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

duplicated line for repeating_words_penalty_for_language_generation

Browse Source
This commit is contained in:
patrickvonplaten
2019-12-23 21:49:32 +01:00
parent aeef4823ab
commit 822f725a07
1 changed files with 0 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
src/transformers/modeling_utils.py
View File

@@ -585,8 +585,6 @@ class PreTrainedModel(nn.Module):
Beginning of sentence token if no prompt is provided. Default to 0. Beginning of sentence token if no prompt is provided. Default to 0.
**eos_token_ids**: (`optional`) int or list of int **eos_token_ids**: (`optional`) int or list of int
End of sequence token or list of tokens to stop the generation. Default to 0. End of sequence token or list of tokens to stop the generation. Default to 0.
**length_penalty**: (`optional`) int
Exponential penalty to the length. Default to 0.
**length_penalty**: (`optional`) float **length_penalty**: (`optional`) float
Exponential penalty to the length. Default to 1. Exponential penalty to the length. Default to 1.
**num_return_sequences**: (`optional`) int **num_return_sequences**: (`optional`) int