First version of the model

README.md

@@ -6,7 +6,7 @@ tags:
 datasets:
 - dcep europarl jrc-acquis
 widget:
-- text: "i) oiseaux sortant pour abattage"
+- text: "Les États membres notifient ces dispositions à la Commission au plus tard à la date mentionnée à l'article 15 et toute modification ultérieure les concernant dans les meilleurs délais."
 
 ---
 
@@ -38,7 +38,7 @@ tokenizer=AutoTokenizer.from_pretrained(pretrained_model_name_or_path = "SEBIS/l
     device=0
 )
 
-fr_text = "i) oiseaux sortant pour abattage"
+fr_text = "Les États membres notifient ces dispositions à la Commission au plus tard à la date mentionnée à l'article 15 et toute modification ultérieure les concernant dans les meilleurs délais."
 
 pipeline([fr_text], max_length=512)
 ```
@@ -49,12 +49,12 @@ The legal_t5_small_trans_fr_de 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
 
+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