jaketae/param-share-transformer
PyTorch implementation of Lessons on Parameter Sharing across Layers in Transformers
This project offers a specialized type of Transformer model that helps deep learning engineers build more efficient natural language processing (NLP) systems. It takes in textual data (like sentences or documents) and processes it through a Transformer architecture, outputting refined data representations that can be used for tasks such as machine translation or text summarization. This is ideal for machine learning engineers and researchers who are working on large-scale NLP problems.
No commits in the last 6 months.
Use this if you need to build high-performance Transformer models for NLP tasks but want to significantly reduce computational costs and memory footprint compared to standard Transformers.
Not ideal if you are looking for a ready-to-use NLP application or if your primary goal is not optimizing model efficiency through parameter sharing.
Stars
26
Forks
4
Language
Python
License
MIT
Category
Last pushed
May 19, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/jaketae/param-share-transformer"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
huggingface/transformers-bloom-inference
Fast Inference Solutions for BLOOM
Tencent/TurboTransformers
a fast and user-friendly runtime for transformer inference (Bert, Albert, GPT2, Decoders, etc)...
mit-han-lab/lite-transformer
[ICLR 2020] Lite Transformer with Long-Short Range Attention
mit-han-lab/hardware-aware-transformers
[ACL'20] HAT: Hardware-Aware Transformers for Efficient Natural Language Processing
LibreTranslate/Locomotive
Toolkit for training/converting LibreTranslate compatible language models 🚂