Skip to content

GitLab

Unverified Commit 259eeb6d authored by Patrick Haller's avatar Patrick Haller Committed by GitHub
Browse files

Fixing the output of code examples in the preprocessing chapter (#17162)

parent f8615044
Hide whitespace changes
Inline Side-by-side
Showing with 19 additions and 13 deletions
docs/source/en/preprocessing.mdx
View file @ 259eeb6d
...@@ -158,14 +158,17 @@ Set the `return_tensors` parameter to either `pt` for PyTorch, or `tf` for Tenso ...@@ -158,14 +158,17 @@ Set the `return_tensors` parameter to either `pt` for PyTorch, or `tf` for Tenso
... "Don't think he knows about second breakfast, Pip.", ... "Don't think he knows about second breakfast, Pip.",
... "What about elevensies?", ... "What about elevensies?",
... ] ... ]
>>> encoded_input = tokenizer(batch, padding=True, truncation=True, return_tensors="pt") >>> encoded_input = tokenizer(batch_sentences, padding=True, truncation=True, return_tensors="pt")
>>> print(encoded_input) >>> print(encoded_input)
{'input_ids': tensor([[ 101, 153, 7719, 21490, 1122, 1114, 9582, 1623, 102], {'input_ids': tensor([[101, 1252, 1184, 1164, 1248, 6462, 136, 102, 0, 0, 0, 0, 0, 0, 0],
[ 101, 5226, 1122, 9649, 1199, 2610, 1236, 102, 0]]), [101, 1790, 112, 189, 1341, 1119, 3520, 1164, 1248, 6462, 117, 21902, 1643, 119, 102],
'token_type_ids': tensor([[0, 0, 0, 0, 0, 0, 0, 0, 0], [101, 1327, 1164, 5450, 23434, 136, 102, 0, 0, 0, 0, 0, 0, 0, 0]]),
[0, 0, 0, 0, 0, 0, 0, 0, 0]]), 'token_type_ids': tensor([[0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0],
'attention_mask': tensor([[1, 1, 1, 1, 1, 1, 1, 1, 1], [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0],
[1, 1, 1, 1, 1, 1, 1, 1, 0]])} [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]]),
'attention_mask': tensor([[1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0],
[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1],
[1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0]])}
``` ```
</pt> </pt>
<tf> <tf>
...@@ -178,15 +181,18 @@ Set the `return_tensors` parameter to either `pt` for PyTorch, or `tf` for Tenso ...@@ -178,15 +181,18 @@ Set the `return_tensors` parameter to either `pt` for PyTorch, or `tf` for Tenso
>>> encoded_input = tokenizer(batch_sentences, padding=True, truncation=True, return_tensors="tf") >>> encoded_input = tokenizer(batch_sentences, padding=True, truncation=True, return_tensors="tf")
>>> print(encoded_input) >>> print(encoded_input)
{'input_ids': <tf.Tensor: shape=(2, 9), dtype=int32, numpy= {'input_ids': <tf.Tensor: shape=(2, 9), dtype=int32, numpy=
array([[ 101, 153, 7719, 21490, 1122, 1114, 9582, 1623, 102], array([[101, 1252, 1184, 1164, 1248, 6462, 136, 102, 0, 0, 0, 0, 0, 0, 0],
[ 101, 5226, 1122, 9649, 1199, 2610, 1236, 102, 0]], [101, 1790, 112, 189, 1341, 1119, 3520, 1164, 1248, 6462, 117, 21902, 1643, 119, 102],
[101, 1327, 1164, 5450, 23434, 136, 102, 0, 0, 0, 0, 0, 0, 0, 0]],
dtype=int32)>, dtype=int32)>,
'token_type_ids': <tf.Tensor: shape=(2, 9), dtype=int32, numpy= 'token_type_ids': <tf.Tensor: shape=(2, 9), dtype=int32, numpy=
array([[0, 0, 0, 0, 0, 0, 0, 0, 0], array([[0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0],
[0, 0, 0, 0, 0, 0, 0, 0, 0]], dtype=int32)>, [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0],
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]], dtype=int32)>,
'attention_mask': <tf.Tensor: shape=(2, 9), dtype=int32, numpy= 'attention_mask': <tf.Tensor: shape=(2, 9), dtype=int32, numpy=
array([[1, 1, 1, 1, 1, 1, 1, 1, 1], array([[1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0],
[1, 1, 1, 1, 1, 1, 1, 1, 0]], dtype=int32)>} [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1],
[1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0]], dtype=int32)>}
``` ```
</tf> </tf>
</frameworkcontent> </frameworkcontent>
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment