riaz.somc/transformers
1
0
Fork 0
mirror of https://github.com/huggingface/transformers.git synced 2025-07-31 10:12:23 +06:00
Code Issues Actions 23 Packages Projects Releases Wiki Activity

Improve GPT2 doc (#18787)

Browse Source 
* Minor typo in GPT2 doc

* improve gpt2 label doc

* update dim of label in GPT2ForTokenClassification

* add change to tf
This commit is contained in:
Ekagra Ranjan 2022-08-31 22:56:39 +05:30 committed by GitHub
parent 74690b62a1
commit f210e2a414
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
2 changed files with 4 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
src/transformers/models/gpt2/modeling_gpt2.py
View File

@ -1225,10 +1225,10 @@ class GPT2DoubleHeadsModel(GPT2PreTrainedModel):
r"""
mc_token_ids (`torch.LongTensor` of shape `(batch_size, num_choices)`, *optional*, default to index of the last token of the input):
Index of the classification token in each input sequence. Selected in the range `[0, input_ids.size(-1) -
1[`.
1]`.
labels (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*):
Labels for language modeling. Note that the labels **are shifted** inside the model, i.e. you can set
`labels = input_ids` Indices are selected in `[-100, 0, ..., config.vocab_size - 1]` All labels set to
`labels = input_ids`. Indices are selected in `[-100, 0, ..., config.vocab_size - 1]`. All labels set to
`-100` are ignored (masked), the loss is only computed for labels in `[0, ..., config.vocab_size - 1]`
mc_labels (`torch.LongTensor` of shape `(batch_size)`, *optional*):
Labels for computing the multiple choice classification loss. Indices should be in `[0, ..., num_choices]`
@ -1519,7 +1519,7 @@ class GPT2ForTokenClassification(GPT2PreTrainedModel):
return_dict: Optional[bool] = None,
) -> Union[Tuple, TokenClassifierOutput]:
r"""
labels (`torch.LongTensor` of shape `(batch_size,)`, *optional*):
labels (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*):
Labels for computing the sequence classification/regression loss. Indices should be in `[0, ...,
config.num_labels - 1]`. If `config.num_labels == 1` a regression loss is computed (Mean-Square loss), If
`config.num_labels > 1` a classification loss is computed (Cross-Entropy).

2
src/transformers/models/gpt2/modeling_tf_gpt2.py
View File

@ -983,7 +983,7 @@ class TFGPT2DoubleHeadsModel(TFGPT2PreTrainedModel):
r"""
mc_token_ids (`tf.Tensor` or `Numpy array` of shape `(batch_size, num_choices)`, *optional*, default to index of the last token of the input):
Index of the classification token in each input sequence. Selected in the range `[0, input_ids.size(-1) -
1[`.
1]`.
Return: