423A35C7/LLaMA-Factory
1
0
Fork 0
mirror of https://github.com/hiyouga/LLaMA-Factory.git synced 2025-12-16 20:00:36 +08:00
Code Issues Packages Projects Releases Wiki Activity

allow non-packing pretraining

Browse Source
This commit is contained in:
hiyouga
2024-03-09 22:21:46 +08:00
parent 412c52e325
commit bdb496644c
22 changed files with 64 additions and 67 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
src/llmtuner/train/utils.py
View File

@@ -46,7 +46,7 @@ def create_modelcard_and_push(
def create_ref_model(
model_args: "ModelArguments", finetuning_args: "FinetuningArguments", add_valuehead: Optional[bool] = False
model_args: "ModelArguments", finetuning_args: "FinetuningArguments", add_valuehead: bool = False
) -> Union["PreTrainedModel", "AutoModelForCausalLMWithValueHead"]:
r"""
Creates reference model for PPO/DPO training. Evaluation mode is not supported.