SEBIS
/

legal_t5_small_trans_de_sv

Text2Text Generation Transformers PyTorch JAX t5 translation Deustch Swedish model Inference Endpoints text-generation-inference

Model card Files Files and versions Community

Mainak Manna commited on Jan 29, 2021

Commit

9842ea7

•

1 Parent(s): 490b220

First version of the model

Files changed (1) hide show

README.md +4 -4

README.md CHANGED Viewed

@@ -6,7 +6,7 @@ tags:
 datasets:
 - dcep europarl jrc-acquis
 widget:
-- text: "unter Hinweis auf die von Vizepräsident Rehn am 23. November 2011 im Ausschuss für Wirtschaft und Währung abgegebene Erläuterung des Themas und die Aussprache mit dem deutschen Sachverständigenrat für Wirtschaft über den europäischen Schuldentilgungsfonds am 29. November 2011,"
 ---
@@ -38,7 +38,7 @@ tokenizer=AutoTokenizer.from_pretrained(pretrained_model_name_or_path = "SEBIS/l
     device=0
 )
-de_text = "unter Hinweis auf die von Vizepräsident Rehn am 23. November 2011 im Ausschuss für Wirtschaft und Währung abgegebene Erläuterung des Themas und die Aussprache mit dem deutschen Sachverständigenrat für Wirtschaft über den europäischen Schuldentilgungsfonds am 29. November 2011,"
 pipeline([de_text], max_length=512)
 ```
@@ -49,12 +49,12 @@ The legal_t5_small_trans_de_sv model was trained on [JRC-ACQUIS](https://wt-publ
 ## Training procedure
-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.
 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.
 ### Preprocessing
 ### Pretraining

 datasets:
 - dcep europarl jrc-acquis
 widget:
+- text: "Betrifft: Leader-Programm"
 ---
     device=0
 )
+de_text = "Betrifft: Leader-Programm"
 pipeline([de_text], max_length=512)
 ```
 ## Training procedure
 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.
 ### Preprocessing
+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.
 ### Pretraining