julien-c HF staff commited on
Commit
8293c4a
β€’
1 Parent(s): 30c3fdb

Migrate model card from transformers-repo

Browse files

Read announcement at https://discuss.huggingface.co/t/announcement-all-model-cards-will-be-migrated-to-hf-co-model-repos/2755
Original file history: https://github.com/huggingface/transformers/commits/master/model_cards/dbmdz/bert-base-german-uncased/README.md

Files changed (1) hide show
  1. README.md +71 -0
README.md ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language: de
3
+ license: mit
4
+ ---
5
+
6
+ # πŸ€— + πŸ“š dbmdz German BERT models
7
+
8
+ In this repository the MDZ Digital Library team (dbmdz) at the Bavarian State
9
+ Library open sources another German BERT models πŸŽ‰
10
+
11
+ # German BERT
12
+
13
+ ## Stats
14
+
15
+ In addition to the recently released [German BERT](https://deepset.ai/german-bert)
16
+ model by [deepset](https://deepset.ai/) we provide another German-language model.
17
+
18
+ The source data for the model consists of a recent Wikipedia dump, EU Bookshop corpus,
19
+ Open Subtitles, CommonCrawl, ParaCrawl and News Crawl. This results in a dataset with
20
+ a size of 16GB and 2,350,234,427 tokens.
21
+
22
+ For sentence splitting, we use [spacy](https://spacy.io/). Our preprocessing steps
23
+ (sentence piece model for vocab generation) follow those used for training
24
+ [SciBERT](https://github.com/allenai/scibert). The model is trained with an initial
25
+ sequence length of 512 subwords and was performed for 1.5M steps.
26
+
27
+ This release includes both cased and uncased models.
28
+
29
+ ## Model weights
30
+
31
+ Currently only PyTorch-[Transformers](https://github.com/huggingface/transformers)
32
+ compatible weights are available. If you need access to TensorFlow checkpoints,
33
+ please raise an issue!
34
+
35
+ | Model | Downloads
36
+ | -------------------------------- | ---------------------------------------------------------------------------------------------------------------
37
+ | `bert-base-german-dbmdz-cased` | [`config.json`](https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-german-dbmdz-cased-config.json) β€’ [`pytorch_model.bin`](https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-german-dbmdz-cased-pytorch_model.bin) β€’ [`vocab.txt`](https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-german-dbmdz-cased-vocab.txt)
38
+ | `bert-base-german-dbmdz-uncased` | [`config.json`](https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-german-dbmdz-uncased-config.json) β€’ [`pytorch_model.bin`](https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-german-dbmdz-uncased-pytorch_model.bin) β€’ [`vocab.txt`](https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-german-dbmdz-uncased-vocab.txt)
39
+
40
+ ## Usage
41
+
42
+ With Transformers >= 2.3 our German BERT models can be loaded like:
43
+
44
+ ```python
45
+ from transformers import AutoModel, AutoTokenizer
46
+
47
+ tokenizer = AutoTokenizer.from_pretrained("dbmdz/bert-base-german-cased")
48
+ model = AutoModel.from_pretrained("dbmdz/bert-base-german-cased")
49
+ ```
50
+
51
+ ## Results
52
+
53
+ For results on downstream tasks like NER or PoS tagging, please refer to
54
+ [this repository](https://github.com/stefan-it/fine-tuned-berts-seq).
55
+
56
+ # Huggingface model hub
57
+
58
+ All models are available on the [Huggingface model hub](https://huggingface.co/dbmdz).
59
+
60
+ # Contact (Bugs, Feedback, Contribution and more)
61
+
62
+ For questions about our BERT models just open an issue
63
+ [here](https://github.com/dbmdz/berts/issues/new) πŸ€—
64
+
65
+ # Acknowledgments
66
+
67
+ Research supported with Cloud TPUs from Google's TensorFlow Research Cloud (TFRC).
68
+ Thanks for providing access to the TFRC ❀️
69
+
70
+ Thanks to the generous support from the [Hugging Face](https://huggingface.co/) team,
71
+ it is possible to download both cased and uncased models from their S3 storage πŸ€—