Spaces:
Runtime error
Runtime error
File size: 1,969 Bytes
20076b6 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 |
from dataclasses import asdict, dataclass, field
from typing import Any, Dict, Optional
@dataclass
class GeneratingArguments:
r"""
Arguments pertaining to specify the decoding parameters.
"""
do_sample: Optional[bool] = field(
default=True, metadata={"help": "Whether or not to use sampling, use greedy decoding otherwise."}
)
temperature: Optional[float] = field(
default=0.95, metadata={"help": "The value used to modulate the next token probabilities."}
)
top_p: Optional[float] = field(
default=0.7,
metadata={
"help": "The smallest set of most probable tokens with probabilities that add up to top_p or higher are kept."
},
)
top_k: Optional[int] = field(
default=50,
metadata={"help": "The number of highest probability vocabulary tokens to keep for top-k filtering."},
)
num_beams: Optional[int] = field(
default=1, metadata={"help": "Number of beams for beam search. 1 means no beam search."}
)
max_length: Optional[int] = field(
default=512,
metadata={"help": "The maximum length the generated tokens can have. It can be overridden by max_new_tokens."},
)
max_new_tokens: Optional[int] = field(
default=512,
metadata={"help": "The maximum numbers of tokens to generate, ignoring the number of tokens in the prompt."},
)
repetition_penalty: Optional[float] = field(
default=1.0, metadata={"help": "The parameter for repetition penalty. 1.0 means no penalty."}
)
length_penalty: Optional[float] = field(
default=1.0, metadata={"help": "Exponential penalty to the length that is used with beam-based generation."}
)
def to_dict(self) -> Dict[str, Any]:
args = asdict(self)
if args.get("max_new_tokens", -1) > 0:
args.pop("max_length", None)
else:
args.pop("max_new_tokens", None)
return args
|