README.md

metadata

language:
  - hy
  - en
  - ru
license: mit
tags:
  - gpt3
  - transformers
  - mgpt

🇦🇲 Armenian mGPT 1.3B

Language model for Armenian. Model has 1.3B parameters as you can guess from it's name.

Armenian belongs to Indo-European language family. It's a very ancient language with approximately 7 million speakers. Here are some facts about it:

1. It has its own unique script.
2. It dates back to the 5th century AD.
3. The Armenian alphabet was created by Mesrop Mashtots.

Technical details

It's one of the models derived from the base mGPT-XL (1.3B) model (see the list below) which was originally trained on the 61 languages from 25 language families using Wikipedia and C4 corpus.

We've found additional data for 23 languages most of which are considered as minor and decided to further tune the base model. Armenian mGPT 1.3B was trained for another 500000 steps with batch_size=4 and context window of 2048 tokens on 1 A100.

Final perplexity for this model on validation is 1.73.

Chart of the training loss:

Other mGPT-1.3B models

• mGPT-1.3B-azerbaijan
• mGPT-1.3B-bashkir
• mGPT-1.3B-belorussian
• mGPT-1.3B-bulgarian
• mGPT-1.3B-buryat
• mGPT-1.3B-chuvash
• mGPT-1.3B-georgian
• mGPT-1.3B-kalmyk
• mGPT-1.3B-kazakh
• mGPT-1.3B-kirgiz
• mGPT-1.3B-mari
• mGPT-1.3B-mongol
• mGPT-1.3B-ossetian
• mGPT-1.3B-persian
• mGPT-1.3B-romanian
• mGPT-1.3B-tajik
• mGPT-1.3B-tatar
• mGPT-1.3B-turkmen
• mGPT-1.3B-tuvan
• mGPT-1.3B-ukranian
• mGPT-1.3B-uzbek
• mGPT-1.3B-yakut

Feedback

If you'll found a bug of have additional data to train model on your language — please, give us feedback.

Model will be improved over time. Stay tuned!