sramshetty / mixture-of-depths Goto Github PK
View Code? Open in Web Editor NEWAn unofficial implementation of "Mixture-of-Depths: Dynamically allocating compute in transformer-based language models"
License: Other
An unofficial implementation of "Mixture-of-Depths: Dynamically allocating compute in transformer-based language models"
License: Other
It seems that in your code all the token in a sequence are put into the transformer (attention and ffn) block?
Here, for auto regressive inference, the input seq length should be 1. It seems every token will be routed to attention and mlp since it will always be chosen as topk token weights. That's confusing.
Hi
First of all thanks for your implementation!
For the selected tokens you multiply the topk_weight by the output of the transformer block (here)
I think without any normalization, this multiplication can cause the model to give too much high value to the hidden_state and put nan after a rms_norm layer.
In this implementation they use softmax to normalize the topk_weight but they say also that this softmax break causality they mention also the auxiliary router.
I'm a bit confused about this normalization and this auxiliary router.
Thank you for your time!
sorted_indices = torch.argsort(topk_indices)
should be
sorted_indices = torch.sort(topk_indices)
Right?
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. ๐๐๐
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.