SondreWold

text-graph-generalization

Implementation of the paper "Compositional Generalization with Grounded Language Models", ACL 2024 Findings

bert-in-context

Official implementation of "BERTs are Generative In-Context Learners"

1brc

1️⃣🐝🏎️ The One Billion Row Challenge -- A fun exploration of how quickly 1B rows from a text file can be aggregated with Java

continuous-sparsification

Implementation of Continuous Sparsification, a method for pruning and ticket search in deep networks

modules

The official repository for our paper "Are Neural Nets Modular? Inspecting Functional Modularity Through Differentiable Weight Masks". We develop a method for analyzing emerging functional modularity in neural networks based on differentiable weight masks and use it to point out important issues in current-day neural networks.

Compositional_Subnetworks

Code for the paper Break It Down: Evidence for Structural Compositionality in Neural Networks, presented at NeurIPS 2023

llm.c

LLM training in simple, raw C/CUDA

more-room-for-language

alphageometry

vimtex

VimTeX: A modern Vim and neovim filetype plugin for LaTeX files.

norallm

Suplementary code for the NORA large language models

candle-grey

A dark monochrome colorscheme with a hint of color for vim

vim-no-color-collections

Collection of Vim themes with barely any colors

cmus

Small, fast and powerful console music player for Unix-like operating systems.

rdflib

RDFLib is a Python library for working with RDF, a simple yet powerful language for representing information.

the_gROKe_policy

am-i-compositional

LNN

A `Neural = Symbolic` framework for sound and complete weighted real-value logic

retro

Official repo to On the Generalization Ability of Retrieval-Enhanced Transformers

norbench

Natural language understanding benchmarks for Norwegian

LTNtorch

PyTorch implementation of Logic Tensor Networks, a Neural-Symbolic framework.

brent

This is the repository for a NoDaLiDa 2023 paper on developing a Norwegian retrieval-augmented langauge model

NorQuAD

Norwegian question answering dataset

logictensornetworks

Deep Learning and Logical Reasoning from Data and Knowledge

pyreason

An explainable inference software supporting annotated, real valued, graph based and temporal logic

qagnn

[NAACL 2021] QAGNN: Question Answering using Language Models and Knowledge Graphs 🤖

CoCo-Ex

CoCo-Ex extracts meaningful concepts from natural language texts and maps them to conjunct concept nodes in ConceptNet, utilizing the maximum of relational information stored in the ConceptNet knowledge graph.

COPA-SSE

Repository for Semi-Structured Explanations for COPA (COPA-SSE)

LTNtorch

PyTorch implementation of Logic Tensor Networks, a Neural-Symbolic framework.

arxiv2022-context-injection-stance

This repository includes the code for integrating contextual information for supervised text classification tasks using a dual-encoder approach and information exchange via cross-attention. You can find the paper here: https://arxiv.org/abs/2211.01874