mixture-of-experts
A Pytorch implementation of Sparsely-Gated Mixture of Experts, for massively increasing the parameter count of language models (by lucidrains)
conformer
Implementation of the convolutional module from the Conformer paper, for use in Transformers (by lucidrains)
| mixture-of-experts | conformer | |
|---|---|---|
| 1 | 1 | |
| 525 | 332 | |
| - | - | |
| 4.1 | 3.1 | |
| 8 months ago | 12 months ago | |
| Python | Python | |
| MIT License | MIT License |
The number of mentions indicates the total number of mentions that we've tracked plus the number of user suggested alternatives.
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
mixture-of-experts
Posts with mentions or reviews of mixture-of-experts.
We have used some of these posts to build our list of alternatives
and similar projects.
-
How to Go beyond Data Parallelism and Model Parallelism: Talking from GShard[R]
Code for https://arxiv.org/abs/2006.16668 found: https://github.com/lucidrains/mixture-of-experts
conformer
Posts with mentions or reviews of conformer.
We have used some of these posts to build our list of alternatives
and similar projects.
-
[N] Conformer-1 - A state-of-the-art speech recognition model trained on 650K hours of data
Found relevant code at https://github.com/lucidrains/conformer + all code implementations here
What are some alternatives?
When comparing mixture-of-experts and conformer you can also consider the following projects:
uformer-pytorch - Implementation of Uformer, Attention-based Unet, in Pytorch
routing-transformer - Fully featured implementation of Routing Transformer
enformer-pytorch - Implementation of Enformer, Deepmind's attention network for predicting gene expression, in Pytorch
tab-transformer-pytorch - Implementation of TabTransformer, attention network for tabular data, in Pytorch
Perceiver - Implementation of Perceiver, General Perception with Iterative Attention in TensorFlow
Nystromformer - An implementation of the Nyströmformer, using Nystrom method to approximate standard self attention