ros/LLaMA-Factory
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

support llama pro #2338 , add rslora

Browse Source 
Former-commit-id: 40d659b7f30dd5a004703c176ec1f22dc864e505
This commit is contained in:
hiyouga
2024-02-15 02:27:36 +08:00
parent b403f8d8a8
commit 596b6828cb
24 changed files with 438 additions and 203 deletions
Download Patch File Download Diff File Expand all files Collapse all files

15
src/llmtuner/hparams/generating_args.py
View File

@@ -9,10 +9,12 @@ class GeneratingArguments:
"""
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,
@@ -25,7 +27,8 @@ class GeneratingArguments:
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,
@@ -36,10 +39,12 @@ class GeneratingArguments:
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]: