423A35C7/LLaMA-Factory
1
0
Fork 0
mirror of https://github.com/hiyouga/LLaMA-Factory.git synced 2025-12-16 20:00:36 +08:00
Code Issues Packages Projects Releases Wiki Activity

format style

Browse Source
This commit is contained in:
hiyouga
2024-01-20 20:15:56 +08:00
parent f6d6e00337
commit 638234ceee
73 changed files with 1492 additions and 2325 deletions
Download Patch File Download Diff File Expand all files Collapse all files

27
src/llmtuner/hparams/generating_args.py
View File

@@ -1,5 +1,5 @@
from typing import Any, Dict, Optional
from dataclasses import asdict, dataclass, field
from typing import Any, Dict, Optional
@dataclass
@@ -8,40 +8,37 @@ class GeneratingArguments:
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."}
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."}
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."}
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."}
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."}
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."}
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."}
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."}
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."}
default=1.0, metadata={"help": "Exponential penalty to the length that is used with beam-based generation."}
)
def to_dict(self) -> Dict[str, Any]: