lancopku/CascadeBERT
Code for CascadeBERT, Findings of EMNLP 2021
This project helps machine learning engineers and researchers speed up how quickly large language models, like BERT, can analyze text. It takes pre-trained language models and text data as input, then processes them more efficiently to deliver the same accurate analysis, but much faster. The typical user is someone building or deploying natural language processing applications and wants to reduce computational costs or improve real-time performance.
No commits in the last 6 months.
Use this if you are working with large language models and need to accelerate their inference speed without sacrificing accuracy.
Not ideal if you are looking for a ready-to-use, no-code solution for text analysis, as this requires technical setup and model preparation.
Stars
12
Forks
1
Language
Python
License
MIT
Category
Last pushed
Mar 30, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/lancopku/CascadeBERT"
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.