Jake Tae

Elite
@jaketae

storyteller. Multimodal AI Story Teller, built with Stable Diffusion, GPT, and neural text-to-speech

537

koclip. KoCLIP: Korean port of OpenAI CLIP, in Flax

155

deep-malware-detection. A neural approach to malware detection in portable executables

81

wordwise. N-gram keyword extraction using spaCy and pretrained language models

62

ensemble-transformers. Ensembling Hugging Face transformers made easy

61

g-mlp. PyTorch implementation of Pay Attention to MLPs

40

mlp-mixer. PyTorch implementation of MLP-Mixer: An all-MLP Architecture for Vision

38

alibi. PyTorch implementation of Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolation

33

fnet. PyTorch implementation of FNet: Mixing Tokens with Fourier transforms

29

param-share-transformer. PyTorch implementation of Lessons on Parameter Sharing across Layers in Transformers

27

conformer. PyTorch implementation of Conformer: Convolution-augmented Transformer for Speech Recognition

18

jaketae.github.io. Personal blog with Jupyter notebooks

15

vit-breast-cancer. Transfer learning pretrained vision transformers for breast histopathology

14

realformer. PyTorch implementation of RealFormer: Transformer Likes Residual Attention

11

graph-neural-ode. Graph neural ordinary differential equations

8

fastapi-bert. Fine-tuning and deploying BERT through FastAPI

8

lm-identifier. A toolkit for identifying pretrained language models from potentially AI-generated text

8

tupe. PyTorch implementation of Rethinking Positional Encoding in Language Pre-training

6

pygrad. Pure Python autograd library based on NumPy

6

auto-tagger. Fine-tuning and zero-shot learning with transformers to automatically tag my study blog posts

5

ml-from-scratch. Machine learning algorithms implemented from scratch with NumPy

5

nn-svd. Neural network compression with SVD

3

res-mlp. PyTorch implementation of ResMLP: Feedforward networks for image classification with data-efficient training

3

image-classifier. Image classifier web application based on MobileNet, built using Flask, TensorFlow, and Matplotlib

2

transformers. 🤗 Transformers: State-of-the-art Natural Language Processing for Pytorch, TensorFlow, and JAX.

1
25
Apply