HuBoren99/SmartBert
The implementation of SmartBERT: A Promotion of Dynamic Early Exiting Mechanism for Accelerating BERT Inference
This project helps machine learning engineers and researchers speed up how quickly their BERT models can make predictions from text data. It takes a pre-trained BERT model and text datasets (like sentiment analysis or question answering), and outputs a faster-performing BERT model for deployment. This is for anyone deploying large language models who needs to optimize inference speed.
No commits in the last 6 months.
Use this if you are a machine learning engineer or researcher looking to accelerate the inference time of your BERT-based natural language processing models.
Not ideal if you are looking for a pre-trained model for direct use without optimization, or if your primary concern is model training speed rather than inference speed.
Stars
9
Forks
2
Language
Python
License
MIT
Category
Last pushed
Jan 15, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/HuBoren99/SmartBert"
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.