We introduce a family of autoregressive GPT-like models with 1.3 billion parameters trained on 61 languages from 25 language families using Wikipedia and Colossal Clean Crawled Corpus.
We reproduce the GPT-3 architecture using GPT-2 sources and the sparse attention mechanism,
Deepspeed
and
Megatron
frameworks allows us to effectively parallelize the training and inference steps. The resulting models show performance on par with the recently released
XGLM
models at the same time covering more languages and enhancing NLP possibilities for low resource languages.
Code
The source code for the mGPT XL model is available on
Github
@misc{https://doi.org/10.48550/arxiv.2204.07580,
doi = {10.48550/ARXIV.2204.07580},
url = {https://arxiv.org/abs/2204.07580},
author = {Shliazhko, Oleh and Fenogenova, Alena and Tikhonova, Maria and Mikhailov, Vladislav and Kozlova, Anastasia and Shavrina, Tatiana},
keywords = {Computation and Language (cs.CL), Artificial Intelligence (cs.AI), FOS: Computer and information sciences, FOS: Computer and information sciences, I.2; I.2.7, 68-06, 68-04, 68T50, 68T01},
title = {mGPT: Few-Shot Learners Go Multilingual},
publisher = {arXiv},
year = {2022},
copyright = {Creative Commons Attribution 4.0 International}
}
Languages
Model supports 61 languages:
ISO codes:
ar he vi id jv ms tl lv lt eu ml ta te hy bn mr hi ur af da en de sv fr it pt ro es el os tg fa ja ka ko th bxr xal mn sw yo be bg ru uk pl my uz ba kk ky tt az cv tr tk tyv sax et fi hu
The model was trained with sequence length 512 using Megatron and Deepspeed libs by
SberDevices
team on a dataset of 600 GB of texts in 61 languages. The model has seen 440 billion BPE tokens in total.
Total training time was around 14 days on 256 Nvidia V100 GPUs.
mGPT huggingface.co is an AI model on huggingface.co that provides mGPT's model effect (), which can be used instantly with this ai-forever mGPT model. huggingface.co supports a free trial of the mGPT model, and also provides paid use of the mGPT. Support call mGPT model through api, including Node.js, Python, http.
mGPT huggingface.co is an online trial and call api platform, which integrates mGPT's modeling effects, including api services, and provides a free online trial of mGPT, you can try mGPT online for free by clicking the link below.
ai-forever mGPT online free url in huggingface.co:
mGPT is an open source model from GitHub that offers a free installation service, and any user can find mGPT on GitHub to install. At the same time, huggingface.co provides the effect of mGPT install, users can directly use mGPT installed effect in huggingface.co for debugging and trial. It also supports api for free installation.