Update README.md

README.md

@@ -36,6 +36,7 @@ OSCAR or Open Super-large Crawled Aggregated coRpus is a multilingual corpus obt
 >>> camembert_fill_mask = pipeline("fill-mask", model="camembert-base")
 >>> results = camembert_fill_mask("Le camembert est <mask> :)")
 
+>>> result
 [{'score': 0.49091097712516785,
   'token': 7200,
   'token_str': 'délicieux',
@@ -59,18 +60,19 @@ OSCAR or Open Super-large Crawled Aggregated coRpus is a multilingual corpus obt
 ```
 
 -**Extract contextual embedding features from Camembert output**
+
 ```python
 import torch
-# Tokenize in sub-words with SentencePiece
-tokenized_sentence = tokenizer.tokenize("J'aime le camembert !")
-# ['▁J', "'", 'aime', '▁le', '▁ca', 'member', 't', '▁!'] 
 
-# 1-hot encode and add special starting and end tokens 
-encoded_sentence = tokenizer.encode(tokenized_sentence)
+>>> tokenized_sentence = tokenizer.tokenize("J'aime le camembert !")
+>>> encoded_sentence = tokenizer.encode(tokenized_sentence)
+# Can be done in one step : tokenize.encode("J'aime le camembert !")
+
+>>> tokenized_sentence 
+['▁J', "'", 'aime', '▁le', '▁ca', 'member', 't', '▁!']
+>>> encoded_sentence
 # [5, 121, 11, 660, 16, 730, 25543, 110, 83, 6] 
-# NB: Can be done in one step : tokenize.encode("J'aime le camembert !")
 
-# Feed tokens to Camembert as a torch tensor (batch dim 1)
 encoded_sentence = torch.tensor(encoded_sentence).unsqueeze(0)
 embeddings, _ = camembert(encoded_sentence)
 # embeddings.detach()
@@ -79,21 +81,4 @@ embeddings, _ = camembert(encoded_sentence)
 #         [ 0.0606, -0.1811, -0.0418,  ..., -0.1815,  0.0880, -0.0766],
 #         [-0.1561, -0.1127,  0.2687,  ..., -0.0648,  0.0249,  0.0446],
 #         ...,
-```
-
--**Extract contextual embedding features from all Camembert layers**
-```python
-from transformers import CamembertConfig
-# (Need to reload the model with new config)
-config = CamembertConfig.from_pretrained("camembert-base", output_hidden_states=True)
-camembert = CamembertModel.from_pretrained("camembert-base", config=config)
-
-embeddings, _, all_layer_embeddings = camembert(encoded_sentence)
-#  all_layer_embeddings list of len(all_layer_embeddings) == 13 (input embedding layer + 12 self attention layers)
-all_layer_embeddings[5]
-# layer 5 contextual embedding : size torch.Size([1, 10, 768])
-#tensor([[[-0.0032,  0.0075,  0.0040,  ..., -0.0025, -0.0178, -0.0210],
-#         [-0.0996, -0.1474,  0.1057,  ..., -0.0278,  0.1690, -0.2982],
-#         [ 0.0557, -0.0588,  0.0547,  ..., -0.0726, -0.0867,  0.0699],
-#         ...,
 ```