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

release v0.6.1

Browse Source 
Former-commit-id: a59d823f554505b2e649e6e111b9dee8306d3ad8
This commit is contained in:
hiyouga
2024-03-29 11:36:08 +08:00
parent 50224b09cc
commit fbd0584391
5 changed files with 95 additions and 57 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
src/llmtuner/train/utils.py
View File

@@ -70,7 +70,7 @@ def create_modelcard_and_push(
def create_ref_model(
model_args: "ModelArguments", finetuning_args: "FinetuningArguments", add_valuehead: bool = False
) -> Union["PreTrainedModel", "AutoModelForCausalLMWithValueHead"]:
) -> Optional[Union["PreTrainedModel", "AutoModelForCausalLMWithValueHead"]]:
r"""
Creates reference model for PPO/DPO training. Evaluation mode is not supported.
@@ -105,7 +105,7 @@ def create_ref_model(
def create_reward_model(
model: "AutoModelForCausalLMWithValueHead", model_args: "ModelArguments", finetuning_args: "FinetuningArguments"
) -> "AutoModelForCausalLMWithValueHead":
) -> Optional["AutoModelForCausalLMWithValueHead"]:
r"""
Creates reward model for PPO training.
"""