csarron/mobilebert-uncased-squad-v2

Question Answering·csarron· 16.1K· 8

transformers mit Question Answering 24.6M params dataset:squad_v2arxiv:2004.02984license:mitdeploy:azure

MobileBERT is a thin version of BERTLARGE, while equipped with bottleneck structures and a carefully designed balance between self-attentions and feed-forward networks.

Open in MLForge Sign up free Desktop app Source ↗

# pull & run locally
pip install mlforge-sdk && mlforge pull csarron/mobilebert-uncased-squad-v2

Model details

Task

Question Answering

Provider

csarron

Framework

transformers

Parameters

24.6M

Size

283 MB

License

mit

Downloads

16.1K

Likes

Paper

arXiv:2004.02984

Updated

2023-07-18

About csarron/mobilebert-uncased-squad-v2

MobileBERT is a thin version of BERTLARGE, while equipped with bottleneck structures and a carefully designed balance between self-attentions and feed-forward networks.

Related Question Answering

E ahotrod/electra_large_discriminator_squad2_512 Question Answering 874.4K 7 🤗 HF R deepset/roberta-base-squad2 Question Answering 503.9K 948 🤗 HF M timpal0l/mdeberta-v3-base-squad2 Question Answering ·278.2M params 259.9K 259 🤗 HF D distilbert/distilbert-base-cased-distilled-squad Question Answering ·65.2M params 212.7K 269 🤗 HF B deepset/bert-large-uncased-whole-word-masking-squad2 Question Answering ·335.1M params 192.2K 31 🤗 HF T deepset/tinyroberta-squad2 Question Answering ·81.5M params 165.9K 114 🤗 HF

Browse all Question Answering models →