mgsm
Datasets
All datasets matching “mgsm”mgsm
Dataset Card for MGSM
Dataset Summary
Multilingual Grade School Math Benchmark (MGSM) is a benchmark of grade-school math problems, proposed in the paper Language models are multilingual chain-of-thought reasoners.
The same 250 problems from GSM8K are each translated via human annotators in 10 languages. The 10 languages are:
Spanish
French
German
Russian
Chinese
Japanese
Thai
Swahili
Bengali
Telugu
GSM8K (Grade School Math 8K) is a dataset of 8.5K high quality… See the full description on the dataset page: https://huggingface.co/datasets/juletxara/mgsm.mgsm-gold
MGSM Gold - Multilingual Grade School Math
This dataset contains the MGSM (Multilingual Grade School Math) benchmark - 250 math word problems translated into 10 languages.
Attribution
This dataset is derived from juletxara/mgsm
Original source: google-research/url-nlp/mgsm
Usage
from datasets import load_dataset
# Load German test set
dataset = load_dataset("alibashir/mgsm-gold", "de")
print(dataset["test"][0])
Languages
Code
Language… See the full description on the dataset page: https://huggingface.co/datasets/alibashir/mgsm-gold.mgsm
Dataset Card for MGSM
Dataset Summary
Copy and merge of this MGSM Dataset, Catalan version, Basque version, Galician version, but in training samples we removed the prompt formatting, e.g. removed Question: ... in question field or Answer: ... in answer field.
Multilingual Grade School Math Benchmark (MGSM) is a benchmark of grade-school math problems, proposed in the paper Language models are multilingual chain-of-thought reasoners.
The same 250 problems from GSM8K are… See the full description on the dataset page: https://huggingface.co/datasets/jbross-ibm-research/mgsm.global-mgsm
Global-MGSM
Dataset Description
Global-MGSM is a unified multilingual grade-school math benchmark built from the Multilingual Grade School Math (MGSM) benchmark and its extensions. Each language is provided as a separate config (subset). All language codes use ISO 639-1 two-letter codes.
Languages (41 configs)
Code
Language
Code
Language
Code
Language
ar
Arabic
bn
Bengali
ca
Catalan
cs
Czech
cy
Welsh
de
German
el
Greek
en
English
es
Spanish
eu… See the full description on the dataset page: https://huggingface.co/datasets/CohereLabs/global-mgsm.MGSM8KInstruct_Crossmgsm_mtMultilingual Grade School Math Benchmark (MGSM) is a benchmark of grade-school math problems, proposed in the paper [Language models are multilingual chain-of-thought reasoners](http://arxiv.org/abs/2210.03057).
The same 250 problems from [GSM8K](https://arxiv.org/abs/2110.14168) are each translated via human annotators in 10 languages. The 10 languages are:
- Spanish
- French
- German
- Russian
- Chinese
- Japanese
- Thai
- Swahili
- Bengali
- Telugu
You can find the input and targets for each of the ten languages (and English) as `.tsv` files.
We also include few-shot exemplars that are also manually translated from each language in `exemplars.py`.