dashstander Goto Github PK

deepspeed

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

demprimary

Scraping tweets about the 2020 Democratic Primary

devinterp

Quantifying degeneracy in toy models

dfa-implemented-python

Deteministic Finite Automaton Implementation in Python Language

didyprog

Differentiable Dynamic Programming

diffuser

Code for the paper "Planning with Diffusion for Flexible Behavior Synthesis"

diffusion-lm

Diffusion-LM

diffusion-retrieval

Use image-text retrieval to augment diffusion models

diffvg

Differentiable Vector Graphics Rasterization

docker-airflow

Docker Apache Airflow

dyck-hopf-algebra

ec

expbert

Representation Engineering with Natural Language Explanations

exploring-contrastive-topology

flaxformer

fnet2d

FNet 2D: Scaling Fourier Transform Token Mixing To Vision

fourier_neural_operator

Use Fourier transform to learn operators in differential equations.

fsa-rust

geomstats

Computations and statistics on manifolds with geometric structures.

git-re-basin

Code release for "Git Re-Basin: Merging Models modulo Permutation Symmetries"

git-re-basin-pytorch

Git Re-Basin: Merging Models modulo Permutation Symmetries in PyTorch

glassy-grokking

glide-text2im

GLIDE: a diffusion-based text-conditional image synthesis model

glip

Grounded Language-Image Pre-training

goldfinch

gpt-neox

An implementation of model parallel autoregressive transformers on GPUs, based on the DeepSpeed library.

graphflow

Deep Learning framework in C++/CUDA that supports symbolic/automatic differentiation, dynamic computation graphs, tensor/matrix operations accelerated by GPU and implementations of various state-of-the-art graph neural networks and other Machine Learning models including Covariant Compositional Networks For Learning Graphs [Risi et al]

guided-diffusion

hidden-transformer-model

homebrewnlp-jax

HomebrewNLP in JAX flavour for maintable, single-host TPU-Training