phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-08-15 14:08:00 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge 6520a6d39a into 46ff302d87

Browse source
This commit is contained in:
Sarthak Deshpande 2025-08-14 07:07:20 +00:00 • committed by GitHub
commit 44cb26db77
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 1 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

2
llama_stack/providers/inline/post_training/huggingface/config.py
View file

@ -71,7 +71,7 @@ class HuggingFacePostTrainingConfig(BaseModel):
dpo_beta: float = 0.1 dpo_beta: float = 0.1
use_reference_model: bool = True use_reference_model: bool = True
dpo_loss_type: Literal["sigmoid", "hinge", "ipo", "kto_pair"] = "sigmoid" dpo_loss_type: Literal["sigmoid", "hinge", "ipo", "kto_pair"] = "sigmoid"
dpo_output_dir: str dpo_output_dir: str | None = None
@classmethod @classmethod
def sample_run_config(cls, __distro_dir__: str, **kwargs: Any) -> dict[str, Any]: def sample_run_config(cls, __distro_dir__: str, **kwargs: Any) -> dict[str, Any]: