configuration/modeling/tokenization: add various fine-tuned XLM-RoBERTa models...

configuration/modeling/tokenization: add various fine-tuned XLM-RoBERTa models for English, German, Spanish and Dutch (CoNLL datasets)

transformers/configuration_xlm_roberta.py

@@ -27,6 +27,10 @@ logger = logging.getLogger(__name__)
 XLM_ROBERTA_PRETRAINED_CONFIG_ARCHIVE_MAP = {
     'xlm-roberta-base': "https://s3.amazonaws.com/models.huggingface.co/bert/xlm-roberta-base-config.json",
     'xlm-roberta-large': "https://s3.amazonaws.com/models.huggingface.co/bert/xlm-roberta-large-config.json",
+    'xlm-roberta-large-finetuned-conll02-dutch': "https://s3.amazonaws.com/models.huggingface.co/bert/xlm-roberta-large-finetuned-conll02-dutch-config.json",
+    'xlm-roberta-large-finetuned-conll02-spanish': "https://s3.amazonaws.com/models.huggingface.co/bert/xlm-roberta-large-finetuned-conll02-spanish-config.json",
+    'xlm-roberta-large-finetuned-conll03-english': "https://s3.amazonaws.com/models.huggingface.co/bert/xlm-roberta-large-finetuned-conll03-english-config.json",
+    'xlm-roberta-large-finetuned-conll03-german': "https://s3.amazonaws.com/models.huggingface.co/bert/xlm-roberta-large-finetuned-conll03-german-config.json",
 }
 
 

transformers/modeling_xlm_roberta.py

@@ -29,6 +29,10 @@ logger = logging.getLogger(__name__)
 XLM_ROBERTA_PRETRAINED_MODEL_ARCHIVE_MAP = {
     'xlm-roberta-base': "https://s3.amazonaws.com/models.huggingface.co/bert/xlm-roberta-base-pytorch_model.bin",
     'xlm-roberta-large': "https://s3.amazonaws.com/models.huggingface.co/bert/xlm-roberta-large-pytorch_model.bin",
+    'xlm-roberta-large-finetuned-conll02-dutch': "https://s3.amazonaws.com/models.huggingface.co/bert/xlm-roberta-large-finetuned-conll02-dutch-pytorch_model.bin",
+    'xlm-roberta-large-finetuned-conll02-spanish': "https://s3.amazonaws.com/models.huggingface.co/bert/xlm-roberta-large-finetuned-conll02-spanish-pytorch_model.bin",
+    'xlm-roberta-large-finetuned-conll03-english': "https://s3.amazonaws.com/models.huggingface.co/bert/xlm-roberta-large-finetuned-conll03-english-pytorch_model.bin",
+    'xlm-roberta-large-finetuned-conll03-german': "https://s3.amazonaws.com/models.huggingface.co/bert/xlm-roberta-large-finetuned-conll03-german-pytorch_model.bin",
 }
 
 

transformers/tokenization_xlm_roberta.py

@@ -32,6 +32,10 @@ PRETRAINED_VOCAB_FILES_MAP = {
     {
     'xlm-roberta-base': "https://s3.amazonaws.com/models.huggingface.co/bert/xlm-roberta-base-sentencepiece.bpe.model",
     'xlm-roberta-large': "https://s3.amazonaws.com/models.huggingface.co/bert/xlm-roberta-large-sentencepiece.bpe.model",
+    'xlm-roberta-large-finetuned-conll02-dutch': "https://s3.amazonaws.com/models.huggingface.co/bert/xlm-roberta-large-finetuned-conll02-dutch-sentencepiece.bpe.model",
+    'xlm-roberta-large-finetuned-conll02-spanish': "https://s3.amazonaws.com/models.huggingface.co/bert/xlm-roberta-large-finetuned-conll02-spanish-sentencepiece.bpe.model",
+    'xlm-roberta-large-finetuned-conll03-english': "https://s3.amazonaws.com/models.huggingface.co/bert/xlm-roberta-large-finetuned-conll03-english-sentencepiece.bpe.model",
+    'xlm-roberta-large-finetuned-conll03-german': "https://s3.amazonaws.com/models.huggingface.co/bert/xlm-roberta-large-finetuned-conll03-german-sentencepiece.bpe.model",
     }
 }