JayYip/m3tl
BERT for Multitask Learning
This project helps machine learning engineers build systems that can learn multiple related tasks simultaneously, like classifying text sentiment and summarizing it, or recognizing objects in images while also generating captions. It takes in various types of data (text, images, etc.) and outputs a single model capable of performing several functions more effectively than training separate models. Developers who work with deep learning and transformer models will find this useful for creating robust AI applications.
544 stars. No commits in the last 6 months. Available on PyPI.
Use this if you are a machine learning engineer or researcher looking to train a single model to perform multiple related tasks across different types of data, leveraging transformer architectures.
Not ideal if you are new to deep learning or only need to solve a single, straightforward classification or regression problem without multi-task or multi-modal complexities.
Stars
544
Forks
124
Language
Jupyter Notebook
License
Apache-2.0
Category
Last pushed
Apr 12, 2023
Commits (30d)
0
Dependencies
12
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/JayYip/m3tl"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
codertimo/BERT-pytorch
Google AI 2018 BERT pytorch implementation
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.
guotong1988/BERT-pre-training
multi-gpu pre-training in one machine for BERT without horovod (Data Parallelism)