Alham Fikri Aji's repositories

paracotta-paraphrase

Synthetic multilingual paraphrase data

summerschool-KD-PEFT

Mexican NLP 2024 Summerschool Tutorial on Knowledge Distillation and Parameter Efficient Finetuning

Stargazers:6Issues:0Issues:0
Language:JavaScriptLicense:MITStargazers:2Issues:2Issues:0

Marian-transfer

Transfer learning experiment demo with Marian

Language:PLSQLStargazers:1Issues:3Issues:0

acl-anthology

Data and software for building the ACL Anthology.

Language:PythonLicense:Apache-2.0Stargazers:0Issues:1Issues:0

ARBML

Implementation of many Arabic NLP and ML projects. Providing real time experience using many interfaces like web, command line and notebooks.

Language:JavaScriptLicense:MITStargazers:0Issues:1Issues:0

data_tooling

Tools for managing datasets for governance and training.

Language:HTMLLicense:Apache-2.0Stargazers:0Issues:0Issues:0

DataLab

The unified platform for data-related resources.

Language:PythonLicense:Apache-2.0Stargazers:0Issues:1Issues:0

datasets

🤗 The largest hub of ready-to-use datasets for ML models with fast, easy-to-use and efficient data manipulation tools

Language:PythonLicense:Apache-2.0Stargazers:0Issues:1Issues:0

evaluation-robustness-consistency

Tools for evaluating model robustness and consistency

Language:PythonLicense:NOASSERTIONStargazers:0Issues:1Issues:0
License:GPL-2.0Stargazers:0Issues:0Issues:0

id-nlp-resource

A list of Indonesian NLP resources.

Stargazers:0Issues:0Issues:0

indolem

IndoLEM is a comprehensive Indonesian NLU benchmark, comprising three pillars NLP task: morpho-syntax, semantic, and discourse. Presented in COLING 2020.

Stargazers:0Issues:0Issues:0

indonesian-mt-data

Benchmarking Multidomain English-Indonesian Machine Translation

Language:RoffStargazers:0Issues:1Issues:0

intgemm

int8_t and int16_t matrix multiply based on https://arxiv.org/abs/1705.01991

License:NOASSERTIONStargazers:0Issues:0Issues:0

karonese

Karonese dataset

Stargazers:0Issues:1Issues:0

lm-evaluation-harness

A framework for few-shot evaluation of autoregressive language models.

Language:PythonLicense:MITStargazers:0Issues:0Issues:0
Language:C++License:MITStargazers:0Issues:0Issues:0

mosesdecoder

Moses, the machine translation system

Language:RoffLicense:LGPL-2.1Stargazers:0Issues:1Issues:0
Language:PythonLicense:Apache-2.0Stargazers:0Issues:1Issues:0

nusa-catalogue

Dataset Catalogue Homepage for Indonesian Languages

Language:JavaScriptLicense:Apache-2.0Stargazers:0Issues:1Issues:0

promptsource

Toolkit for creating, sharing and using natural language prompts.

Language:PythonLicense:Apache-2.0Stargazers:0Issues:1Issues:0

rosie

Base content for AIML 2.0 chatbot

License:GPL-3.0Stargazers:0Issues:1Issues:0
Stargazers:0Issues:0Issues:0

Semantic_Relatedness_SemEval2024

SemEval 2024 Task 1 : Textual Semantic Relatedness

Language:Jupyter NotebookStargazers:0Issues:0Issues:0
Language:PythonStargazers:0Issues:1Issues:0

stif-indonesia

Implementation of "Semi-Supervised Low-Resource Style Transfer of Indonesian Informal to Formal Language with Iterative Forward-Translation". TBD

Language:ForthLicense:MITStargazers:0Issues:1Issues:0
Language:PythonStargazers:0Issues:1Issues:0

variant-lite

variant lite - A C++17-like variant, a type-safe union for C++98, C++11 and later in a single-file header-only library

License:BSL-1.0Stargazers:0Issues:0Issues:0

xmtf

Crosslingual Generalization through Multitask Finetuning

Stargazers:0Issues:0Issues:0