Update links from s3 to huggingface.co

src/transformers/configuration_retribert.py

@@ -22,7 +22,7 @@ logger = logging.get_logger(__name__)
 
 # TODO: upload to AWS
 RETRIBERT_PRETRAINED_CONFIG_ARCHIVE_MAP = {
-    "retribert-base-uncased": "https://s3.amazonaws.com/models.huggingface.co/bert/distilbert-base-uncased-config.json",
+    "retribert-base-uncased": "https://huggingface.co/distilbert-base-uncased/resolve/main/config.json",
 }
 
 

src/transformers/configuration_roberta.py

@@ -22,12 +22,12 @@ from .utils import logging
 logger = logging.get_logger(__name__)
 
 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",
-    "roberta-base-openai-detector": "https://s3.amazonaws.com/models.huggingface.co/bert/roberta-base-openai-detector-config.json",
-    "roberta-large-openai-detector": "https://s3.amazonaws.com/models.huggingface.co/bert/roberta-large-openai-detector-config.json",
+    "roberta-base": "https://huggingface.co/roberta-base/resolve/main/config.json",
+    "roberta-large": "https://huggingface.co/roberta-large/resolve/main/config.json",
+    "roberta-large-mnli": "https://huggingface.co/roberta-large-mnli/resolve/main/config.json",
+    "distilroberta-base": "https://huggingface.co/distilroberta-base/resolve/main/config.json",
+    "roberta-base-openai-detector": "https://huggingface.co/roberta-base-openai-detector/resolve/main/config.json",
+    "roberta-large-openai-detector": "https://huggingface.co/roberta-large-openai-detector/resolve/main/config.json",
 }
 
 

src/transformers/configuration_squeezebert.py

@@ -21,9 +21,9 @@ from .utils import logging
 logger = logging.get_logger(__name__)
 
 SQUEEZEBERT_PRETRAINED_CONFIG_ARCHIVE_MAP = {
-    "squeezebert/squeezebert-uncased": "https://s3.amazonaws.com/models.huggingface.co/bert/squeezebert/squeezebert-uncased/config.json",
-    "squeezebert/squeezebert-mnli": "https://s3.amazonaws.com/models.huggingface.co/bert/squeezebert/squeezebert-mnli/config.json",
-    "squeezebert/squeezebert-mnli-headless": "https://s3.amazonaws.com/models.huggingface.co/bert/squeezebert/squeezebert-mnli-headless/config.json",
+    "squeezebert/squeezebert-uncased": "https://huggingface.co/squeezebert/squeezebert-uncased/resolve/main/config.json",
+    "squeezebert/squeezebert-mnli": "https://huggingface.co/squeezebert/squeezebert-mnli/resolve/main/config.json",
+    "squeezebert/squeezebert-mnli-headless": "https://huggingface.co/squeezebert/squeezebert-mnli-headless/resolve/main/config.json",
 }
 
 

src/transformers/configuration_t5.py

@@ -21,11 +21,11 @@ from .utils import logging
 logger = logging.get_logger(__name__)
 
 T5_PRETRAINED_CONFIG_ARCHIVE_MAP = {
-    "t5-small": "https://s3.amazonaws.com/models.huggingface.co/bert/t5-small-config.json",
-    "t5-base": "https://s3.amazonaws.com/models.huggingface.co/bert/t5-base-config.json",
-    "t5-large": "https://s3.amazonaws.com/models.huggingface.co/bert/t5-large-config.json",
-    "t5-3b": "https://s3.amazonaws.com/models.huggingface.co/bert/t5-3b-config.json",
-    "t5-11b": "https://s3.amazonaws.com/models.huggingface.co/bert/t5-11b-config.json",
+    "t5-small": "https://huggingface.co/t5-small/resolve/main/config.json",
+    "t5-base": "https://huggingface.co/t5-base/resolve/main/config.json",
+    "t5-large": "https://huggingface.co/t5-large/resolve/main/config.json",
+    "t5-3b": "https://huggingface.co/t5-3b/resolve/main/config.json",
+    "t5-11b": "https://huggingface.co/t5-11b/resolve/main/config.json",
 }
 
 

src/transformers/configuration_transfo_xl.py

@@ -25,7 +25,7 @@ from .utils import logging
 logger = logging.get_logger(__name__)
 
 TRANSFO_XL_PRETRAINED_CONFIG_ARCHIVE_MAP = {
-    "transfo-xl-wt103": "https://s3.amazonaws.com/models.huggingface.co/bert/transfo-xl-wt103-config.json",
+    "transfo-xl-wt103": "https://huggingface.co/transfo-xl-wt103/resolve/main/config.json",
 }
 
 

src/transformers/configuration_xlm.py

@@ -21,16 +21,16 @@ from .utils import logging
 logger = logging.get_logger(__name__)
 
 XLM_PRETRAINED_CONFIG_ARCHIVE_MAP = {
-    "xlm-mlm-en-2048": "https://s3.amazonaws.com/models.huggingface.co/bert/xlm-mlm-en-2048-config.json",
-    "xlm-mlm-ende-1024": "https://s3.amazonaws.com/models.huggingface.co/bert/xlm-mlm-ende-1024-config.json",
-    "xlm-mlm-enfr-1024": "https://s3.amazonaws.com/models.huggingface.co/bert/xlm-mlm-enfr-1024-config.json",
-    "xlm-mlm-enro-1024": "https://s3.amazonaws.com/models.huggingface.co/bert/xlm-mlm-enro-1024-config.json",
-    "xlm-mlm-tlm-xnli15-1024": "https://s3.amazonaws.com/models.huggingface.co/bert/xlm-mlm-tlm-xnli15-1024-config.json",
-    "xlm-mlm-xnli15-1024": "https://s3.amazonaws.com/models.huggingface.co/bert/xlm-mlm-xnli15-1024-config.json",
-    "xlm-clm-enfr-1024": "https://s3.amazonaws.com/models.huggingface.co/bert/xlm-clm-enfr-1024-config.json",
-    "xlm-clm-ende-1024": "https://s3.amazonaws.com/models.huggingface.co/bert/xlm-clm-ende-1024-config.json",
-    "xlm-mlm-17-1280": "https://s3.amazonaws.com/models.huggingface.co/bert/xlm-mlm-17-1280-config.json",
-    "xlm-mlm-100-1280": "https://s3.amazonaws.com/models.huggingface.co/bert/xlm-mlm-100-1280-config.json",
+    "xlm-mlm-en-2048": "https://huggingface.co/xlm-mlm-en-2048/resolve/main/config.json",
+    "xlm-mlm-ende-1024": "https://huggingface.co/xlm-mlm-ende-1024/resolve/main/config.json",
+    "xlm-mlm-enfr-1024": "https://huggingface.co/xlm-mlm-enfr-1024/resolve/main/config.json",
+    "xlm-mlm-enro-1024": "https://huggingface.co/xlm-mlm-enro-1024/resolve/main/config.json",
+    "xlm-mlm-tlm-xnli15-1024": "https://huggingface.co/xlm-mlm-tlm-xnli15-1024/resolve/main/config.json",
+    "xlm-mlm-xnli15-1024": "https://huggingface.co/xlm-mlm-xnli15-1024/resolve/main/config.json",
+    "xlm-clm-enfr-1024": "https://huggingface.co/xlm-clm-enfr-1024/resolve/main/config.json",
+    "xlm-clm-ende-1024": "https://huggingface.co/xlm-clm-ende-1024/resolve/main/config.json",
+    "xlm-mlm-17-1280": "https://huggingface.co/xlm-mlm-17-1280/resolve/main/config.json",
+    "xlm-mlm-100-1280": "https://huggingface.co/xlm-mlm-100-1280/resolve/main/config.json",
 }
 
 

src/transformers/configuration_xlm_prophetnet.py

@@ -22,7 +22,7 @@ from .utils import logging
 logger = logging.get_logger(__name__)
 
 XLM_PROPHETNET_PRETRAINED_CONFIG_ARCHIVE_MAP = {
-    "microsoft/xprophetnet-large-wiki100-cased": "https://s3.amazonaws.com/models.huggingface.co/bert/microsoft/xprophetnet-large-wiki100-cased/config.json",
+    "microsoft/xprophetnet-large-wiki100-cased": "https://huggingface.co/microsoft/xprophetnet-large-wiki100-cased/resolve/main/config.json",
 }
 
 

src/transformers/configuration_xlm_roberta.py

@@ -22,12 +22,12 @@ from .utils import logging
 logger = logging.get_logger(__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",
+    "xlm-roberta-base": "https://huggingface.co/xlm-roberta-base/resolve/main/config.json",
+    "xlm-roberta-large": "https://huggingface.co/xlm-roberta-large/resolve/main/config.json",
+    "xlm-roberta-large-finetuned-conll02-dutch": "https://huggingface.co/xlm-roberta-large-finetuned-conll02-dutch/resolve/main/config.json",
+    "xlm-roberta-large-finetuned-conll02-spanish": "https://huggingface.co/xlm-roberta-large-finetuned-conll02-spanish/resolve/main/config.json",
+    "xlm-roberta-large-finetuned-conll03-english": "https://huggingface.co/xlm-roberta-large-finetuned-conll03-english/resolve/main/config.json",
+    "xlm-roberta-large-finetuned-conll03-german": "https://huggingface.co/xlm-roberta-large-finetuned-conll03-german/resolve/main/config.json",
 }
 
 

src/transformers/configuration_xlnet.py

@@ -22,8 +22,8 @@ from .utils import logging
 logger = logging.get_logger(__name__)
 
 XLNET_PRETRAINED_CONFIG_ARCHIVE_MAP = {
-    "xlnet-base-cased": "https://s3.amazonaws.com/models.huggingface.co/bert/xlnet-base-cased-config.json",
-    "xlnet-large-cased": "https://s3.amazonaws.com/models.huggingface.co/bert/xlnet-large-cased-config.json",
+    "xlnet-base-cased": "https://huggingface.co/xlnet-base-cased/resolve/main/config.json",
+    "xlnet-large-cased": "https://huggingface.co/xlnet-large-cased/resolve/main/config.json",
 }
 
 

src/transformers/tokenization_albert.py

@@ -31,14 +31,14 @@ VOCAB_FILES_NAMES = {"vocab_file": "spiece.model"}
 
 PRETRAINED_VOCAB_FILES_MAP = {
     "vocab_file": {
-        "albert-base-v1": "https://s3.amazonaws.com/models.huggingface.co/bert/albert-base-v1-spiece.model",
-        "albert-large-v1": "https://s3.amazonaws.com/models.huggingface.co/bert/albert-large-v1-spiece.model",
-        "albert-xlarge-v1": "https://s3.amazonaws.com/models.huggingface.co/bert/albert-xlarge-v1-spiece.model",
-        "albert-xxlarge-v1": "https://s3.amazonaws.com/models.huggingface.co/bert/albert-xxlarge-v1-spiece.model",
-        "albert-base-v2": "https://s3.amazonaws.com/models.huggingface.co/bert/albert-base-v2-spiece.model",
-        "albert-large-v2": "https://s3.amazonaws.com/models.huggingface.co/bert/albert-large-v2-spiece.model",
-        "albert-xlarge-v2": "https://s3.amazonaws.com/models.huggingface.co/bert/albert-xlarge-v2-spiece.model",
-        "albert-xxlarge-v2": "https://s3.amazonaws.com/models.huggingface.co/bert/albert-xxlarge-v2-spiece.model",
+        "albert-base-v1": "https://huggingface.co/albert-base-v1/resolve/main/spiece.model",
+        "albert-large-v1": "https://huggingface.co/albert-large-v1/resolve/main/spiece.model",
+        "albert-xlarge-v1": "https://huggingface.co/albert-xlarge-v1/resolve/main/spiece.model",
+        "albert-xxlarge-v1": "https://huggingface.co/albert-xxlarge-v1/resolve/main/spiece.model",
+        "albert-base-v2": "https://huggingface.co/albert-base-v2/resolve/main/spiece.model",
+        "albert-large-v2": "https://huggingface.co/albert-large-v2/resolve/main/spiece.model",
+        "albert-xlarge-v2": "https://huggingface.co/albert-xlarge-v2/resolve/main/spiece.model",
+        "albert-xxlarge-v2": "https://huggingface.co/albert-xxlarge-v2/resolve/main/spiece.model",
     }
 }
 

src/transformers/tokenization_albert_fast.py

@@ -34,24 +34,24 @@ VOCAB_FILES_NAMES = {"vocab_file": "spiece.model", "tokenizer_file": "tokenizer.
 
 PRETRAINED_VOCAB_FILES_MAP = {
     "vocab_file": {
-        "albert-base-v1": "https://s3.amazonaws.com/models.huggingface.co/bert/albert-base-v1-spiece.model",
-        "albert-large-v1": "https://s3.amazonaws.com/models.huggingface.co/bert/albert-large-v1-spiece.model",
-        "albert-xlarge-v1": "https://s3.amazonaws.com/models.huggingface.co/bert/albert-xlarge-v1-spiece.model",
-        "albert-xxlarge-v1": "https://s3.amazonaws.com/models.huggingface.co/bert/albert-xxlarge-v1-spiece.model",
-        "albert-base-v2": "https://s3.amazonaws.com/models.huggingface.co/bert/albert-base-v2-spiece.model",
-        "albert-large-v2": "https://s3.amazonaws.com/models.huggingface.co/bert/albert-large-v2-spiece.model",
-        "albert-xlarge-v2": "https://s3.amazonaws.com/models.huggingface.co/bert/albert-xlarge-v2-spiece.model",
-        "albert-xxlarge-v2": "https://s3.amazonaws.com/models.huggingface.co/bert/albert-xxlarge-v2-spiece.model",
+        "albert-base-v1": "https://huggingface.co/albert-base-v1/resolve/main/spiece.model",
+        "albert-large-v1": "https://huggingface.co/albert-large-v1/resolve/main/spiece.model",
+        "albert-xlarge-v1": "https://huggingface.co/albert-xlarge-v1/resolve/main/spiece.model",
+        "albert-xxlarge-v1": "https://huggingface.co/albert-xxlarge-v1/resolve/main/spiece.model",
+        "albert-base-v2": "https://huggingface.co/albert-base-v2/resolve/main/spiece.model",
+        "albert-large-v2": "https://huggingface.co/albert-large-v2/resolve/main/spiece.model",
+        "albert-xlarge-v2": "https://huggingface.co/albert-xlarge-v2/resolve/main/spiece.model",
+        "albert-xxlarge-v2": "https://huggingface.co/albert-xxlarge-v2/resolve/main/spiece.model",
     },
     "tokenizer_file": {
-        "albert-base-v1": "https://s3.amazonaws.com/models.huggingface.co/bert/albert-base-v1-tokenizer.json",
-        "albert-large-v1": "https://s3.amazonaws.com/models.huggingface.co/bert/albert-large-v1-tokenizer.json",
-        "albert-xlarge-v1": "https://s3.amazonaws.com/models.huggingface.co/bert/albert-xlarge-v1-tokenizer.json",
-        "albert-xxlarge-v1": "https://s3.amazonaws.com/models.huggingface.co/bert/albert-xxlarge-v1-tokenizer.json",
-        "albert-base-v2": "https://s3.amazonaws.com/models.huggingface.co/bert/albert-base-v2-tokenizer.json",
-        "albert-large-v2": "https://s3.amazonaws.com/models.huggingface.co/bert/albert-large-v2-tokenizer.json",
-        "albert-xlarge-v2": "https://s3.amazonaws.com/models.huggingface.co/bert/albert-xlarge-v2-tokenizer.json",
-        "albert-xxlarge-v2": "https://s3.amazonaws.com/models.huggingface.co/bert/albert-xxlarge-v2-tokenizer.json",
+        "albert-base-v1": "https://huggingface.co/albert-base-v1/resolve/main/tokenizer.json",
+        "albert-large-v1": "https://huggingface.co/albert-large-v1/resolve/main/tokenizer.json",
+        "albert-xlarge-v1": "https://huggingface.co/albert-xlarge-v1/resolve/main/tokenizer.json",
+        "albert-xxlarge-v1": "https://huggingface.co/albert-xxlarge-v1/resolve/main/tokenizer.json",
+        "albert-base-v2": "https://huggingface.co/albert-base-v2/resolve/main/tokenizer.json",
+        "albert-large-v2": "https://huggingface.co/albert-large-v2/resolve/main/tokenizer.json",
+        "albert-xlarge-v2": "https://huggingface.co/albert-xlarge-v2/resolve/main/tokenizer.json",
+        "albert-xxlarge-v2": "https://huggingface.co/albert-xxlarge-v2/resolve/main/tokenizer.json",
     },
 }
 

src/transformers/tokenization_bart.py

@@ -24,8 +24,8 @@ logger = logging.get_logger(__name__)
 
 
 # vocab and merges same as roberta
-vocab_url = "https://s3.amazonaws.com/models.huggingface.co/bert/roberta-large-vocab.json"
-merges_url = "https://s3.amazonaws.com/models.huggingface.co/bert/roberta-large-merges.txt"
+vocab_url = "https://huggingface.co/roberta-large/resolve/main/vocab.json"
+merges_url = "https://huggingface.co/roberta-large/resolve/main/merges.txt"
 _all_bart_models = [
     "facebook/bart-base",
     "facebook/bart-large",

src/transformers/tokenization_bart_fast.py

@@ -25,9 +25,9 @@ logger = logging.get_logger(__name__)
 
 
 # vocab and merges same as roberta
-vocab_url = "https://s3.amazonaws.com/models.huggingface.co/bert/roberta-large-vocab.json"
-merges_url = "https://s3.amazonaws.com/models.huggingface.co/bert/roberta-large-merges.txt"
-tokenizer_url = "https://s3.amazonaws.com/models.huggingface.co/bert/roberta-large-tokenizer.json"
+vocab_url = "https://huggingface.co/roberta-large/resolve/main/vocab.json"
+merges_url = "https://huggingface.co/roberta-large/resolve/main/merges.txt"
+tokenizer_url = "https://huggingface.co/roberta-large/resolve/main/tokenizer.json"
 _all_bart_models = [
     "facebook/bart-base",
     "facebook/bart-large",

src/transformers/tokenization_bert.py

@@ -30,24 +30,24 @@ VOCAB_FILES_NAMES = {"vocab_file": "vocab.txt"}
 
 PRETRAINED_VOCAB_FILES_MAP = {
     "vocab_file": {
-        "bert-base-uncased": "https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-uncased-vocab.txt",
-        "bert-large-uncased": "https://s3.amazonaws.com/models.huggingface.co/bert/bert-large-uncased-vocab.txt",
-        "bert-base-cased": "https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-cased-vocab.txt",
-        "bert-large-cased": "https://s3.amazonaws.com/models.huggingface.co/bert/bert-large-cased-vocab.txt",
-        "bert-base-multilingual-uncased": "https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-multilingual-uncased-vocab.txt",
-        "bert-base-multilingual-cased": "https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-multilingual-cased-vocab.txt",
-        "bert-base-chinese": "https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-chinese-vocab.txt",
+        "bert-base-uncased": "https://huggingface.co/bert-base-uncased/resolve/main/vocab.txt",
+        "bert-large-uncased": "https://huggingface.co/bert-large-uncased/resolve/main/vocab.txt",
+        "bert-base-cased": "https://huggingface.co/bert-base-cased/resolve/main/vocab.txt",
+        "bert-large-cased": "https://huggingface.co/bert-large-cased/resolve/main/vocab.txt",
+        "bert-base-multilingual-uncased": "https://huggingface.co/bert-base-multilingual-uncased/resolve/main/vocab.txt",
+        "bert-base-multilingual-cased": "https://huggingface.co/bert-base-multilingual-cased/resolve/main/vocab.txt",
+        "bert-base-chinese": "https://huggingface.co/bert-base-chinese/resolve/main/vocab.txt",
         "bert-base-german-cased": "https://int-deepset-models-bert.s3.eu-central-1.amazonaws.com/pytorch/bert-base-german-cased-vocab.txt",
-        "bert-large-uncased-whole-word-masking": "https://s3.amazonaws.com/models.huggingface.co/bert/bert-large-uncased-whole-word-masking-vocab.txt",
-        "bert-large-cased-whole-word-masking": "https://s3.amazonaws.com/models.huggingface.co/bert/bert-large-cased-whole-word-masking-vocab.txt",
-        "bert-large-uncased-whole-word-masking-finetuned-squad": "https://s3.amazonaws.com/models.huggingface.co/bert/bert-large-uncased-whole-word-masking-finetuned-squad-vocab.txt",
-        "bert-large-cased-whole-word-masking-finetuned-squad": "https://s3.amazonaws.com/models.huggingface.co/bert/bert-large-cased-whole-word-masking-finetuned-squad-vocab.txt",
-        "bert-base-cased-finetuned-mrpc": "https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-cased-finetuned-mrpc-vocab.txt",
-        "bert-base-german-dbmdz-cased": "https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-german-dbmdz-cased-vocab.txt",
-        "bert-base-german-dbmdz-uncased": "https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-german-dbmdz-uncased-vocab.txt",
-        "TurkuNLP/bert-base-finnish-cased-v1": "https://s3.amazonaws.com/models.huggingface.co/bert/TurkuNLP/bert-base-finnish-cased-v1/vocab.txt",
-        "TurkuNLP/bert-base-finnish-uncased-v1": "https://s3.amazonaws.com/models.huggingface.co/bert/TurkuNLP/bert-base-finnish-uncased-v1/vocab.txt",
-        "wietsedv/bert-base-dutch-cased": "https://s3.amazonaws.com/models.huggingface.co/bert/wietsedv/bert-base-dutch-cased/vocab.txt",
+        "bert-large-uncased-whole-word-masking": "https://huggingface.co/bert-large-uncased-whole-word-masking/resolve/main/vocab.txt",
+        "bert-large-cased-whole-word-masking": "https://huggingface.co/bert-large-cased-whole-word-masking/resolve/main/vocab.txt",
+        "bert-large-uncased-whole-word-masking-finetuned-squad": "https://huggingface.co/bert-large-uncased-whole-word-masking-finetuned-squad/resolve/main/vocab.txt",
+        "bert-large-cased-whole-word-masking-finetuned-squad": "https://huggingface.co/bert-large-cased-whole-word-masking-finetuned-squad/resolve/main/vocab.txt",
+        "bert-base-cased-finetuned-mrpc": "https://huggingface.co/bert-base-cased-finetuned-mrpc/resolve/main/vocab.txt",
+        "bert-base-german-dbmdz-cased": "https://huggingface.co/bert-base-german-dbmdz-cased/resolve/main/vocab.txt",
+        "bert-base-german-dbmdz-uncased": "https://huggingface.co/bert-base-german-dbmdz-uncased/resolve/main/vocab.txt",
+        "TurkuNLP/bert-base-finnish-cased-v1": "https://huggingface.co/TurkuNLP/bert-base-finnish-cased-v1/resolve/main/vocab.txt",
+        "TurkuNLP/bert-base-finnish-uncased-v1": "https://huggingface.co/TurkuNLP/bert-base-finnish-uncased-v1/resolve/main/vocab.txt",
+        "wietsedv/bert-base-dutch-cased": "https://huggingface.co/wietsedv/bert-base-dutch-cased/resolve/main/vocab.txt",
     }
 }
 

src/transformers/tokenization_bert_fast.py

@@ -30,44 +30,44 @@ VOCAB_FILES_NAMES = {"vocab_file": "vocab.txt", "tokenizer_file": "tokenizer.jso
 
 PRETRAINED_VOCAB_FILES_MAP = {
     "vocab_file": {
-        "bert-base-uncased": "https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-uncased-vocab.txt",
-        "bert-large-uncased": "https://s3.amazonaws.com/models.huggingface.co/bert/bert-large-uncased-vocab.txt",
-        "bert-base-cased": "https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-cased-vocab.txt",
-        "bert-large-cased": "https://s3.amazonaws.com/models.huggingface.co/bert/bert-large-cased-vocab.txt",
-        "bert-base-multilingual-uncased": "https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-multilingual-uncased-vocab.txt",
-        "bert-base-multilingual-cased": "https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-multilingual-cased-vocab.txt",
-        "bert-base-chinese": "https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-chinese-vocab.txt",
+        "bert-base-uncased": "https://huggingface.co/bert-base-uncased/resolve/main/vocab.txt",
+        "bert-large-uncased": "https://huggingface.co/bert-large-uncased/resolve/main/vocab.txt",
+        "bert-base-cased": "https://huggingface.co/bert-base-cased/resolve/main/vocab.txt",
+        "bert-large-cased": "https://huggingface.co/bert-large-cased/resolve/main/vocab.txt",
+        "bert-base-multilingual-uncased": "https://huggingface.co/bert-base-multilingual-uncased/resolve/main/vocab.txt",
+        "bert-base-multilingual-cased": "https://huggingface.co/bert-base-multilingual-cased/resolve/main/vocab.txt",
+        "bert-base-chinese": "https://huggingface.co/bert-base-chinese/resolve/main/vocab.txt",
         "bert-base-german-cased": "https://int-deepset-models-bert.s3.eu-central-1.amazonaws.com/pytorch/bert-base-german-cased-vocab.txt",
-        "bert-large-uncased-whole-word-masking": "https://s3.amazonaws.com/models.huggingface.co/bert/bert-large-uncased-whole-word-masking-vocab.txt",
-        "bert-large-cased-whole-word-masking": "https://s3.amazonaws.com/models.huggingface.co/bert/bert-large-cased-whole-word-masking-vocab.txt",
-        "bert-large-uncased-whole-word-masking-finetuned-squad": "https://s3.amazonaws.com/models.huggingface.co/bert/bert-large-uncased-whole-word-masking-finetuned-squad-vocab.txt",
-        "bert-large-cased-whole-word-masking-finetuned-squad": "https://s3.amazonaws.com/models.huggingface.co/bert/bert-large-cased-whole-word-masking-finetuned-squad-vocab.txt",
-        "bert-base-cased-finetuned-mrpc": "https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-cased-finetuned-mrpc-vocab.txt",
-        "bert-base-german-dbmdz-cased": "https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-german-dbmdz-cased-vocab.txt",
-        "bert-base-german-dbmdz-uncased": "https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-german-dbmdz-uncased-vocab.txt",
-        "TurkuNLP/bert-base-finnish-cased-v1": "https://s3.amazonaws.com/models.huggingface.co/bert/TurkuNLP/bert-base-finnish-cased-v1/vocab.txt",
-        "TurkuNLP/bert-base-finnish-uncased-v1": "https://s3.amazonaws.com/models.huggingface.co/bert/TurkuNLP/bert-base-finnish-uncased-v1/vocab.txt",
-        "wietsedv/bert-base-dutch-cased": "https://s3.amazonaws.com/models.huggingface.co/bert/wietsedv/bert-base-dutch-cased/vocab.txt",
+        "bert-large-uncased-whole-word-masking": "https://huggingface.co/bert-large-uncased-whole-word-masking/resolve/main/vocab.txt",
+        "bert-large-cased-whole-word-masking": "https://huggingface.co/bert-large-cased-whole-word-masking/resolve/main/vocab.txt",
+        "bert-large-uncased-whole-word-masking-finetuned-squad": "https://huggingface.co/bert-large-uncased-whole-word-masking-finetuned-squad/resolve/main/vocab.txt",
+        "bert-large-cased-whole-word-masking-finetuned-squad": "https://huggingface.co/bert-large-cased-whole-word-masking-finetuned-squad/resolve/main/vocab.txt",
+        "bert-base-cased-finetuned-mrpc": "https://huggingface.co/bert-base-cased-finetuned-mrpc/resolve/main/vocab.txt",
+        "bert-base-german-dbmdz-cased": "https://huggingface.co/bert-base-german-dbmdz-cased/resolve/main/vocab.txt",
+        "bert-base-german-dbmdz-uncased": "https://huggingface.co/bert-base-german-dbmdz-uncased/resolve/main/vocab.txt",
+        "TurkuNLP/bert-base-finnish-cased-v1": "https://huggingface.co/TurkuNLP/bert-base-finnish-cased-v1/resolve/main/vocab.txt",
+        "TurkuNLP/bert-base-finnish-uncased-v1": "https://huggingface.co/TurkuNLP/bert-base-finnish-uncased-v1/resolve/main/vocab.txt",
+        "wietsedv/bert-base-dutch-cased": "https://huggingface.co/wietsedv/bert-base-dutch-cased/resolve/main/vocab.txt",
     },
     "tokenizer_file": {
-        "bert-base-uncased": "https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-uncased-tokenizer.json",
-        "bert-large-uncased": "https://s3.amazonaws.com/models.huggingface.co/bert/bert-large-uncased-tokenizer.json",
-        "bert-base-cased": "https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-cased-tokenizer.json",
-        "bert-large-cased": "https://s3.amazonaws.com/models.huggingface.co/bert/bert-large-cased-tokenizer.json",
-        "bert-base-multilingual-uncased": "https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-multilingual-uncased-tokenizer.json",
-        "bert-base-multilingual-cased": "https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-multilingual-cased-tokenizer.json",
-        "bert-base-chinese": "https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-chinese-tokenizer.json",
+        "bert-base-uncased": "https://huggingface.co/bert-base-uncased/resolve/main/tokenizer.json",
+        "bert-large-uncased": "https://huggingface.co/bert-large-uncased/resolve/main/tokenizer.json",
+        "bert-base-cased": "https://huggingface.co/bert-base-cased/resolve/main/tokenizer.json",
+        "bert-large-cased": "https://huggingface.co/bert-large-cased/resolve/main/tokenizer.json",
+        "bert-base-multilingual-uncased": "https://huggingface.co/bert-base-multilingual-uncased/resolve/main/tokenizer.json",
+        "bert-base-multilingual-cased": "https://huggingface.co/bert-base-multilingual-cased/resolve/main/tokenizer.json",
+        "bert-base-chinese": "https://huggingface.co/bert-base-chinese/resolve/main/tokenizer.json",
         "bert-base-german-cased": "https://int-deepset-models-bert.s3.eu-central-1.amazonaws.com/pytorch/bert-base-german-cased-tokenizer.json",
-        "bert-large-uncased-whole-word-masking": "https://s3.amazonaws.com/models.huggingface.co/bert/bert-large-uncased-whole-word-masking-tokenizer.json",
-        "bert-large-cased-whole-word-masking": "https://s3.amazonaws.com/models.huggingface.co/bert/bert-large-cased-whole-word-masking-tokenizer.json",
-        "bert-large-uncased-whole-word-masking-finetuned-squad": "https://s3.amazonaws.com/models.huggingface.co/bert/bert-large-uncased-whole-word-masking-finetuned-squad-tokenizer.json",
-        "bert-large-cased-whole-word-masking-finetuned-squad": "https://s3.amazonaws.com/models.huggingface.co/bert/bert-large-cased-whole-word-masking-finetuned-squad-tokenizer.json",
-        "bert-base-cased-finetuned-mrpc": "https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-cased-finetuned-mrpc-tokenizer.json",
-        "bert-base-german-dbmdz-cased": "https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-german-dbmdz-cased-tokenizer.json",
-        "bert-base-german-dbmdz-uncased": "https://s3.amazonaws.com/models.huggingface.co/bert/bert-base-german-dbmdz-uncased-tokenizer.json",
-        "TurkuNLP/bert-base-finnish-cased-v1": "https://s3.amazonaws.com/models.huggingface.co/bert/TurkuNLP/bert-base-finnish-cased-v1/tokenizer.json",
-        "TurkuNLP/bert-base-finnish-uncased-v1": "https://s3.amazonaws.com/models.huggingface.co/bert/TurkuNLP/bert-base-finnish-uncased-v1/tokenizer.json",
-        "wietsedv/bert-base-dutch-cased": "https://s3.amazonaws.com/models.huggingface.co/bert/wietsedv/bert-base-dutch-cased/tokenizer.json",
+        "bert-large-uncased-whole-word-masking": "https://huggingface.co/bert-large-uncased-whole-word-masking/resolve/main/tokenizer.json",
+        "bert-large-cased-whole-word-masking": "https://huggingface.co/bert-large-cased-whole-word-masking/resolve/main/tokenizer.json",
+        "bert-large-uncased-whole-word-masking-finetuned-squad": "https://huggingface.co/bert-large-uncased-whole-word-masking-finetuned-squad/resolve/main/tokenizer.json",
+        "bert-large-cased-whole-word-masking-finetuned-squad": "https://huggingface.co/bert-large-cased-whole-word-masking-finetuned-squad/resolve/main/tokenizer.json",
+        "bert-base-cased-finetuned-mrpc": "https://huggingface.co/bert-base-cased-finetuned-mrpc/resolve/main/tokenizer.json",
+        "bert-base-german-dbmdz-cased": "https://huggingface.co/bert-base-german-dbmdz-cased/resolve/main/tokenizer.json",
+        "bert-base-german-dbmdz-uncased": "https://huggingface.co/bert-base-german-dbmdz-uncased/resolve/main/tokenizer.json",
+        "TurkuNLP/bert-base-finnish-cased-v1": "https://huggingface.co/TurkuNLP/bert-base-finnish-cased-v1/resolve/main/tokenizer.json",
+        "TurkuNLP/bert-base-finnish-uncased-v1": "https://huggingface.co/TurkuNLP/bert-base-finnish-uncased-v1/resolve/main/tokenizer.json",
+        "wietsedv/bert-base-dutch-cased": "https://huggingface.co/wietsedv/bert-base-dutch-cased/resolve/main/tokenizer.json",
     },
 }
 

src/transformers/tokenization_bert_generation.py

@@ -30,7 +30,7 @@ logger = logging.get_logger(__name__)
 VOCAB_FILES_NAMES = {"vocab_file": "spiece.model"}
 
 tokenizer_url = (
-    "https://s3.amazonaws.com/models.huggingface.co/bert/google/bert_for_seq_generation_L-24_bbc_encoder/spiece.model"
+    "https://huggingface.co/google/bert_for_seq_generation_L-24_bbc_encoder/resolve/main/spiece.model"
 )
 
 

src/transformers/tokenization_bert_japanese.py

@@ -31,10 +31,10 @@ VOCAB_FILES_NAMES = {"vocab_file": "vocab.txt"}
 
 PRETRAINED_VOCAB_FILES_MAP = {
     "vocab_file": {
-        "cl-tohoku/bert-base-japanese": "https://s3.amazonaws.com/models.huggingface.co/bert/cl-tohoku/bert-base-japanese/vocab.txt",
-        "cl-tohoku/bert-base-japanese-whole-word-masking": "https://s3.amazonaws.com/models.huggingface.co/bert/cl-tohoku/bert-base-japanese-whole-word-masking/vocab.txt",
-        "cl-tohoku/bert-base-japanese-char": "https://s3.amazonaws.com/models.huggingface.co/bert/cl-tohoku/bert-base-japanese-char/vocab.txt",
-        "cl-tohoku/bert-base-japanese-char-whole-word-masking": "https://s3.amazonaws.com/models.huggingface.co/bert/cl-tohoku/bert-base-japanese-char-whole-word-masking/vocab.txt",
+        "cl-tohoku/bert-base-japanese": "https://huggingface.co/cl-tohoku/bert-base-japanese/resolve/main/vocab.txt",
+        "cl-tohoku/bert-base-japanese-whole-word-masking": "https://huggingface.co/cl-tohoku/bert-base-japanese-whole-word-masking/resolve/main/vocab.txt",
+        "cl-tohoku/bert-base-japanese-char": "https://huggingface.co/cl-tohoku/bert-base-japanese-char/resolve/main/vocab.txt",
+        "cl-tohoku/bert-base-japanese-char-whole-word-masking": "https://huggingface.co/cl-tohoku/bert-base-japanese-char-whole-word-masking/resolve/main/vocab.txt",
     }
 }
 

src/transformers/tokenization_bertweet.py

@@ -37,10 +37,10 @@ VOCAB_FILES_NAMES = {
 
 PRETRAINED_VOCAB_FILES_MAP = {
     "vocab_file": {
-        "vinai/bertweet-base": "https://s3.amazonaws.com/models.huggingface.co/bert/vinai/bertweet-base/vocab.txt",
+        "vinai/bertweet-base": "https://huggingface.co/vinai/bertweet-base/resolve/main/vocab.txt",
     },
     "merges_file": {
-        "vinai/bertweet-base": "https://s3.amazonaws.com/models.huggingface.co/bert/vinai/bertweet-base/bpe.codes",
+        "vinai/bertweet-base": "https://huggingface.co/vinai/bertweet-base/resolve/main/bpe.codes",
     },
 }
 

src/transformers/tokenization_camembert.py

@@ -31,7 +31,7 @@ VOCAB_FILES_NAMES = {"vocab_file": "sentencepiece.bpe.model"}
 
 PRETRAINED_VOCAB_FILES_MAP = {
     "vocab_file": {
-        "camembert-base": "https://s3.amazonaws.com/models.huggingface.co/bert/camembert-base-sentencepiece.bpe.model",
+        "camembert-base": "https://huggingface.co/camembert-base/resolve/main/sentencepiece.bpe.model",
     }
 }
 

src/transformers/tokenization_camembert_fast.py

@@ -36,10 +36,10 @@ VOCAB_FILES_NAMES = {"vocab_file": "sentencepiece.bpe.model", "tokenizer_file":
 
 PRETRAINED_VOCAB_FILES_MAP = {
     "vocab_file": {
-        "camembert-base": "https://s3.amazonaws.com/models.huggingface.co/bert/camembert-base-sentencepiece.bpe.model",
+        "camembert-base": "https://huggingface.co/camembert-base/resolve/main/sentencepiece.bpe.model",
     },
     "tokenizer_file": {
-        "camembert-base": "https://s3.amazonaws.com/models.huggingface.co/bert/camembert-base-tokenizer.json",
+        "camembert-base": "https://huggingface.co/camembert-base/resolve/main/tokenizer.json",
     },
 }