phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-03 19:57:35 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge 66f4af7fec into d266c59c2a

Browse source
This commit is contained in:
Sarthak Deshpande 2025-10-03 14:11:23 +02:00 • committed by GitHub
commit 31bbb2de18
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
2 changed files with 2 additions and 2 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
use_reference_model: bool = True
dpo_loss_type: Literal["sigmoid", "hinge", "ipo", "kto_pair"] = "sigmoid"
dpo_output_dir: str
dpo_output_dir: str | None = None
@classmethod
def sample_run_config(cls, __distro_dir__: str, **kwargs: Any) -> dict[str, Any]:

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

@ -135,7 +135,7 @@ class HuggingFacePostTrainingImpl:
resources_allocated, checkpoints = await recipe.train(
model=finetuned_model,
output_dir=f"{self.config.dpo_output_dir}/{job_uuid}",
output_dir=f"{self.config.dpo_output_dir}/{job_uuid}" if self.config.dpo_output_dir else None,
job_uuid=job_uuid,
dpo_config=algorithm_config,
config=training_config,