Multilingual GPT model 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 Paper mGPT: Few Shot Learners Go Multilingual Abstract PDF Languages Model supports 61 languages: ISO codes: Languages: Training Data Statistics Size: 488 Billion UTF characters "General training corpus statistics" Details 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.
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy