clovaai/length-adaptive-transformer
Official Pytorch Implementation of Length-Adaptive Transformer (ACL 2021)
This project helps machine learning engineers and researchers optimize the speed and efficiency of their natural language processing (NLP) models. You provide an existing BERT or DistilBERT model trained for tasks like question answering or text classification, and the project outputs a more efficient version of that model. This is for users who fine-tune transformer models for specific NLP applications.
102 stars. No commits in the last 6 months.
Use this if you are a machine learning engineer or researcher looking to make your BERT or DistilBERT models run faster and more efficiently for question answering or text classification tasks.
Not ideal if you are not working with BERT or DistilBERT models, or if your primary tasks are not question answering or text classification.
Stars
102
Forks
13
Language
Python
License
Apache-2.0
Category
Last pushed
Nov 02, 2020
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/clovaai/length-adaptive-transformer"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
lucidrains/x-transformers
A concise but complete full-attention transformer with a set of promising experimental features...
kanishkamisra/minicons
Utility for behavioral and representational analyses of Language Models
lucidrains/simple-hierarchical-transformer
Experiments around a simple idea for inducing multiple hierarchical predictive model within a GPT
lucidrains/dreamer4
Implementation of Danijar's latest iteration for his Dreamer line of work
Nicolepcx/Transformers-in-Action
This is the corresponding code for the book Transformers in Action