language:
- 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
license: apache-2.0
tags:
- multilingual
- PyTorch
- Transformers
- gpt3
- gpt2
- Deepspeed
- Megatron
datasets:
- mc4
- wikipedia
pipeline_tag: text-generation
thumbnail: https://github.com/sberbank-ai/mgpt
model-index:
- name: mGPT
results:
- task:
type: text-generation
name: Text Generation
dataset:
name: AI2 Reasoning Challenge (25-Shot)
type: ai2_arc
config: ARC-Challenge
split: test
args:
num_few_shot: 25
metrics:
- type: acc_norm
value: 23.81
name: normalized accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ai-forever/mGPT
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: HellaSwag (10-Shot)
type: hellaswag
split: validation
args:
num_few_shot: 10
metrics:
- type: acc_norm
value: 26.37
name: normalized accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ai-forever/mGPT
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: MMLU (5-Shot)
type: cais/mmlu
config: all
split: test
args:
num_few_shot: 5
metrics:
- type: acc
value: 25.17
name: accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ai-forever/mGPT
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: TruthfulQA (0-shot)
type: truthful_qa
config: multiple_choice
split: validation
args:
num_few_shot: 0
metrics:
- type: mc2
value: 39.62
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ai-forever/mGPT
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: Winogrande (5-shot)
type: winogrande
config: winogrande_xl
split: validation
args:
num_few_shot: 5
metrics:
- type: acc
value: 50.67
name: accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ai-forever/mGPT
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: GSM8k (5-shot)
type: gsm8k
config: main
split: test
args:
num_few_shot: 5
metrics:
- type: acc
value: 0
name: accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=ai-forever/mGPT
name: Open LLM Leaderboard
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
@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
Languages:
Arabic, Hebrew, Vietnamese, Indonesian, Javanese, Malay, Tagalog, Latvian, Lithuanian, Basque, Malayalam, Tamil, Telugu, Armenian, Bengali, Marathi, Hindi, Urdu, Afrikaans, Danish, English, German, Swedish, French, Italian, Portuguese, Romanian, Spanish, Greek, Ossetian, Tajik, Persian, Japanese, Georgian, Korean, Thai, Buryat, Kalmyk, Mongolian, Swahili, Yoruba, Belarusian, Bulgarian, Russian, Ukrainian, Polish, Burmese, Uzbek, Bashkir, Kazakh, Kyrgyz, Tatar, Azerbaijani, Chuvash, Turkish, Turkmen, Tuvan, Yakut, Estonian, Finnish, Hungarian
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.
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 27.61 |
| AI2 Reasoning Challenge (25-Shot) | 23.81 |
| HellaSwag (10-Shot) | 26.37 |
| MMLU (5-Shot) | 25.17 |
| TruthfulQA (0-shot) | 39.62 |
| Winogrande (5-shot) | 50.67 |
| GSM8k (5-shot) | 0.00 |