grouphug
Multi-task modelling extensions for huggingface transformers (by chatdesk)
llrt
Local Learning Rule Tensors neural network library (by bparkis)
grouphug | llrt | |
---|---|---|
1 | 5 | |
16 | 0 | |
- | - | |
1.5 | 0.0 | |
about 1 year ago | almost 2 years ago | |
Python | C++ | |
GNU General Public License v3.0 or later | GNU General Public License v3.0 only |
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.
grouphug
Posts with mentions or reviews of grouphug.
We have used some of these posts to build our list of alternatives
and similar projects. The last one was on 2022-06-17.
-
[D] Is anyone working on interesting ML libraries and looking for contributors?
Recently released a package for multi-task modelling with huggingface, which could definitely use contributors.
llrt
Posts with mentions or reviews of llrt.
We have used some of these posts to build our list of alternatives
and similar projects. The last one was on 2022-06-17.
-
Connectionist simulation tool
Local learning rule tensors: https://github.com/bparkis/llrt
-
Framework for investigating local neuron learning rules
Local learning rule tensors: https://github.com/bparkis/llrt It's a framework to allow you to flexibly specify how an individual neuron works, such as its learning rule, and then connect many of these neurons together in connectivity patterns such as Dense or Local2D. Unlike other ML frameworks, the connectivity pattern can be applied independently from the neuron behavior. So, you can easily test a proposed local learning rule across a variety of architectures.
- Framework for investigating neuron local learning rules
-
[D] Is anyone working on interesting ML libraries and looking for contributors?
See if https://github.com/bparkis/llrt interests you.
-
[Project] Framework for testing out different local learning rules
I made this project: https://github.com/bparkis/llrt It is a framework to allow you to flexibly specify how an individual neuron works, such as its learning rule, and then connect many of these neurons together in connectivity patterns such as Dense or Local2D. Unlike other ML frameworks, the connectivity pattern can be applied independently from the neuron behavior.
What are some alternatives?
When comparing grouphug and llrt you can also consider the following projects:
composer - Supercharge Your Model Training
hamilton - A scalable general purpose micro-framework for defining dataflows. THIS REPOSITORY HAS BEEN MOVED TO www.github.com/dagworks-inc/hamilton
hamilton - Hamilton helps data scientists and engineers define testable, modular, self-documenting dataflows, that encode lineage and metadata. Runs and scales everywhere python does.