cbenge509/BERTVision
A parameter-efficient compression model architecture for a variety of NLP tasks at BERT level performance at a fraction of the computational requirements.
This tool helps data scientists and AI researchers process text data for tasks like question answering and sentiment analysis more efficiently. It takes large language model embeddings as input and outputs predictions for text classification or span annotation, offering similar performance to larger models but with significantly reduced computational cost. It is ideal for those working with NLP models and looking to optimize resource usage.
Use this if you need to deploy or experiment with powerful language models like BERT for text classification or question answering but are constrained by computational resources or model size.
Not ideal if you are not working with existing BERT-like language models or if your primary concern is not model size and computational efficiency.
Stars
10
Forks
—
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Jan 25, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/cbenge509/BERTVision"
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.