EfficientFormer
predictive-spy
EfficientFormer | predictive-spy | |
---|---|---|
2 | 7 | |
947 | 121 | |
1.1% | - | |
3.3 | 4.7 | |
9 months ago | 4 months ago | |
Python | Python | |
GNU General Public License v3.0 or later | 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.
EfficientFormer
-
A look at Apple’s new Transformer-powered predictive text model
I'm pretty fatigued on constantly providing references and sources in this thread but an example of what they've made availably publicly:
https://github.com/snap-research/EfficientFormer
-
Snap and Northeastern University Researchers Propose EfficientFormer: A Vision Transformer That Runs As Fast As MobileNet While Maintaining High Performance
Continue reading | Check out the paper, github
predictive-spy
-
Ferret: An End-to-End MLLM by Apple
According to this article[1] it has about 34 million parameters.
https://jackcook.com/2023/09/08/predictive-text.html
- A look at Apple’s new Transformer-powered predictive text model
- Apple UniLM: new 34M-parameter language model built into upcoming iOS
-
[P] A look at Apple’s new Transformer-powered predictive text model
- GitHub: https://github.com/jackcook/predictive-spy
What are some alternatives?
PyTorch-Model-Compare - Compare neural networks by their feature similarity
function-identification - This project demonstrates how a convolutional neural network can be used to detect the boundaries of a function in compiled code
Efficient-AI-Backbones - Efficient AI Backbones including GhostNet, TNT and MLP, developed by Huawei Noah's Ark Lab.
kgpt - A custom GPT based on [Zero To Hero](https://karpathy.ai/zero-to-hero.html) utilizing tiktoken with the intent to augment AI Transformer-model education and reverse engineer GPT models from scratch.
dytox - Dynamic Token Expansion with Continual Transformers, accepted at CVPR 2022
ml-ferret
llama.cpp - LLM inference in C/C++
CoreML-Models - Largest list of models for Core ML (for iOS 11+)
ml-cvnets - CVNets: A library for training computer vision networks
AppleNeuralHash2ONNX - Convert Apple NeuralHash model for CSAM Detection to ONNX.
transformers - 🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.