raruidol

unilm

Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities

mlx

MLX: An array framework for Apple silicon

pyxel

A retro game engine for Python

Qwen

The official repo of Qwen (通义千问) chat & pretrained large language model proposed by Alibaba Cloud.

aima-python

Python implementation of algorithms from Russell And Norvig's "Artificial Intelligence - A Modern Approach"

bertviz

BertViz: Visualize Attention in NLP Models (BERT, GPT2, BART, etc.)

metaseq

Repo for external large-scale work

ml-ane-transformers

Reference implementation of the Transformer architecture optimized for Apple Neural Engine (ANE)

educational

jraph

A Graph Neural Network Library in Jax

TabPFN

Official implementation of the TabPFN paper (https://arxiv.org/abs/2207.01848) and the tabpfn package.

RetNet

An implementation of "Retentive Network: A Successor to Transformer for Large Language Models"

Sudachi

A Japanese Tokenizer for Business

pycantonese

Cantonese Linguistics and NLP

ftcc

Fast Text Classification with Compressors dictionary

RussiaUkraine_weibo_dataset

model-recycling

Ranking of fine-tuned HF models as base models.

setfit-few-shot-classification-sample

acl22-identifying-the-human-values-behind-arguments

Machine Learning scripts for the identification of human values behind arguments.

SubER

SubER - Subtitle Edit Rate

ACL-22

m-arg_multimodal-argumentation-dataset

ML-Argument-Based-Computational-Persuasion

This repo contains the source code and a benchmark for predicting user's utilities with Machine Learning techniques for Computational Persuasion

FairArgumentativeLM

Code & Data for the paper "Fair and Argumentative Language Modeling for Computational Argumentation"

argscichat_project

Official repository of paper "ArgSciChat: A Dataset of Argumentative Conversational Discussions on Scientific Papers"

TYPIC

Multimodal-USElecDeb60To16

Multimodal USElecDeb60To16 dataset - Augmenting pre-trained language models with audio feature embedding for argumentation mining in political debates

MandarinArguments

aif-arg-datasets

The repository containing links, descriptions and references for the datasets from ARG Tech group.

seq-to-seq-catalan

Sequence to sequence language resources for Catalan and for two tasks, namely: Summarization and Machine Translation.