tech-srl/layer_norm_expressivity_role
Code for the paper "On the Expressivity Role of LayerNorm in Transformers' Attention" (Findings of ACL'2023)
This project helps machine learning researchers and academics understand how Layer Normalization impacts the performance of Transformer models, particularly in their attention mechanisms. It takes experimental setups for tasks like 'Majority' and 'Unselectable Keys' and outputs results that demonstrate the expressivity role of Layer Normalization. This is for researchers specializing in deep learning architecture and natural language processing.
No commits in the last 6 months.
Use this if you are a machine learning researcher investigating the fundamental properties and architectural choices within Transformer networks.
Not ideal if you are looking for an off-the-shelf solution for an applied NLP task or a general-purpose Transformer library.
Stars
57
Forks
3
Language
Python
License
—
Category
Last pushed
Sep 27, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/tech-srl/layer_norm_expressivity_role"
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