Pinned Repositories
bitsandbytes
Accessible large language models via k-bit quantization for PyTorch.
carbonneutral
Resources to calculate how to become a carbon neutral lab.
clusterNet
Deep neural network framework for multiple GPUs
ConvE
Convolutional 2D Knowledge Graph Embeddings resources
crowdflower
Code for the Kaggle crowdflower competition
deepnet
Deep neural network implemented with gnumpy/cudamat
public-data
Public data from research
sparse_learning
Sparse learning library and sparse momentum resources.
spodernet
NLP
transformer-xl
TimDettmers's Repositories
TimDettmers/bitsandbytes
Accessible large language models via k-bit quantization for PyTorch.
TimDettmers/ConvE
Convolutional 2D Knowledge Graph Embeddings resources
TimDettmers/sparse_learning
Sparse learning library and sparse momentum resources.
TimDettmers/transformer-xl
TimDettmers/carbonneutral
Resources to calculate how to become a carbon neutral lab.
TimDettmers/spodernet
NLP
TimDettmers/sched
Schedule GPU jobs over ssh.
TimDettmers/accelerate
🚀 A simple way to train and use PyTorch models with multi-GPU, TPU, mixed-precision
TimDettmers/CreditAssignment
Using PageRank to solve credit assignment problems for deep learning contributions.
TimDettmers/AutoDL-Projects
Automated deep learning algorithms implemented in PyTorch or Tensorflow.
TimDettmers/bashmagic
TimDettmers/bitsandbytes-docs
Library for 8-bit optimizers and quantization routines.
TimDettmers/tracker
Tracks time on active windows and other productivity stats.
TimDettmers/transformers_private
TimDettmers/alttab-vim
Vim like selection of applications and windows for unix
TimDettmers/bibtex
Bibtex entries for my papers.
TimDettmers/blog-1
Public repo for HF blog posts
TimDettmers/clusterNet2
Scientific Deep Learning and NLP software for GPU clusters
TimDettmers/DeepSpeed
DeepSpeed is a deep learning optimization library that makes distributed training easy, efficient, and effective.
TimDettmers/DrQA
Reading Wikipedia to Answer Open-Domain Questions
TimDettmers/fairseq
Facebook AI Research Sequence-to-Sequence Toolkit written in Python.
TimDettmers/hotpot
TimDettmers/jiant
jiant is an nlp toolkit
TimDettmers/peft
🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
TimDettmers/pytorch
Tensors and Dynamic neural networks in Python with strong GPU acceleration
TimDettmers/redisk
TimDettmers/rtx_benchmarks
NLP Benchmarks for RTX GPUs.
TimDettmers/slides
Slides from varies talks.
TimDettmers/tensor2tensor
Library of deep learning models and datasets designed to make deep learning more accessible and accelerate ML research.
TimDettmers/transformers
🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.