README.md

metadata

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

☕ Tatar mGPT 1.3B

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

Tatar belongs to Turkic language family. It's a very resonant language with approximately 5.3 million speakers. Here are some facts about it:

1. Spoken primarily by the Tatars, mainly in the Republic of Tatarstan in Russia.
2. Historically, it has used both the Arabic and Cyrillic scripts, but the Latin script is also gaining popularity.
3. The Tatars have a rich history, notably their association with the Golden Horde in the 13th-15th centuries.

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. Tatar mGPT 1.3B was trained for another 5000 steps with batch_size=4 and context window of 2048 tokens on 1 A100.

Final perplexity for this model on validation is 3.69.

Chart of the training loss and perplexity:

Other mGPT-1.3B models

• 🇦🇲 mGPT-1.3B Armenian
• 🇦🇿 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 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!