423A35C7/LLaMA-Factory
1
0
Fork 0
mirror of https://github.com/hiyouga/LLaMA-Factory.git synced 2025-12-15 11:20:35 +08:00
Code Issues Packages Projects Releases Wiki Activity

fix #944

Browse Source
This commit is contained in:
hiyouga
2023-09-21 19:51:02 +08:00
parent ace3f85a72
commit 338b8664ed
11 changed files with 116 additions and 101 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
src/llmtuner/hparams/model_args.py
View File

@@ -63,18 +63,10 @@ class ModelArguments:
default=None,
metadata={"help": "Auth token to log in with Hugging Face Hub."}
)
compute_dtype: Optional[torch.dtype] = field(
default=None,
metadata={"help": "Used in quantization configs. Do not specify this argument manually."}
)
model_max_length: Optional[int] = field(
default=None,
metadata={"help": "Used in rope scaling. Do not specify this argument manually."}
)
def __post_init__(self):
if self.compute_dtype is not None or self.model_max_length is not None:
raise ValueError("These arguments cannot be specified.")
self.compute_dtype = None
self.model_max_length = None
if self.checkpoint_dir is not None: # support merging multiple lora weights
self.checkpoint_dir = [cd.strip() for cd in self.checkpoint_dir.split(",")]