fix typo/presentation

hubconfs/gpt2_hubconf.py

@@ -1,27 +1,27 @@
 from pytorch_pretrained_bert.tokenization_gpt2 import GPT2Tokenizer
 from pytorch_pretrained_bert.modeling_gpt2 import (
-	GPT2Model,
+    GPT2Model,
-	GPT2LMHeadModel,
+    GPT2LMHeadModel,
-	GPT2DoubleHeadsModel
+    GPT2DoubleHeadsModel
 )
 
 # A lot of models share the same param doc. Use a decorator
 # to save typing
 gpt2_docstring = """
-	Params:
+    Params:
-		pretrained_model_name_or_path: either:
+        pretrained_model_name_or_path: either:
-			- a str with the name of a pre-trained model to load selected in the list of:
+            - a str with the name of a pre-trained model to load selected in the list of:
-				. `gpt2`
+                . `gpt2`
-			- a path or url to a pretrained model archive containing:
+            - a path or url to a pretrained model archive containing:
-				. `gpt2_config.json` a configuration file for the model
+                . `gpt2_config.json` a configuration file for the model
-				. `pytorch_model.bin` a PyTorch dump of a GPT2Model instance
+                . `pytorch_model.bin` a PyTorch dump of a GPT2Model instance
-			- a path or url to a pretrained model archive containing:
+            - a path or url to a pretrained model archive containing:
-				. `gpt2_config.json` a configuration file for the model
+                . `gpt2_config.json` a configuration file for the model
-				. a TensorFlow checkpoint with trained weights
+                . a TensorFlow checkpoint with trained weights
-		from_tf: should we load the weights from a locally saved TensorFlow checkpoint
+        from_tf: should we load the weights from a locally saved TensorFlow checkpoint
-		cache_dir: an optional path to a folder in which the pre-trained models will be cached.
+        cache_dir: an optional path to a folder in which the pre-trained models will be cached.
-		state_dict: an optional state dictionary (collections.OrderedDict object) to use instead of pre-trained models
+        state_dict: an optional state dictionary (collections.OrderedDict object) to use instead of pre-trained models
-		*inputs, **kwargs: additional input for the specific GPT-2 class
+        *inputs, **kwargs: additional input for the specific GPT-2 class
 """
 
 
@@ -35,27 +35,27 @@ def _append_from_pretrained_docstring(docstr):
 def gpt2Tokenizer(*args, **kwargs):
     """
     Instantiate a GPT-2 BPE tokenizer for OpenAI GPT-2 from a pre-trained/customized vocab file.
-	Peculiarities:
+    Peculiarities:
         - Byte-level BPE
 
     Args:
     pretrained_model_name_or_path: Path to pretrained model archive
                                    or one of pre-trained vocab configs below.
-                                       * openai-gpt
+                                       * gpt2
     Keyword args:
-	special_tokens: Special tokens in vocabulary that are not pretrained ([SEP], [CLS]...)
+    special_tokens: Special tokens in vocabulary that are not pretrained ([SEP], [CLS]...)
-					Default: None
+                    Default: None
-	max_len: An artificial maximum length to truncate tokenized sequences to;
+    max_len: An artificial maximum length to truncate tokenized sequences to;
-        	 Effective maximum length is always the minimum of this
+             Effective maximum length is always the minimum of this
              value (if specified) and the underlying BERT model's
              sequence length.
-			 Default: None
+             Default: None
 
     Example:
-		>>> import torch
+        >>> import torch
         >>> tokenizer = torch.hub.load('huggingface/pytorch-pretrained-BERT', 'gpt2Tokenizer', 'gpt2')
-		
+
-		>>> text = "Who was Jim Henson ?"
+        >>> text = "Who was Jim Henson ?"
         >>> indexed_tokens = tokenizer.encode(tokenized_text)
     """
     tokenizer = GPT2Tokenizer.from_pretrained(*args, **kwargs)
@@ -66,31 +66,31 @@ def gpt2Tokenizer(*args, **kwargs):
 def gpt2Model(*args, **kwargs):
     """
     gpt2Model is the basic OpenAI GPT-2 Transformer model based on
-	identical stacked masked self-attention blocks and pre-trained
+    identical stacked masked self-attention blocks and pre-trained
-	on large scale dataset using language modeling signal.
+    on large scale dataset using language modeling signal.
 
     Example:
         # Load the tokenizer
-		>>> import torch
+        >>> import torch
         >>> tokenizer = torch.hub.load('huggingface/pytorch-pretrained-BERT', 'gpt2Tokenizer', 'gpt2')
 
         #  Prepare tokenized input
         >>> text_1 = "Who was Jim Henson ?"
-		>>> text_2 = "Jim Henson was a puppeteer"
+        >>> text_2 = "Jim Henson was a puppeteer"
         >>> indexed_tokens_1 = tokenizer.encode(text_1)
         >>> indexed_tokens_2 = tokenizer.encode(text_2)
-		>>> tokens_tensor_1 = torch.tensor([indexed_tokens_1])
+        >>> tokens_tensor_1 = torch.tensor([indexed_tokens_1])
-		>>> tokens_tensor_2 = torch.tensor([indexed_tokens_2])
+        >>> tokens_tensor_2 = torch.tensor([indexed_tokens_2])
 
         # Load gpt2Model
         >>> model = torch.hub.load('huggingface/pytorch-pretrained-BERT', 'gpt2Model', 'gpt2')
         >>> model.eval()
 
         # Predict hidden states features for each layer
-		# past can be used to reuse precomputed hidden state in a subsequent predictions
+        # past can be used to reuse precomputed hidden state in a subsequent predictions
         >>> with torch.no_grad():
                 hidden_states_1, past = model(tokens_tensor_1)
-				hidden_states_2, past = model(tokens_tensor_2, past=past)
+                hidden_states_2, past = model(tokens_tensor_2, past=past)
     """
     model = GPT2Model.from_pretrained(*args, **kwargs)
     return model
@@ -100,34 +100,34 @@ def gpt2Model(*args, **kwargs):
 def gpt2LMHeadModel(*args, **kwargs):
     """
     gpt2LMHeadModel is the OpenAI GPT-2 Transformer model with the
-	tied (pre-trained) language modeling head on top.
+    tied (pre-trained) language modeling head on top.
 
-	Example:
+    Example:
         # Load the tokenizer
-		>>> import torch
+        >>> import torch
         >>> tokenizer = torch.hub.load('huggingface/pytorch-pretrained-BERT', 'gpt2Tokenizer', 'gpt2')
 
         #  Prepare tokenized input
         >>> text_1 = "Who was Jim Henson ?"
-		>>> text_2 = "Jim Henson was a puppeteer"
+        >>> text_2 = "Jim Henson was a puppeteer"
         >>> indexed_tokens_1 = tokenizer.encode(text_1)
         >>> indexed_tokens_2 = tokenizer.encode(text_2)
-		>>> tokens_tensor_1 = torch.tensor([indexed_tokens_1])
+        >>> tokens_tensor_1 = torch.tensor([indexed_tokens_1])
-		>>> tokens_tensor_2 = torch.tensor([indexed_tokens_2])
+        >>> tokens_tensor_2 = torch.tensor([indexed_tokens_2])
 
         # Load gpt2LMHeadModel
         >>> model = torch.hub.load('huggingface/pytorch-pretrained-BERT', 'gpt2LMHeadModel', 'gpt2')
         >>> model.eval()
 
         # Predict hidden states features for each layer
-		# past can be used to reuse precomputed hidden state in a subsequent predictions
+        # past can be used to reuse precomputed hidden state in a subsequent predictions
         >>> with torch.no_grad():
-				predictions_1, past = model(tokens_tensor_1)
+                predictions_1, past = model(tokens_tensor_1)
-				predictions_2, past = model(tokens_tensor_2, past=past)
+                predictions_2, past = model(tokens_tensor_2, past=past)
 
-		# Get the predicted last token
+        # Get the predicted last token
-		>>> predicted_index = torch.argmax(predictions_2[0, -1, :]).item()
+        >>> predicted_index = torch.argmax(predictions_2[0, -1, :]).item()
-		>>> predicted_token = tokenizer.decode([predicted_index])
+        >>> predicted_token = tokenizer.decode([predicted_index])
         >>> assert predicted_token == ' who'
     """
     model = GPT2LMHeadModel.from_pretrained(*args, **kwargs)
@@ -138,19 +138,19 @@ def gpt2LMHeadModel(*args, **kwargs):
 def gpt2DoubleHeadsModel(*args, **kwargs):
     """
     gpt2DoubleHeadsModel is the OpenAI GPT-2 Transformer model with the
-	tied (pre-trained) language modeling head and a multiple choice
+    tied (pre-trained) language modeling head and a multiple choice
-	classification head (only initialized, not pre-trained).
+    classification head (only initialized, not pre-trained).
 
-	Example:
+    Example:
         # Load the tokenizer
-		>>> import torch
+        >>> import torch
         >>> tokenizer = torch.hub.load('huggingface/pytorch-pretrained-BERT', 'gpt2Tokenizer', 'gpt2')
 
         #  Prepare tokenized input
-		>>> text = "Who was Jim Henson ?"
+        >>> text = "Who was Jim Henson ?"
         >>> indexed_tokens = tokenizer.encode(text)
         >>> tokens_tensor = torch.tensor([indexed_tokens])
-		>>> mc_token_ids = torch.LongTensor([ [len(indexed_tokens)] ])
+        >>> mc_token_ids = torch.LongTensor([ [len(indexed_tokens)] ])
 
         # Load gpt2DoubleHeadsModel
         >>> model = torch.hub.load('huggingface/pytorch-pretrained-BERT', 'gpt2DoubleHeadsModel', 'gpt2')

hubconfs/transformer_xl_hubconf.py

@@ -1,7 +1,7 @@
 from pytorch_pretrained_bert.tokenization_transfo_xl import TransfoXLTokenizer
 from pytorch_pretrained_bert.modeling_transfo_xl import (
-	TransfoXLModel,
+    TransfoXLModel,
-	TransfoXLLMHeadModel
+    TransfoXLLMHeadModel
 )
 
 # A lot of models share the same param doc. Use a decorator
@@ -11,20 +11,20 @@ transformer_xl_docstring = """
     - you don't need to specify positioning embeddings indices
     - the tokens in the vocabulary have to be sorted to decreasing frequency.
 
-	Params:
+    Params:
-		pretrained_model_name_or_path: either:
+        pretrained_model_name_or_path: either:
-			- a str with the name of a pre-trained model to load selected in the list of:
+            - a str with the name of a pre-trained model to load selected in the list of:
-				. `transfo-xl-wt103`
+                . `transfo-xl-wt103`
-			- a path or url to a pretrained model archive containing:
+            - a path or url to a pretrained model archive containing:
-				. `transfo_xl_config.json` a configuration file for the model
+                . `transfo_xl_config.json` a configuration file for the model
-				. `pytorch_model.bin` a PyTorch dump of a TransfoXLModel instance
+                . `pytorch_model.bin` a PyTorch dump of a TransfoXLModel instance
-			- a path or url to a pretrained model archive containing:
+            - a path or url to a pretrained model archive containing:
-				. `transfo_xl_config.json` a configuration file for the model
+                . `transfo_xl_config.json` a configuration file for the model
-				. `model.chkpt` a TensorFlow checkpoint
+                . `model.chkpt` a TensorFlow checkpoint
-		from_tf: should we load the weights from a locally saved TensorFlow checkpoint
+        from_tf: should we load the weights from a locally saved TensorFlow checkpoint
-		cache_dir: an optional path to a folder in which the pre-trained models will be cached.
+        cache_dir: an optional path to a folder in which the pre-trained models will be cached.
-		state_dict: an optional state dictionnary (collections.OrderedDict object) to use instead of pre-trained models
+        state_dict: an optional state dictionnary (collections.OrderedDict object) to use instead of pre-trained models
-		*inputs, **kwargs: additional input for the specific TransformerXL class
+        *inputs, **kwargs: additional input for the specific TransformerXL class
 """
 
 
@@ -45,12 +45,12 @@ def transformerXLTokenizer(*args, **kwargs):
                                        * transfo-xl-wt103
 
     Example:
-		>>> import torch
+        >>> import torch
         >>> tokenizer = torch.hub.load('huggingface/pytorch-pretrained-BERT', 'transformerXLTokenizer', 'transfo-xl-wt103')
-		
+        
-		>>> text = "Who was Jim Henson ?"
+        >>> text = "Who was Jim Henson ?"
         >>> tokenized_text = tokenizer.tokenize(tokenized_text)
-		>>> indexed_tokens = tokenizer.convert_tokens_to_ids(tokenized_text)
+        >>> indexed_tokens = tokenizer.convert_tokens_to_ids(tokenized_text)
     """
     tokenizer = TransfoXLTokenizer.from_pretrained(*args, **kwargs)
     return tokenizer
@@ -60,33 +60,33 @@ def transformerXLTokenizer(*args, **kwargs):
 def transformerXLModel(*args, **kwargs):
     """
     gpt2Model is the basic OpenAI GPT-2 Transformer model based on
-	identical stacked masked self-attention blocks and pre-trained
+    identical stacked masked self-attention blocks and pre-trained
-	on large scale dataset using language modeling signal.
+    on large scale dataset using language modeling signal.
 
     Example:
         # Load the tokenizer
-		>>> import torch
+        >>> import torch
         >>> tokenizer = torch.hub.load('huggingface/pytorch-pretrained-BERT', 'transformerXLTokenizer', 'transfo-xl-wt103')
 
         #  Prepare tokenized input
         >>> text_1 = "Who was Jim Henson ?"
-		>>> text_2 = "Jim Henson was a puppeteer"
+        >>> text_2 = "Jim Henson was a puppeteer"
-		>>> tokenized_text_1 = tokenizer.tokenize(text_1)
+        >>> tokenized_text_1 = tokenizer.tokenize(text_1)
-		>>> tokenized_text_2 = tokenizer.tokenize(text_2)
+        >>> tokenized_text_2 = tokenizer.tokenize(text_2)
         >>> indexed_tokens_1 = tokenizer.convert_tokens_to_ids(tokenized_text_1)
         >>> indexed_tokens_2 = tokenizer.convert_tokens_to_ids(tokenized_text_2)
-		>>> tokens_tensor_1 = torch.tensor([indexed_tokens_1])
+        >>> tokens_tensor_1 = torch.tensor([indexed_tokens_1])
-		>>> tokens_tensor_2 = torch.tensor([indexed_tokens_2])
+        >>> tokens_tensor_2 = torch.tensor([indexed_tokens_2])
 
         # Load transformerXLModel
         >>> model = torch.hub.load('huggingface/pytorch-pretrained-BERT', 'transformerXLModel', 'transfo-xl-wt103')
         >>> model.eval()
 
         # Predict hidden states features for each layer
-		# We can re-use the memory cells in a subsequent call to attend a longer context
+        # We can re-use the memory cells in a subsequent call to attend a longer context
         >>> with torch.no_grad():
                 hidden_states_1, mems_1 = model(tokens_tensor_1)
-				hidden_states_2, mems_2 = model(tokens_tensor_2, mems=mems_1)
+                hidden_states_2, mems_2 = model(tokens_tensor_2, mems=mems_1)
     """
     model = TransfoXLModel.from_pretrained(*args, **kwargs)
     return model
@@ -96,37 +96,37 @@ def transformerXLModel(*args, **kwargs):
 def transformerXLLMHeadModel(*args, **kwargs):
     """
     gpt2LMHeadModel is the OpenAI GPT-2 Transformer model with the
-	tied (pre-trained) language modeling head on top.
+    tied (pre-trained) language modeling head on top.
 
-	Example:
+    Example:
         # Load the tokenizer
-		>>> import torch
+        >>> import torch
         >>> tokenizer = torch.hub.load('huggingface/pytorch-pretrained-BERT', 'transformerXLTokenizer', 'transfo-xl-wt103')
 
         #  Prepare tokenized input
         >>> text_1 = "Who was Jim Henson ?"
-		>>> text_2 = "Jim Henson was a puppeteer"
+        >>> text_2 = "Jim Henson was a puppeteer"
-		>>> tokenized_text_1 = tokenizer.tokenize(text_1)
+        >>> tokenized_text_1 = tokenizer.tokenize(text_1)
-		>>> tokenized_text_2 = tokenizer.tokenize(text_2)
+        >>> tokenized_text_2 = tokenizer.tokenize(text_2)
         >>> indexed_tokens_1 = tokenizer.convert_tokens_to_ids(tokenized_text_1)
         >>> indexed_tokens_2 = tokenizer.convert_tokens_to_ids(tokenized_text_2)
-		>>> tokens_tensor_1 = torch.tensor([indexed_tokens_1])
+        >>> tokens_tensor_1 = torch.tensor([indexed_tokens_1])
-		>>> tokens_tensor_2 = torch.tensor([indexed_tokens_2])
+        >>> tokens_tensor_2 = torch.tensor([indexed_tokens_2])
 
         # Load transformerXLLMHeadModel
         >>> model = torch.hub.load('huggingface/pytorch-pretrained-BERT', 'transformerXLLMHeadModel', 'transfo-xl-wt103')
         >>> model.eval()
 
         # Predict hidden states features for each layer
-		# We can re-use the memory cells in a subsequent call to attend a longer context
+        # We can re-use the memory cells in a subsequent call to attend a longer context
         >>> with torch.no_grad():
                 predictions_1, mems_1 = model(tokens_tensor_1)
-				predictions_2, mems_2 = model(tokens_tensor_2, mems=mems_1)
+                predictions_2, mems_2 = model(tokens_tensor_2, mems=mems_1)
 
-		# Get the predicted last token
+        # Get the predicted last token
-		>>> predicted_index = torch.argmax(predictions_2[0, -1, :]).item()
+        >>> predicted_index = torch.argmax(predictions_2[0, -1, :]).item()
-		>>> predicted_token = tokenizer.convert_ids_to_tokens([predicted_index])[0]
+        >>> predicted_token = tokenizer.convert_ids_to_tokens([predicted_index])[0]
-		>>> assert predicted_token == 'who'
+        >>> assert predicted_token == 'who'
     """
     model = TransfoXLLMHeadModel.from_pretrained(*args, **kwargs)
     return model