Merge branch 'master' into check-link-validity

transformers/modeling_ctrl.py

@@ -252,7 +252,7 @@ class CTRLModel(CTRLPreTrainedModel):
         **last_hidden_state**: ``torch.FloatTensor`` of shape ``(batch_size, sequence_length, hidden_size)``
             Sequence of hidden-states at the last layer of the model.
         **past**:
-            list of ``torch.FloatTensor`` (one for each layer) of shape ``(batch_size, num_heads, sequence_length, sequence_length)``:
+            list of ``torch.FloatTensor`` (one for each layer) of shape ``(2, batch_size, num_heads, sequence_length, embed_size_per_head)``:
             that contains pre-computed hidden-states (key and values in the attention blocks).
             Can be used (see `past` input) to speed up sequential decoding. The token ids which have their past given to this model 
             should not be passed as input ids as they have already been computed.
@@ -438,7 +438,7 @@ class CTRLLMHeadModel(CTRLPreTrainedModel):
         **prediction_scores**: ``torch.FloatTensor`` of shape ``(batch_size, sequence_length, config.vocab_size)``
             Prediction scores of the language modeling head (scores for each vocabulary token before SoftMax).
         **past**:
-            list of ``torch.FloatTensor`` (one for each layer) of shape ``(batch_size, num_heads, sequence_length, sequence_length)``:
+            list of ``torch.FloatTensor`` (one for each layer) of shape ``(2, batch_size, num_heads, sequence_length, embed_size_per_head)``:
             that contains pre-computed hidden-states (key and values in the attention blocks).
             Can be used (see `past` input) to speed up sequential decoding. The token ids which have their past given to this model 
             should not be passed as input ids as they have already been computed.

transformers/modeling_gpt2.py

@@ -329,7 +329,7 @@ class GPT2Model(GPT2PreTrainedModel):
         **last_hidden_state**: ``torch.FloatTensor`` of shape ``(batch_size, sequence_length, hidden_size)``
             Sequence of hidden-states at the last layer of the model.
         **past**:
-            list of ``torch.FloatTensor`` (one for each layer) of shape ``(batch_size, num_heads, sequence_length, sequence_length)``:
+            list of ``torch.FloatTensor`` (one for each layer) of shape ``(2, batch_size, num_heads, sequence_length, embed_size_per_head)``:
             that contains pre-computed hidden-states (key and values in the attention blocks).
             Can be used (see `past` input) to speed up sequential decoding. The token ids which have their past given to this model 
             should not be passed as input ids as they have already been computed.
@@ -503,7 +503,7 @@ class GPT2LMHeadModel(GPT2PreTrainedModel):
         **prediction_scores**: ``torch.FloatTensor`` of shape ``(batch_size, sequence_length, config.vocab_size)``
             Prediction scores of the language modeling head (scores for each vocabulary token before SoftMax).
         **past**:
-            list of ``torch.FloatTensor`` (one for each layer) of shape ``(batch_size, num_heads, sequence_length, sequence_length)``:
+            list of ``torch.FloatTensor`` (one for each layer) of shape ``(2, batch_size, num_heads, sequence_length, embed_size_per_head)``:
             that contains pre-computed hidden-states (key and values in the attention blocks).
             Can be used (see `past` input) to speed up sequential decoding. The token ids which have their past given to this model 
             should not be passed as input ids as they have already been computed.
@@ -596,7 +596,7 @@ class GPT2DoubleHeadsModel(GPT2PreTrainedModel):
         **mc_prediction_scores**: ``torch.FloatTensor`` of shape ``(batch_size, num_choices)``
             Prediction scores of the multiplechoice classification head (scores for each choice before SoftMax).
         **past**:
-            list of ``torch.FloatTensor`` (one for each layer) of shape ``(batch_size, num_heads, sequence_length, sequence_length)``:
+            list of ``torch.FloatTensor`` (one for each layer) of shape ``(2, batch_size, num_heads, sequence_length, embed_size_per_head)``:
             that contains pre-computed hidden-states (key and values in the attention blocks).
             Can be used (see `past` input) to speed up sequential decoding. The token ids which have their past given to this model 
             should not be passed as input ids as they have already been computed.

transformers/modeling_openai.py

@@ -50,8 +50,10 @@ def load_tf_weights_in_openai_gpt(model, config, openai_checkpoint_folder_path):
 
     logger.info("Loading weights from {}".format(openai_checkpoint_folder_path))
 
-    names = json.load(open(openai_checkpoint_folder_path + '/parameters_names.json', "r", encoding='utf-8'))
-    shapes = json.load(open(openai_checkpoint_folder_path + '/params_shapes.json', "r", encoding='utf-8'))
+    with open(openai_checkpoint_folder_path + '/parameters_names.json', "r", encoding='utf-8') as names_handle:
+        names = json.load(names_handle)
+    with open(openai_checkpoint_folder_path + '/params_shapes.json', "r", encoding='utf-8') as shapes_handle:
+        shapes = json.load(shapes_handle)
     offsets = np.cumsum([np.prod(shape) for shape in shapes])
     init_params = [np.load(openai_checkpoint_folder_path + '/params_{}.npy'.format(n)) for n in range(10)]
     init_params = np.split(np.concatenate(init_params, 0), offsets)[:-1]

transformers/modeling_tf_ctrl.py

@@ -400,7 +400,7 @@ class TFCTRLModel(TFCTRLPreTrainedModel):
         **last_hidden_state**: ``tf.Tensor`` of shape ``(batch_size, sequence_length, hidden_size)``
             Sequence of hidden-states at the last layer of the model.
         **past**:
-            list of ``tf.Tensor`` (one for each layer) of shape ``(batch_size, num_heads, sequence_length, sequence_length)``:
+            list of ``tf.Tensor`` (one for each layer) of shape ``(2, batch_size, num_heads, sequence_length, embed_size_per_head)``:
             that contains pre-computed hidden-states (key and values in the attention blocks).
             Can be used (see `past` input) to speed up sequential decoding.
         **hidden_states**: (`optional`, returned when ``config.output_hidden_states=True``)
@@ -462,7 +462,7 @@ class TFCTRLLMHeadModel(TFCTRLPreTrainedModel):
         **prediction_scores**: ``torch.FloatTensor`` of shape ``(batch_size, sequence_length, config.vocab_size)``
             Prediction scores of the language modeling head (scores for each vocabulary token before SoftMax).
         **past**:
-            list of ``tf.Tensor`` (one for each layer) of shape ``(batch_size, num_heads, sequence_length, sequence_length)``:
+            list of ``tf.Tensor`` (one for each layer) of shape ``(2, batch_size, num_heads, sequence_length, embed_size_per_head)``:
             that contains pre-computed hidden-states (key and values in the attention blocks).
             Can be used (see `past` input) to speed up sequential decoding.
         **hidden_states**: (`optional`, returned when ``config.output_hidden_states=True``)