jaketae

Megatron-DeepSpeed

Ongoing research training transformer language models at scale, including: BERT & GPT-2

deep-malware-detection

A neural approach to malware detection in portable executables

ensemble-transformers

Ensembling Hugging Face transformers made easy

fnet

PyTorch implementation of FNet: Mixing Tokens with Fourier transforms

g-mlp

PyTorch implementation of Pay Attention to MLPs

koclip

KoCLIP: Korean port of OpenAI CLIP, in Flax

storyteller

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

wordwise

N-gram keyword extraction using spaCy and pretrained language models

editts

Official implementation of EdiTTS: Score-based Editing for Controllable Text-to-Speech (INTERSPEECH 2022)

mlp-singer

Official implementation of MLP Singer: Towards Rapid Parallel Korean Singing Voice Synthesis (IEEE MLSP 2021)

jaketae/storyteller

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

jaketae/koclip

KoCLIP: Korean port of OpenAI CLIP, in Flax

jaketae/deep-malware-detection

A neural approach to malware detection in portable executables

jaketae/wordwise

N-gram keyword extraction using spaCy and pretrained language models

jaketae/ensemble-transformers

Ensembling Hugging Face transformers made easy

jaketae/g-mlp

PyTorch implementation of Pay Attention to MLPs

jaketae/fnet

PyTorch implementation of FNet: Mixing Tokens with Fourier transforms

jaketae/param-share-transformer

PyTorch implementation of Lessons on Parameter Sharing across Layers in Transformers

jaketae/alibi

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

jaketae/mlp-mixer

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

jaketae/jaketae.github.io

Personal blog with Jupyter notebooks

jaketae/realformer

PyTorch implementation of RealFormer: Transformer Likes Residual Attention

jaketae/lm-identifier

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

jaketae/tupe

PyTorch implementation of Rethinking Positional Encoding in Language Pre-training

jaketae/vit-breast-cancer

Transfer learning pretrained vision transformers for breast histopathology

jaketae/graph-neural-ode

Graph neural ordinary differential equations

jaketae/transformers

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

jaketae/accelerate

🚀 A simple way to train and use PyTorch models with multi-GPU, TPU, mixed-precision

jaketae/datasets

🤗 Fast, efficient, open-access datasets and evaluation metrics in PyTorch, TensorFlow, NumPy and Pandas

jaketae/diffusers

🤗 Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch

jaketae/fairseq

Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

jaketae/H3

Language Modeling with the H3 State Space Model

jaketae/hillhouse

Reimagining the newly constructed Hillhouse Avenue of Yale University

jaketae/ivy

The Unified Machine Learning Framework

jaketae/jaketae

jaketae/nn-svd

Neural network compression with SVD

jaketae/promptsource

Toolkit for collecting and applying prompts

jaketae/pytorch

Tensors and Dynamic neural networks in Python with strong GPU acceleration

jaketae/speechbrain

A PyTorch-based Speech Toolkit

jaketae/TTS

🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production