fheinsen's Stars
sustcsonglin/flash-linear-attention
Efficient implementations of state-of-the-art linear attention models in Pytorch and Triton
glassroom/heinsen_position_embeddings
Reference implementation of "Encoding Position by Decaying and Updating Different Exponentiated States Differently," as proposed by Franz A. Heinsen in March 2024
glassroom/heinsen_attention
Reference implementation of "Softmax Attention with Constant Cost per Token" (Heinsen, 2024)
ollama/ollama
Get up and running with Llama 3, Mistral, Gemma 2, and other large language models.
johnryan465/pscan
glassroom/heinsen_sequence
Code implementing "Efficient Parallelization of a Ubiquitious Sequential Computation" (Heinsen, 2023)
glassroom/heinsen_tree
Reference implementation of "Tree Methods for Hierarchical Classification in Parallel" (Heinsen, 2022) in PyTorch.
glassroom/heinsen_routing
Reference implementation of "An Algorithm for Routing Vectors in Sequences" (Heinsen, 2022) and "An Algorithm for Routing Capsules in All Domains" (Heinsen, 2019), for composing deep neural networks.
acburigo/CapsNet
CapsNet (from "Dynamic Routing Between Capsules") implemented in pytorch.
sebastianruder/NLP-progress
Repository to track the progress in Natural Language Processing (NLP), including the datasets and the current state-of-the-art for the most common NLP tasks.
facebookresearch/fairseq
Facebook AI Research Sequence-to-Sequence Toolkit written in Python.
facebookresearch/fairseq-lua
Facebook AI Research Sequence-to-Sequence Toolkit
glassroom/git-gpg
Use git on an untrusted server via a GPG-encrypted repository.
rustyio/BinaryVice
BinaryVice is better than term_to_binary/1 at serializing structured Erlang data.
rustyio/BERT-JS
Javascript implementation of BERT serialization (Binary ERlang Term).
rustyio/sync
On-the-fly recompiling and reloading in Erlang. Code without friction.
rustyio/super-imap
SuperIMAP - Monitor inboxes for incoming email, at scale.