Trainers#
- easydel.trainers.__init__
BaseTrainerDPOConfigDPOTrainerGRPOConfigGRPOTrainerJaxDistributedConfigORPOConfigORPOTrainerRewardConfigRewardTrainerSFTConfigSFTTrainerTrainerTrainingArgumentsconversations_formatting_function()create_constant_length_dataset()create_prompt_creator()get_formatting_func_from_dataset()instructions_formatting_function()pack_sequences()
- easydel.trainers.base_trainer
- Direct Preference Optimization Trainer
- Group Relative Policy Optimization
- Odds Ratio Preference Optimization Trainer
- easydel.trainers.packer
- easydel.trainers.prompt_utils
- Reward Trainer
- Supervised Fine Tuning Trainer
- Trainer
- easydel.trainers.trainer_protocol
- easydel.trainers.training_configurations
- easydel.trainers.training_utils
- easydel.trainers.utils
DPODataCollatorWithPaddingDataCollatorForCompletionOnlyLMDataCollatorForPreferenceJaxDistributedConfigRewardDataCollatorWithPaddingadd_bos_token_if_needed()add_eos_token_if_needed()conversations_formatting_function()create_constant_length_dataset()create_prompt_creator()first_true_indices()get_formatting_func_from_dataset()instructions_formatting_function()leave_alone_context_manager()pad()pad_sequence()pad_to_length()shift_and_pad()tolist()truncate_right()