Mainak Manna commited on
Commit
2b61726
1 Parent(s): 4d3bf2f

First version of the model

Browse files
Files changed (1) hide show
  1. README.md +4 -4
README.md CHANGED
@@ -6,7 +6,7 @@ tags:
6
  datasets:
7
  - dcep europarl jrc-acquis
8
  widget:
9
- - text: "Dies führt zu einer unverhältnismäßigen Überbeanspruchung der administrativen Kapazität."
10
 
11
  ---
12
 
@@ -38,7 +38,7 @@ tokenizer=AutoTokenizer.from_pretrained(pretrained_model_name_or_path = "SEBIS/l
38
  device=0
39
  )
40
 
41
- de_text = "Dies führt zu einer unverhältnismäßigen Überbeanspruchung der administrativen Kapazität."
42
 
43
  pipeline([de_text], max_length=512)
44
  ```
@@ -49,12 +49,12 @@ The legal_t5_small_trans_de_cs model was trained on [JRC-ACQUIS](https://wt-publ
49
 
50
  ## Training procedure
51
 
52
- An unigram model trained with 88M lines of text from the parallel corpus (of all possible language pairs) to get the vocabulary (with byte pair encoding), which is used with this model.
53
-
54
  The model was trained on a single TPU Pod V3-8 for 250K steps in total, using sequence length 512 (batch size 4096). It has a total of approximately 220M parameters and was trained using the encoder-decoder architecture. The optimizer used is AdaFactor with inverse square root learning rate schedule for pre-training.
55
 
56
  ### Preprocessing
57
 
 
 
58
  ### Pretraining
59
 
60
 
 
6
  datasets:
7
  - dcep europarl jrc-acquis
8
  widget:
9
+ - text: "17. empfiehlt die Einführung einer spezifischen Strategie zur Unterstützung neuer und demokratisch gewählter Parlamente im Hinblick auf eine dauerhafte Verankerung von Demokratie, Rechtsstaatlichkeit und guter Staatsführung;"
10
 
11
  ---
12
 
 
38
  device=0
39
  )
40
 
41
+ de_text = "17. empfiehlt die Einführung einer spezifischen Strategie zur Unterstützung neuer und demokratisch gewählter Parlamente im Hinblick auf eine dauerhafte Verankerung von Demokratie, Rechtsstaatlichkeit und guter Staatsführung;"
42
 
43
  pipeline([de_text], max_length=512)
44
  ```
 
49
 
50
  ## Training procedure
51
 
 
 
52
  The model was trained on a single TPU Pod V3-8 for 250K steps in total, using sequence length 512 (batch size 4096). It has a total of approximately 220M parameters and was trained using the encoder-decoder architecture. The optimizer used is AdaFactor with inverse square root learning rate schedule for pre-training.
53
 
54
  ### Preprocessing
55
 
56
+ An unigram model trained with 88M lines of text from the parallel corpus (of all possible language pairs) to get the vocabulary (with byte pair encoding), which is used with this model.
57
+
58
  ### Pretraining
59
 
60