Hugging Face's logo

ikim-uk-essen
/
geberta-base

Fill-Mask
Transformers
PyTorch
Safetensors
deberta-v2
Inference Endpoints
Model card Files Community
1
amindada commited on
Commit
eda3324
·
1 Parent(s): f4cd3f1

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -10,7 +10,7 @@
10
  GeBERTa is a set of German DeBERTa models developed in a joint effort between the University of Florida, NVIDIA, and IKIM.
11
  The models range in size from 122M to 750M parameters. The pre-training dataset consists of documents from different domains:
12
 
13
- | Domain | Source Data | Data Size | #Docs | #Tokens |
14
  | -------- | ----------- | --------- | ------ | ------- |
15
  | Formal | Wikipedia | 9GB | 2,665,357 | 1.9B |
16
  | Formal | News | 28GB | 12,305,326 | 6.1B |
 
10
  GeBERTa is a set of German DeBERTa models developed in a joint effort between the University of Florida, NVIDIA, and IKIM.
11
  The models range in size from 122M to 750M parameters. The pre-training dataset consists of documents from different domains:
12
 
13
+ | Domain | Dataset | Data Size | #Docs | #Tokens |
14
  | -------- | ----------- | --------- | ------ | ------- |
15
  | Formal | Wikipedia | 9GB | 2,665,357 | 1.9B |
16
  | Formal | News | 28GB | 12,305,326 | 6.1B |