Pinned Repositories
biomedical
Tools for curating biomedical training data for large-scale language modeling
formal-algos-transformers
Implementations based on https://arxiv.org/abs/2207.09238
hcc_risk_models
Hierarchical Condition Category (HCC) Risk Models from the Centers for Medicare and Medicaid Services (CMS) and the Department of Health and Human Services (HHS)
hilbertcurve
maps between 1-D space filling hilbert curve and N-D coordinates
keybert-service
service to extract keywords from text using keybert
mldev
rabacus
Rabacus is a `Python <http://www.python.org>`_ package for performing analytic radiative transfer calculations in simple geometries relevant to cosmology and astrophysics. It also contains tools to calculate cosmological quantities such as the power spectrum and mass function.
sphray
THIS CODE IS HERE FOR ARCHIVAL PURPOSES AND IS NOT MAINTAINED
kwnlp-dump-downloader
Utilities for downloading and checking the status of Wikimedia dumps.
qwikidata
Python tools for interacting with Wikidata
galtay's Repositories
galtay/hilbertcurve
maps between 1-D space filling hilbert curve and N-D coordinates
galtay/hacdc
galtay/lamo
galtay/mldev
galtay/awesome-neurips-2023
Conference schedule, top papers, and analysis of the data for NeurIPS 2023!
galtay/dcaf_case_management
Rails-based case management system for abortion funds
galtay/flash-attention
Fast and memory-efficient exact attention
galtay/galtay.github.io
Website
galtay/kepler-mapper
KeplerMapper is a Python class for visualization of high-dimensional data and 3-D point cloud data.
galtay/kor
LLMEOW 😽
galtay/langchain
⚡ Building applications with LLMs through composability ⚡
galtay/lcelexplore
Langchain Expression Language Exploration
galtay/legisplain
galtay/llm-foundry-hyperdemocracy
LLM training code for MosaicML foundation models
galtay/llm-toolkit
langchain stuff
galtay/mimic
tools for working with the MIMIC biomedical dataset
galtay/mlbydo
HacDC ML by Doing
galtay/mosaicml-examples
Fast and flexible reference benchmarks
galtay/nanoGPT
The simplest, fastest repository for training/finetuning medium-sized GPTs.
galtay/nextgenlp
Extensions on tools first developed for Hack4NF 2022
galtay/nomic
Interact, analyze and structure massive text, image, embedding, audio and video datasets
galtay/pmc
Tools for working with PubMed Central
galtay/prelude
Prelude is an enhanced Emacs 25.1+ distribution that should make your experience with Emacs both more pleasant and more powerful.
galtay/streamlit-example
Example Streamlit app that you can fork to test out share.streamlit.io
galtay/test_bigbio_st
galtay/text-iter-benchmarks
galtay/train_lms
Scripts for training language models
galtay/trl
Train transformer language models with reinforcement learning.
galtay/vespa_examples
galtay/vllm-scripts