riaz.somc/transformers
1
0
Fork 0
mirror of https://github.com/huggingface/transformers.git synced 2025-07-31 18:22:34 +06:00
Code Issues Actions 4 Packages Projects Releases Wiki Activity

update docs of length_penalty

Browse Source
This commit is contained in:
Manan Dey 2022-04-30 11:43:51 +05:30
parent 7152ed2bae
commit 466bf4800b
1 changed files with 3 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
src/transformers/generation_utils.py
View File

@ -950,9 +950,9 @@ class GenerationMixin:
eos_token_id (`int`, *optional*): eos_token_id (`int`, *optional*):
The id of the *end-of-sequence* token. The id of the *end-of-sequence* token.
length_penalty (`float`, *optional*, defaults to 1.0): length_penalty (`float`, *optional*, defaults to 1.0):
Exponential penalty to the length. 1.0 means no penalty. Set to values < 1.0 in order to encourage the Exponential penalty to the length. 1.0 means that the beam score is penalized by the sequence length. 0.0 means no penalty. Set to values < 0.0 in order to encourage the
model to generate shorter sequences, to a value > 1.0 in order to encourage the model to produce longer model to generate longer sequences, to a value > 0.0 in order to encourage the model to produce shorter
sequences. sequences.
no_repeat_ngram_size (`int`, *optional*, defaults to 0): no_repeat_ngram_size (`int`, *optional*, defaults to 0):
If set to int > 0, all ngrams of that size can only occur once. If set to int > 0, all ngrams of that size can only occur once.
encoder_no_repeat_ngram_size (`int`, *optional*, defaults to 0): encoder_no_repeat_ngram_size (`int`, *optional*, defaults to 0):