patience definition to match the paper
This commit is contained in:
@@ -263,7 +263,7 @@ def cli():
|
||||
parser.add_argument("--temperature", type=float, default=0, help="temperature to use for sampling")
|
||||
parser.add_argument("--best_of", type=optional_int, default=5, help="number of candidates when sampling with non-zero temperature")
|
||||
parser.add_argument("--beam_size", type=optional_int, default=5, help="number of beams in beam search, only applicable when temperature is zero")
|
||||
parser.add_argument("--patience", type=float, default=0.0, help="optional patience value to use in beam decoding, as in https://arxiv.org/abs/2204.05424, the default (0.0) is equivalent to not using patience")
|
||||
parser.add_argument("--patience", type=float, default=None, help="optional patience value to use in beam decoding, as in https://arxiv.org/abs/2204.05424, the default (1.0) is equivalent to conventional beam search")
|
||||
parser.add_argument("--length_penalty", type=float, default=None, help="optional token length penalty coefficient (alpha) as in https://arxiv.org/abs/1609.08144, uses simple lengt normalization by default")
|
||||
|
||||
parser.add_argument("--suppress_tokens", type=str, default="-1", help="comma-separated list of token ids to suppress during sampling; '-1' will suppress most special characters except common punctuations")
|
||||
|
||||
Reference in New Issue
Block a user