Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
ufal
/
robeczech-base
like
10
Fill-Mask
Transformers
PyTorch
google-tensorflow
TensorFlow
Safetensors
Czech
roberta
RobeCzech
Czech
RoBERTa
ÚFAL
Inference Endpoints
arxiv:
2105.11314
License:
cc-by-nc-sa-4.0
Model card
Files
Files and versions
Community
4
Train
Deploy
Use this model
main
robeczech-base
4 contributors
History:
19 commits
Milan Straka
Explicitly set model_max_length in the tokenizer config.
98c2170
2 days ago
scripts-for-generating-v1.1
Add scripts used to generate v1.1.
9 months ago
.gitattributes
744 Bytes
Adding `safetensors` variant of this model (#3)
over 1 year ago
LICENSE
20.9 kB
Add explicit LICENSE.
over 3 years ago
README.md
7.1 kB
Describe that we dropped the pooler in v1.1.
9 months ago
config.json
516 Bytes
Release version 1.1 of RobeCzech.
9 months ago
merges.txt
601 kB
Add RobeCzech checkpoint.
over 3 years ago
model.safetensors
504 MB
LFS
Release version 1.1 of RobeCzech.
9 months ago
pytorch_model.bin
504 MB
LFS
Release version 1.1 of RobeCzech.
9 months ago
special_tokens_map.json
963 Bytes
Add serialized fast tokenizer.
over 1 year ago
tf_model.h5
666 MB
LFS
Release version 1.1 of RobeCzech.
9 months ago
tokenizer.json
1.66 MB
Release version 1.1 of RobeCzech.
9 months ago
tokenizer_config.json
209 Bytes
Explicitly set model_max_length in the tokenizer config.
2 days ago
vocab.json
955 kB
Release version 1.1 of RobeCzech.
9 months ago