Pinned Repositories
BPE-Tokenizer
Buddi.ai
clip-retriever
configs
configs
CropCast
digits
MNIST classification model using numpy
docs
image-search
kaze
Whisper-MOE
A generalist model that performs diverse cross-attention tasks like text-to-speech, speech-to-text, and translation.It takes Fine-tunes eight Whisper models with TTT MLP backbones, using 3000-token context lengths and an MOE router for dynamic expert selection. Effective for handling of large datasets and lifelong learning.
wisebreadloaf's Repositories
wisebreadloaf/Whisper-MOE
A generalist model that performs diverse cross-attention tasks like text-to-speech, speech-to-text, and translation.It takes Fine-tunes eight Whisper models with TTT MLP backbones, using 3000-token context lengths and an MOE router for dynamic expert selection. Effective for handling of large datasets and lifelong learning.
wisebreadloaf/kaze
wisebreadloaf/BPE-Tokenizer
wisebreadloaf/Buddi.ai
wisebreadloaf/clip-retriever
wisebreadloaf/configs
configs
wisebreadloaf/CropCast
wisebreadloaf/digits
MNIST classification model using numpy
wisebreadloaf/docs
wisebreadloaf/image-search
wisebreadloaf/wisebreadloaf
Config files for my GitHub profile.
wisebreadloaf/imgtoage
wisebreadloaf/Simba
A simpler Pytorch + Zeta Implementation of the paper: "SiMBA: Simplified Mamba-based Architecture for Vision and Multivariate Time series"
wisebreadloaf/stable-diffusion
wisebreadloaf/Variational-Auto-encoder
MLP and CNN based Variational auto encoders written in pytorch
wisebreadloaf/Variational-Autoencoder-demo
wisebreadloaf/ViTAR
Implementation of ViTaR: ViTAR: Vision Transformer with Any Resolution in PyTorch