Sophia
Adan-pytorch
Sophia | Adan-pytorch | |
---|---|---|
3 | 1 | |
360 | 240 | |
- | - | |
7.0 | 3.2 | |
7 months ago | over 1 year ago | |
Python | Python | |
Apache License 2.0 | MIT License |
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.
Sophia
- [D] Potential scammer on github stealing work of other ML researchers?
-
[R] Sophia: A Scalable Stochastic Second-order Optimizer for Language Model Pre-training
Github repo
-
The Sophia optimizer, a faster alternative to AdamW
Code: https://github.com/kyegomez/Sophia
Looking forward to trying it out this week
Adan-pytorch
-
I tried the new adan optimizer..... Promising results(?)
Sometimes, google tries to be useful by recommending stuff like this https://github.com/lucidrains/Adan-pytorch
What are some alternatives?
Otter - 🦦 Otter, a multi-modal model based on OpenFlamingo (open-sourced version of DeepMind's Flamingo), trained on MIMIC-IT and showcasing improved instruction-following and in-context learning ability.
torchopt - TorchOpt is an efficient library for differentiable optimization built upon PyTorch.
Adan - Adan: Adaptive Nesterov Momentum Algorithm for Faster Optimizing Deep Models
LOGICGUIDE - Plug in and Play implementation of "Certified Reasoning with Language Models" that elevates model reasoning by 40%
adan-experiments - Checking out the new adan optimizer
tree-of-thoughts - Plug in and Play Implementation of Tree of Thoughts: Deliberate Problem Solving with Large Language Models that Elevates Model Reasoning by atleast 70%
AdamP - AdamP: Slowing Down the Slowdown for Momentum Optimizers on Scale-invariant Weights (ICLR 2021)
Sophia - The official implementation of “Sophia: A Scalable Stochastic Second-order Optimizer for Language Model Pre-training”
deep-daze - Simple command line tool for text to image generation using OpenAI's CLIP and Siren (Implicit neural representation network). Technique was originally created by https://twitter.com/advadnoun