From 645f45c462ae39e2e8a301d6503ba29f9178ab73 Mon Sep 17 00:00:00 2001 From: WybeKoper <40920213+WybeKoper@users.noreply.github.com> Date: Wed, 31 Mar 2021 13:23:15 +0200 Subject: [PATCH] Fixed some typos and removed legacy url (#10989) * Fixed typos * Removed legacy colab notebook from readme Co-authored-by: WybeKoper --- examples/multiple-choice/README.md | 3 --- src/transformers/generation_utils.py | 8 ++++---- .../models/xlm_prophetnet/tokenization_xlm_prophetnet.py | 2 +- .../models/xlm_roberta/tokenization_xlm_roberta_fast.py | 2 +- 4 files changed, 6 insertions(+), 9 deletions(-) diff --git a/examples/multiple-choice/README.md b/examples/multiple-choice/README.md index 3c804b53b4..f86f731b54 100644 --- a/examples/multiple-choice/README.md +++ b/examples/multiple-choice/README.md @@ -129,6 +129,3 @@ python ./examples/multiple-choice/run_tf_multiple_choice.py \ --gradient_accumulation_steps 2 \ --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) diff --git a/src/transformers/generation_utils.py b/src/transformers/generation_utils.py index 777deafc50..086ad26992 100644 --- a/src/transformers/generation_utils.py +++ b/src/transformers/generation_utils.py @@ -1302,10 +1302,10 @@ class GenerationMixin: # argmax 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: 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 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) - # 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: 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 input_ids = torch.cat([input_ids, next_tokens[:, None]], dim=-1) diff --git a/src/transformers/models/xlm_prophetnet/tokenization_xlm_prophetnet.py b/src/transformers/models/xlm_prophetnet/tokenization_xlm_prophetnet.py index edf14eb9c2..43a423b9ec 100644 --- a/src/transformers/models/xlm_prophetnet/tokenization_xlm_prophetnet.py +++ b/src/transformers/models/xlm_prophetnet/tokenization_xlm_prophetnet.py @@ -56,7 +56,7 @@ def load_vocab(vocab_file): 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 `__. This tokenizer inherits from :class:`~transformers.PreTrainedTokenizer` which contains most of the main methods. diff --git a/src/transformers/models/xlm_roberta/tokenization_xlm_roberta_fast.py b/src/transformers/models/xlm_roberta/tokenization_xlm_roberta_fast.py index b3f97e3eaf..0c68590439 100644 --- a/src/transformers/models/xlm_roberta/tokenization_xlm_roberta_fast.py +++ b/src/transformers/models/xlm_roberta/tokenization_xlm_roberta_fast.py @@ -67,7 +67,7 @@ PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = { class XLMRobertaTokenizerFast(PreTrainedTokenizerFast): """ 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 `__. This tokenizer inherits from :class:`~transformers.PreTrainedTokenizerFast` which contains most of the main