Data

Tools

Indexes

Applications

Experiments

Open Source Science

puli

Inference code for NYTUD's PULI models. Work in progress.

https://github.com/matyasosvath/puli

Science Score: 44.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • ✓
    CITATION.cff file
    Found CITATION.cff file
  • ✓
    codemeta.json file
    Found codemeta.json file
  • ✓
    .zenodo.json file
    Found .zenodo.json file
  • ○
    DOI references
  • ○
    Academic publication links
  • ○
    Academic email domains
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (6.8%) to scientific vocabulary
Last synced: 10 months ago · JSON representation ·

Repository

Inference code for NYTUD's PULI models. Work in progress.

Basic Info
  • Host: GitHub
  • Owner: matyasosvath
  • License: mit
  • Language: Python
  • Default Branch: master
  • Homepage:
  • Size: 69.3 KB
Statistics
  • Stars: 1
  • Watchers: 1
  • Forks: 0
  • Open Issues: 1
  • Releases: 0
Created almost 2 years ago · Last pushed over 1 year ago
Metadata Files
Readme Contributing License Citation

README.md

PULI Language Models

PULI models - including variations such as PULI GPT-3SX, PULI GPT-2, and PULI BERT-Large - are state-of-the-art language models developed by the Hungarian Research Centre for Linguistics. It is trained on large-scale corpora to support various natural language processing (NLP) tasks. The inference code are freely available for research purposes and can be accessed on the Hugging Face Model Hub under the following repositories.

Currently supported models:

License

This project (not the models!) is licensed under the MIT License. For more information, please contant osvath.matyas@nytud.hun-ren.hu.

Contributing

Contributions are welcome! Please read the CONTRIBUTING.md file for details on how to contribute.

Owner

  • Name: Mátyás
  • Login: matyasosvath
  • Kind: user

Citation (CITATION.cff) 

---
authors:
  - affiliation: Hungarian Research Centre of Linguistics
    family-names: Osváth
    given-names: Mátyás
cff-version: "0.0.1"
keywords:
  - "Transformers"
  - "Large language model"
  - "Autoregressive language model"
  - "Generative Pretrained Transformer"
license: "MIT Licence"
message: "If you use this software, please cite it using these metadata."
repository-code: "https://github.com/matyasosvath/puli"
title: "PULI: Large Language Modeling in PyTorch"
version: "0.0.1"
date-released: 2024-08-31
...

GitHub Events

Total
Last Year

Dependencies

.github/workflows/python-package.yml actions
  • actions/checkout v4 composite
  • actions/setup-python v3 composite
requirements.txt pypi
  • sentencepiece *
  • torch *
  • tqdm *
  • transformers *
setup.py pypi