SUMIN/HuggingFace_transformer
1
0
Fork 0
Code Issues Pull Requests Actions 7 Packages Projects Releases Wiki Activity

Fixed some typos and removed legacy url (#10989)

Browse Source 
* Fixed typos

* Removed legacy colab notebook from readme

Co-authored-by: WybeKoper <WybeKoper@users.noreply.github.com>
This commit is contained in:
WybeKoper
2021-03-31 13:23:15 +02:00
committed by GitHub
parent e87505f3a1
commit 645f45c462
4 changed files with 6 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
examples/multiple-choice/README.md
View File

@@ -129,6 +129,3 @@ python ./examples/multiple-choice/run_tf_multiple_choice.py \
--gradient_accumulation_steps 2 \ --gradient_accumulation_steps 2 \
--overwrite_output --overwrite_output
``` ```
# Run it in colab
[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/ViktorAlm/notebooks/blob/master/MPC_GPU_Demo_for_TF_and_PT.ipynb)

8
src/transformers/generation_utils.py
View File

@@ -1302,10 +1302,10 @@ class GenerationMixin:
# argmax # argmax
next_tokens = torch.argmax(next_tokens_scores, dim=-1) next_tokens = torch.argmax(next_tokens_scores, dim=-1)
# add code that transfomers next_tokens to tokens_to_add # add code that transforms next_tokens to tokens_to_add
if eos_token_id is not None: if eos_token_id is not None:
assert pad_token_id is not None, "If eos_token_id is defined, make sure that pad_token_id is defined." assert pad_token_id is not None, "If eos_token_id is defined, make sure that pad_token_id is defined."
next_tokens = next_tokens * unfinished_sequences + (pad_token_id) * (1 - unfinished_sequences) next_tokens = next_tokens * unfinished_sequences + pad_token_id * (1 - unfinished_sequences)
# add token and increase length by one # add token and increase length by one
input_ids = torch.cat([input_ids, next_tokens[:, None]], dim=-1) input_ids = torch.cat([input_ids, next_tokens[:, None]], dim=-1)
@@ -1526,10 +1526,10 @@ class GenerationMixin:
next_tokens = torch.multinomial(probs, num_samples=1).squeeze(1) next_tokens = torch.multinomial(probs, num_samples=1).squeeze(1)
# add code that transfomers next_tokens to tokens_to_add # add code that transforms next_tokens to tokens_to_add
if eos_token_id is not None: if eos_token_id is not None:
assert pad_token_id is not None, "If eos_token_id is defined, make sure that pad_token_id is defined." assert pad_token_id is not None, "If eos_token_id is defined, make sure that pad_token_id is defined."
next_tokens = next_tokens * unfinished_sequences + (pad_token_id) * (1 - unfinished_sequences) next_tokens = next_tokens * unfinished_sequences + pad_token_id * (1 - unfinished_sequences)
# add token and increase length by one # add token and increase length by one
input_ids = torch.cat([input_ids, next_tokens[:, None]], dim=-1) input_ids = torch.cat([input_ids, next_tokens[:, None]], dim=-1)

2
src/transformers/models/xlm_prophetnet/tokenization_xlm_prophetnet.py
View File

@@ -56,7 +56,7 @@ def load_vocab(vocab_file):
class XLMProphetNetTokenizer(PreTrainedTokenizer): class XLMProphetNetTokenizer(PreTrainedTokenizer):
""" """
Adapted from :class:`~transfomers.RobertaTokenizer` and class:`~transfomers.XLNetTokenizer`. Based on Adapted from :class:`~transformers.RobertaTokenizer` and class:`~transformers.XLNetTokenizer`. Based on
`SentencePiece <https://github.com/google/sentencepiece>`__. `SentencePiece <https://github.com/google/sentencepiece>`__.
This tokenizer inherits from :class:`~transformers.PreTrainedTokenizer` which contains most of the main methods. This tokenizer inherits from :class:`~transformers.PreTrainedTokenizer` which contains most of the main methods.

2
src/transformers/models/xlm_roberta/tokenization_xlm_roberta_fast.py
View File

@@ -67,7 +67,7 @@ PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = {
class XLMRobertaTokenizerFast(PreTrainedTokenizerFast): class XLMRobertaTokenizerFast(PreTrainedTokenizerFast):
""" """
Construct a "fast" XLM-RoBERTa tokenizer (backed by HuggingFace's `tokenizers` library). Adapted from Construct a "fast" XLM-RoBERTa tokenizer (backed by HuggingFace's `tokenizers` library). Adapted from
:class:`~transfomers.RobertaTokenizer` and class:`~transfomers.XLNetTokenizer`. Based on `BPE :class:`~transformers.RobertaTokenizer` and class:`~transformers.XLNetTokenizer`. Based on `BPE
<https://huggingface.co/docs/tokenizers/python/latest/components.html?highlight=BPE#models>`__. <https://huggingface.co/docs/tokenizers/python/latest/components.html?highlight=BPE#models>`__.
This tokenizer inherits from :class:`~transformers.PreTrainedTokenizerFast` which contains most of the main This tokenizer inherits from :class:`~transformers.PreTrainedTokenizerFast` which contains most of the main