39.8-int8
yujiepan/mobilebert-uncased-squadv1-14blocks-structured39.8-int8
mobilebert-uncased-squadv1-14blocks-structured39.8-int8 is a machine learning model from yujiepan. 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. The card lists the license as apache-2.0.
should probably proofread and complete it, then remove this comment. --
All-time downloads
228
Public
Repo size
290 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin116 MB · 61%
At a glance
- Library
- transformers
- License
- apache-2.0
- Model type
- mobilebert
- Access
- Public
- Created
- May 15, 2023
- Updated
- May 15, 2023
- SHA
- d7fe266a
Datasets
Model card
From the Hugging Face model README
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
mobilebert-uncased-squadv1-14blocks-structured39.8-int8
This model is a fine-tuned version of google/mobilebert-uncased on the squad dataset.
Notice that this model only has the first 14 transformer blocks. It is quantized and structually pruned by NNCF. The sparsity in remaining linear layers is 39.8%.
- Torch f1: 90.15
- IR f1: 89.8414
Framework versions
- Transformers 4.25.1
- Pytorch 1.13.1+cu116
- Datasets 2.8.0
- Tokenizers 0.13.2
- Library
- transformers
- Type
- mobilebert
- License
- apache-2.0
- Created
- May 15, 2023
- Updated
- May 15, 2023