lion-pytorch
opytimizer
lion-pytorch | opytimizer | |
---|---|---|
3 | 7 | |
1,925 | 594 | |
- | - | |
3.8 | 5.5 | |
about 1 month ago | 5 months ago | |
Python | Python | |
MIT License | Apache License 2.0 |
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.
lion-pytorch
-
Applying All Recent Innovations To Train a Code Model
Various people are trying LiON on their projects, with varying degrees of success. A good starting point to look around is the lion-pytorch on github from Phil Wang aka lucidrains (thank you man!).
- AMD RoCM Dockerfiles
-
[D] Lion , An Optimizer That Outperforms Adam - Symbolic Discovery of Optimization Algorithms
Code Implementation: https://github.com/lucidrains/lion-pytorch
opytimizer
-
[P] Opytimizer: A Nature-Inspired Python Optimizer
We do have a Simulated Annealing version designed to work with the library's structure: https://github.com/gugarosa/opytimizer/blob/master/opytimizer/optimizers/science/sa.py
-
Opytimizer: A Nature-Inspired Python Optimizer
Opytimizer: A Nature-Inspired Python Optimizer
Thanks mate! That would be a great addition indeed. We do have some examples over https://github.com/gugarosa/opytimizer/tree/master/examples/..., but they are not clearly depicted as the README would be. Thanks a lot!!
-
Gradient-Free-Optimizers A collection of modern optimization methods in Python
There's also Opytimizer [0] for almost every metaheuristic optimization algorithm under the Sun.
[0] https://github.com/gugarosa/opytimizer
What are some alternatives?
llm-foundry - LLM training code for Databricks foundation models
BayesianOptimization - A Python implementation of global optimization with gaussian processes.
dnn_from_scratch - A high level deep learning library for Convolutional Neural Networks,GANs and more, made from scratch(numpy/cupy implementation).
Hyperactive - An optimization and data collection toolbox for convenient and fast prototyping of computationally expensive models.
pytorch-lightning - Pretrain, finetune and deploy AI models on multiple GPUs, TPUs with zero code changes.
optimization-tutorial - Tutorials for the optimization techniques used in Gradient-Free-Optimizers and Hyperactive.
Gradient-Centralization-TensorFlow - Instantly improve your training performance of TensorFlow models with just 2 lines of code!
Gradient-Free-Optimizers - Simple and reliable optimization with local, global, population-based and sequential techniques in numerical discrete search spaces.