sayakpaul/BERT-for-Mobile
Compares the DistilBERT and MobileBERT architectures for mobile deployments.
This project helps machine learning engineers and mobile developers evaluate and deploy text classification models on mobile devices. It provides pre-trained DistilBERT models fine-tuned on the SST-2 dataset, along with TensorFlow Lite conversion and evaluation code. You can use this to integrate powerful language understanding into your mobile applications, taking text input and classifying it.
No commits in the last 6 months.
Use this if you are a mobile developer or ML engineer looking to implement efficient text classification models like DistilBERT into your mobile apps using TensorFlow Lite.
Not ideal if you need to train custom BERT models from scratch or are looking for a complete MobileBERT training workflow within this specific repository.
Stars
33
Forks
5
Language
Jupyter Notebook
License
—
Category
Last pushed
Oct 15, 2020
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/sayakpaul/BERT-for-Mobile"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
codertimo/BERT-pytorch
Google AI 2018 BERT pytorch implementation
JayYip/m3tl
BERT for Multitask Learning
920232796/bert_seq2seq
pytorch实现 Bert 做seq2seq任务，使用unilm方案,现在也可以做自动摘要，文本分类，情感分析，NER，词性标注等任务,支持t5模型，支持GPT2进行文章续写。
sileod/tasknet
Easy modernBERT fine-tuning and multi-task learning
graykode/toeicbert
TOEIC(Test of English for International Communication) solving using pytorch-pretrained-BERT model.