![:octocat: :octocat:](https://github.githubassets.com/images/icons/emoji/octocat.png)
-
Tilburg University
- The Netherlands
-
09:34
- 1h ahead - https://javad.pourmostafa.me
- https://orcid.org/0000-0003-2083-1664
- @JPourmostafa
Stars
- All languages
- ASL
- C
- C#
- C++
- CMake
- CSS
- Charity
- Clojure
- CoffeeScript
- Emacs Lisp
- Erlang
- Fortran
- Go
- Groff
- HTML
- Haskell
- Java
- JavaScript
- Jinja
- Jupyter Notebook
- Kotlin
- Lua
- MATLAB
- MDX
- Makefile
- Mathematica
- Objective-C
- PHP
- PLSQL
- Pascal
- Perl
- PostScript
- Python
- QML
- R
- Roff
- Ruby
- Rust
- SCSS
- Scala
- Shell
- Smalltalk
- Swift
- TeX
- TypeScript
- Vim Script
A pip-installable PyTorch implementation of TSMixer, providing an easy-to-use and efficient solution for time-series forecasting.
My HomeAssistant Configuration (Home Assistant Supervised, Debian 10)
(NAACL 2024) Guiding Large Language Models to Post-Edit Machine Translation with Error Annotations
Model, Code & Data for the EMNLP'23 paper "Making Large Language Models Better Data Creators"
Quickly rewrite git repository history (filter-branch replacement)
Site infrastructure for gwern.net. Custom Hakyll website with unique link archiving, popup UX, transclusions/collapses, dark+reader mode, bidirectional backlinks, and typography (sidenotes, dropcap…
Interpretability for sequence generation models 🐛 🔍
A curated list of papers, theses, datasets, and tools related to the application of Machine Learning for Software Engineering
Python API wrapper for Instructure's Canvas LMS. Easily manage courses, users, gradebooks, and more.
Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.
Anonymous Github is a proxy server to support anonymous browsing of Github repositories for open-science code and data.
Tools for evaluating the performance of MT metrics on data from recent WMT metrics shared tasks.
A byte-level decoder architecture that matches the performance of tokenized Transformers.
MAchine Translation Evaluation Online (MATEO)
GEMBA — GPT Estimation Metric Based Assessment
Bicleaner is a parallel corpus classifier/cleaner that aims at detecting noisy sentence pairs in a parallel corpus.
BLEURT is a metric for Natural Language Generation based on transfer learning.
Sync your Outlook and Google calendars
Track and predict the energy consumption and carbon footprint of training deep learning models.
Ensembling Hugging Face transformers made easy
An Emacs framework for the stubborn martian hacker
Critical difference diagram with Wilcoxon-Holm post-hoc analysis.
AutoPrompt: Automatic Prompt Construction for Masked Language Models.
Large Language Model Text Generation Inference