core.training_args

core.training_args

extra axolotl specific training args

Classes

Name	Description
AxolotlCPOConfig	CPO config for CPO training
AxolotlKTOConfig	KTO config for KTO training
AxolotlORPOConfig	ORPO config for ORPO training
AxolotlPRMConfig	PRM config for PRM training
AxolotlRewardConfig	Reward config for Reward training
AxolotlTrainingArguments	Training arguments for Causal trainer

core.training_args.AxolotlCPOConfig(simpo_gamma=None)

CPO config for CPO training

core.training_args.AxolotlKTOConfig()

KTO config for KTO training

core.training_args.AxolotlORPOConfig()

ORPO config for ORPO training

core.training_args.AxolotlPRMConfig()

PRM config for PRM training

core.training_args.AxolotlRewardConfig()

Reward config for Reward training

core.training_args.AxolotlTrainingArguments()

Training arguments for Causal trainer

This code is duplicated due to HF TrainingArguments not setting output_dir with a default value so it can’t be used as a mixin.