Downloads · 30 days
123
2% of all-time downloads
AI-Sweden-Models/bert-large-nordic-pile-1M-steps
bert-large-nordic-pile-1M-steps is a fill-mask model from AI-Sweden-Models. Use it when you need the model to fill a missing word. It is set up for transformers.
This model is trained on the Swedish subset of the Nordic Pile corpus using the Wafer-Scale Engine (WSE).
Downloads · 30 days
123
2% of all-time downloads
All-time downloads
6K
Public
Repo size
5.2 GB
Likes
3
Public
Click a slice to open those files.
.bin1.7 GB · 100%
From the Hugging Face model README
This model is trained on the Swedish subset of the Nordic Pile corpus using the Wafer-Scale Engine (WSE).
from transformers import pipeline
classifier = pipeline("fill-mask", model="AI-Sweden-Models/bert-large-nordic-pile-1M-steps")
classifier("Stockholm är Sveriges [MASK].")
[{'score': 0.6612114906311035,
'token': 21168,
'token_str': 'huvudstad',
'sequence': 'Stockholm är Sveriges huvudstad.'},
{'score': 0.06771031022071838,
'token': 7625,
'token_str': 'hjärta',
'sequence': 'Stockholm är Sveriges hjärta.'},
{'score': 0.040731027722358704,
'token': 40158,
'token_str': 'framsida',
'sequence': 'Stockholm är Sveriges framsida.'},
{'score': 0.03236057981848717,
'token': 58649,
'token_str': 'mittpunkt',
'sequence': 'Stockholm är Sveriges mittpunkt.'},
{'score': 0.018861057236790657,
'token': 37202,
'token_str': 'navel',
'sequence': 'Stockholm är Sveriges navel.'}]