Skip to content

euroeval.dataset_configs.czech

[docs] module euroeval.dataset_configs.czech 

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
"""All Czech dataset configurations used in EuroEval."""

from ..data_models import DatasetConfig
from ..languages import CZECH
from ..tasks import COMMON_SENSE, KNOW, LA, NER, RC, SENT, SUMM

### Official datasets ###

CSFD_SENTIMENT_CONFIG = DatasetConfig(
    name="csfd-sentiment",
    pretty_name="CSFD Sentiment",
    source="EuroEval/csfd-sentiment-mini",
    task=SENT,
    languages=[CZECH],
)

CS_GEC_CONFIG = DatasetConfig(
    name="cs-gec",
    pretty_name="CS-GEC",
    source="EuroEval/cs-gec-mini",
    task=LA,
    languages=[CZECH],
)

PONER_CONFIG = DatasetConfig(
    name="poner",
    pretty_name="PoNER",
    source="EuroEval/poner-mini",
    task=NER,
    languages=[CZECH],
)

SQAD_CONFIG = DatasetConfig(
    name="sqad",
    pretty_name="SQAD",
    source="EuroEval/sqad-mini",
    task=RC,
    languages=[CZECH],
)

CZECH_NEWS_CONFIG = DatasetConfig(
    name="czech-news",
    pretty_name="Czech News",
    source="EuroEval/czech-news-mini",
    task=SUMM,
    languages=[CZECH],
)

UMIMETO_QA_CONFIG = DatasetConfig(
    name="umimeto-qa",
    pretty_name="Umimeto QA",
    source="EuroEval/umimeto-qa",
    task=KNOW,
    languages=[CZECH],
)

HELLASWAG_CS_CONFIG = DatasetConfig(
    name="hellaswag-cs",
    pretty_name="HellaSwag-cs",
    source="EuroEval/hellaswag-cs-mini",
    task=COMMON_SENSE,
    languages=[CZECH],
)


### Unofficial datasets ###

SCALA_CS_CONFIG = DatasetConfig(
    name="scala-cs",
    pretty_name="ScaLA-cs",
    source="EuroEval/scala-cs",
    task=LA,
    languages=[CZECH],
    unofficial=True,
)