updating hub

hubconfs/bert_hubconf.py

@@ -23,6 +23,9 @@ bert_docstring = """
                 . `bert-base-multilingual-uncased`
                 . `bert-base-multilingual-cased`
                 . `bert-base-chinese`
+                . `bert-base-german-cased`
+                . `bert-large-uncased-whole-word-masking`
+                . `bert-large-cased-whole-word-masking`
             - a path or url to a pretrained model archive containing:
                 . `bert_config.json` a configuration file for the model
                 . `pytorch_model.bin` a PyTorch dump of a BertForPreTraining
@@ -81,6 +84,7 @@ def bertTokenizer(*args, **kwargs):
                  Default: ["[UNK]", "[SEP]", "[PAD]", "[CLS]", "[MASK]"]
 
     Example:
+        >>> import torch
         >>> sentence = 'Hello, World!'
         >>> tokenizer = torch.hub.load('huggingface/pytorch-pretrained-BERT', 'bertTokenizer', 'bert-base-cased', do_basic_tokenize=False)
         >>> toks = tokenizer.tokenize(sentence)
@@ -101,6 +105,7 @@ def bertModel(*args, **kwargs):
 
     Example:
         # Load the tokenizer
+        >>> import torch
         >>> tokenizer = torch.hub.load('huggingface/pytorch-pretrained-BERT', 'bertTokenizer', 'bert-base-cased', do_basic_tokenize=False)
         #  Prepare tokenized input
         >>> text = "[CLS] Who was Jim Henson ? [SEP] Jim Henson was a puppeteer [SEP]"
@@ -129,6 +134,7 @@ def bertForNextSentencePrediction(*args, **kwargs):
 
     Example:
         # Load the tokenizer
+        >>> import torch
         >>> tokenizer = torch.hub.load('huggingface/pytorch-pretrained-BERT', 'bertTokenizer', 'bert-base-cased', do_basic_tokenize=False)
         #  Prepare tokenized input
         >>> text = "[CLS] Who was Jim Henson ? [SEP] Jim Henson was a puppeteer [SEP]"
@@ -158,6 +164,7 @@ def bertForPreTraining(*args, **kwargs):
 
     Example:
         # Load the tokenizer
+        >>> import torch
         >>> tokenizer = torch.hub.load('huggingface/pytorch-pretrained-BERT', 'bertTokenizer', 'bert-base-cased', do_basic_tokenize=False)
         #  Prepare tokenized input
         >>> text = "[CLS] Who was Jim Henson ? [SEP] Jim Henson was a puppeteer [SEP]"
@@ -181,6 +188,7 @@ def bertForMaskedLM(*args, **kwargs):
 
     Example:
         # Load the tokenizer
+        >>> import torch
         >>> tokenizer = torch.hub.load('huggingface/pytorch-pretrained-BERT', 'bertTokenizer', 'bert-base-cased', do_basic_tokenize=False)
         #  Prepare tokenized input
         >>> text = "[CLS] Who was Jim Henson ? [SEP] Jim Henson was a puppeteer [SEP]"
@@ -222,6 +230,7 @@ def bertForSequenceClassification(*args, **kwargs):
 
     Example:
         # Load the tokenizer
+        >>> import torch
         >>> tokenizer = torch.hub.load('huggingface/pytorch-pretrained-BERT', 'bertTokenizer', 'bert-base-cased', do_basic_tokenize=False)
         #  Prepare tokenized input
         >>> text = "[CLS] Who was Jim Henson ? [SEP] Jim Henson was a puppeteer [SEP]"
@@ -256,6 +265,7 @@ def bertForMultipleChoice(*args, **kwargs):
 
     Example:
         # Load the tokenizer
+        >>> import torch
         >>> tokenizer = torch.hub.load('huggingface/pytorch-pretrained-BERT', 'bertTokenizer', 'bert-base-cased', do_basic_tokenize=False)
         #  Prepare tokenized input
         >>> text = "[CLS] Who was Jim Henson ? [SEP] Jim Henson was a puppeteer [SEP]"
@@ -288,6 +298,7 @@ def bertForQuestionAnswering(*args, **kwargs):
 
     Example:
         # Load the tokenizer
+        >>> import torch
         >>> tokenizer = torch.hub.load('huggingface/pytorch-pretrained-BERT', 'bertTokenizer', 'bert-base-cased', do_basic_tokenize=False)
         #  Prepare tokenized input
         >>> text = "[CLS] Who was Jim Henson ? [SEP] Jim Henson was a puppeteer [SEP]"
@@ -326,6 +337,7 @@ def bertForTokenClassification(*args, **kwargs):
 
     Example:
         # Load the tokenizer
+        >>> import torch
         >>> tokenizer = torch.hub.load('huggingface/pytorch-pretrained-BERT', 'bertTokenizer', 'bert-base-cased', do_basic_tokenize=False)
         #  Prepare tokenized input
         >>> text = "[CLS] Who was Jim Henson ? [SEP] Jim Henson was a puppeteer [SEP]"

hubconfs/gpt2_hubconf.py

@@ -11,7 +11,7 @@ gpt2_docstring = """
     Params:
         pretrained_model_name_or_path: either:
             - a str with the name of a pre-trained model to load selected in the list of:
-                . `gpt2`
+                . `gpt2`, `gpt2-medium`
             - a path or url to a pretrained model archive containing:
                 . `gpt2_config.json` a configuration file for the model
                 . `pytorch_model.bin` a PyTorch dump of a GPT2Model instance
@@ -147,10 +147,14 @@ def gpt2DoubleHeadsModel(*args, **kwargs):
         >>> tokenizer = torch.hub.load('huggingface/pytorch-pretrained-BERT', 'gpt2Tokenizer', 'gpt2')
 
         #  Prepare tokenized input
-        >>> text = "Who was Jim Henson ?"
-        >>> indexed_tokens = tokenizer.encode(text)
-        >>> tokens_tensor = torch.tensor([indexed_tokens])
-        >>> mc_token_ids = torch.LongTensor([ [len(indexed_tokens)] ])
+        >>> text1 = "Who was Jim Henson ? Jim Henson was a puppeteer"
+        >>> text2 = "Who was Jim Henson ? Jim Henson was a mysterious young man"
+        >>> tokenized_text1 = tokenizer.tokenize(text1)
+        >>> tokenized_text2 = tokenizer.tokenize(text2)
+        >>> indexed_tokens1 = tokenizer.convert_tokens_to_ids(tokenized_text1)
+        >>> indexed_tokens2 = tokenizer.convert_tokens_to_ids(tokenized_text2)
+        >>> tokens_tensor = torch.tensor([[indexed_tokens1, indexed_tokens2]])
+        >>> mc_token_ids = torch.LongTensor([[len(tokenized_text1)-1, len(tokenized_text2)-1]])
 
         # Load gpt2DoubleHeadsModel
         >>> model = torch.hub.load('huggingface/pytorch-pretrained-BERT', 'gpt2DoubleHeadsModel', 'gpt2')

hubconfs/gpt_hubconf.py

@@ -126,7 +126,7 @@ def openAIGPTLMHeadModel(*args, **kwargs):
 
 	Example:
         # Load the tokenizer
-		>>> import torch
+        >>> import torch
         >>> tokenizer = torch.hub.load('huggingface/pytorch-pretrained-BERT', 'openAIGPTTokenizer', 'openai-gpt')
 
         #  Prepare tokenized input
@@ -161,15 +161,18 @@ def openAIGPTDoubleHeadsModel(*args, **kwargs):
 
 	Example:
         # Load the tokenizer
-		>>> import torch
+        >>> import torch
         >>> tokenizer = torch.hub.load('huggingface/pytorch-pretrained-BERT', 'openAIGPTTokenizer', 'openai-gpt')
 
         #  Prepare tokenized input
-        >>> text = "Who was Jim Henson ? Jim Henson was a puppeteer"
-        >>> tokenized_text = tokenizer.tokenize(text)
-        >>> indexed_tokens = tokenizer.convert_tokens_to_ids(tokenized_text)
-        >>> tokens_tensor = torch.tensor([indexed_tokens])
-		>>> mc_token_ids = torch.LongTensor([ [len(tokenized_text)] ])
+        >>> text1 = "Who was Jim Henson ? Jim Henson was a puppeteer"
+        >>> text2 = "Who was Jim Henson ? Jim Henson was a mysterious young man"
+        >>> tokenized_text1 = tokenizer.tokenize(text1)
+        >>> tokenized_text2 = tokenizer.tokenize(text2)
+        >>> indexed_tokens1 = tokenizer.convert_tokens_to_ids(tokenized_text1)
+        >>> indexed_tokens2 = tokenizer.convert_tokens_to_ids(tokenized_text2)
+        >>> tokens_tensor = torch.tensor([[indexed_tokens1, indexed_tokens2]])
+        >>> mc_token_ids = torch.LongTensor([[len(tokenized_text1)-1, len(tokenized_text2)-1]])
 
         # Load openAIGPTDoubleHeadsModel
         >>> model = torch.hub.load('huggingface/pytorch-pretrained-BERT', 'openAIGPTDoubleHeadsModel', 'openai-gpt')