soft launch distilroberta

transformers/configuration_roberta.py

@@ -28,6 +28,7 @@ ROBERTA_PRETRAINED_CONFIG_ARCHIVE_MAP = {
     'roberta-base': "https://s3.amazonaws.com/models.huggingface.co/bert/roberta-base-config.json",
     'roberta-large': "https://s3.amazonaws.com/models.huggingface.co/bert/roberta-large-config.json",
     'roberta-large-mnli': "https://s3.amazonaws.com/models.huggingface.co/bert/roberta-large-mnli-config.json",
+    'distilroberta-base': "https://s3.amazonaws.com/models.huggingface.co/bert/distilroberta-base-config.json",
 }
 
 

transformers/modeling_roberta.py

@@ -34,6 +34,7 @@ ROBERTA_PRETRAINED_MODEL_ARCHIVE_MAP = {
     'roberta-base': "https://s3.amazonaws.com/models.huggingface.co/bert/roberta-base-pytorch_model.bin",
     'roberta-large': "https://s3.amazonaws.com/models.huggingface.co/bert/roberta-large-pytorch_model.bin",
     'roberta-large-mnli': "https://s3.amazonaws.com/models.huggingface.co/bert/roberta-large-mnli-pytorch_model.bin",
+    'distilroberta-base': "https://s3.amazonaws.com/models.huggingface.co/bert/distilroberta-base-pytorch_model.bin",
 }
 
 class RobertaEmbeddings(BertEmbeddings):

transformers/modeling_tf_roberta.py

@@ -35,6 +35,7 @@ TF_ROBERTA_PRETRAINED_MODEL_ARCHIVE_MAP = {
     'roberta-base': "https://s3.amazonaws.com/models.huggingface.co/bert/roberta-base-tf_model.h5",
     'roberta-large': "https://s3.amazonaws.com/models.huggingface.co/bert/roberta-large-tf_model.h5",
     'roberta-large-mnli': "https://s3.amazonaws.com/models.huggingface.co/bert/roberta-large-mnli-tf_model.h5",
+    'distilroberta-base': "https://s3.amazonaws.com/models.huggingface.co/bert/distilroberta-base-tf_model.h5",
 }
 
 class TFRobertaEmbeddings(TFBertEmbeddings):

transformers/tokenization_roberta.py

@@ -46,12 +46,14 @@ PRETRAINED_VOCAB_FILES_MAP = {
         'roberta-base': "https://s3.amazonaws.com/models.huggingface.co/bert/roberta-base-vocab.json",
         'roberta-large': "https://s3.amazonaws.com/models.huggingface.co/bert/roberta-large-vocab.json",
         'roberta-large-mnli': "https://s3.amazonaws.com/models.huggingface.co/bert/roberta-large-mnli-vocab.json",
+        'distilroberta-base': "https://s3.amazonaws.com/models.huggingface.co/bert/distilroberta-base-vocab.json",
     },
     'merges_file':
     {
         'roberta-base': "https://s3.amazonaws.com/models.huggingface.co/bert/roberta-base-merges.txt",
         'roberta-large': "https://s3.amazonaws.com/models.huggingface.co/bert/roberta-large-merges.txt",
         'roberta-large-mnli': "https://s3.amazonaws.com/models.huggingface.co/bert/roberta-large-mnli-merges.txt",
+        'distilroberta-base': "https://s3.amazonaws.com/models.huggingface.co/bert/distilroberta-base-merges.txt",
     },
 }
 
@@ -59,6 +61,7 @@ PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = {
     'roberta-base': 512,
     'roberta-large': 512,
     'roberta-large-mnli': 512,
+    'distilroberta-base': 512,
 }