Path	Lines of Code
MANIFEST.in	6
pyproject.toml	25
scripts/add_copyrights.py	41
scripts/generate_tiny_models.py	199
scripts/generate_toolcall_dataset.py	113
scripts/generate_zen_dataset.py	614
scripts/log_example_reports.py	120
scripts/log_reports.py	122
setup.cfg	87
setup.py	2
trl/__init__.py	199
trl/accelerate_configs/fsdp1.yaml	28
trl/accelerate_configs/fsdp2.yaml	24
trl/accelerate_configs/multi_gpu.yaml	16
trl/accelerate_configs/single_gpu.yaml	16
trl/accelerate_configs/zero1.yaml	20
trl/accelerate_configs/zero2.yaml	21
trl/accelerate_configs/zero3.yaml	22
trl/cli.py	72
trl/core.py	105
trl/data_utils.py	325
trl/environment/__init__.py	10
trl/environment/base_environment.py	299
trl/extras/__init__.py	10
trl/extras/best_of_n_sampler.py	67
trl/extras/dataset_formatting.py	60
trl/extras/profiling.py	27
trl/extras/vllm_client.py	148
trl/import_utils.py	91
trl/mergekit_utils.py	180
trl/models/__init__.py	54
trl/models/activation_offloading.py	236
trl/models/auxiliary_modules.py	64
trl/models/modeling_base.py	481
trl/models/modeling_sd_base.py	490
trl/models/modeling_value_head.py	237
trl/models/sd_utils.py	74
trl/models/utils.py	208
trl/rewards/__init__.py	10
trl/rewards/format_rewards.py	7
trl/scripts/__init__.py	10
trl/scripts/dpo.py	82
trl/scripts/env.py	57
trl/scripts/grpo.py	82
trl/scripts/kto.py	51
trl/scripts/sft.py	63
trl/scripts/utils.py	138
trl/scripts/vllm_serve.py	316
trl/trainer/__init__.py	145
trl/trainer/alignprop_config.py	96
trl/trainer/alignprop_trainer.py	291
trl/trainer/bco_config.py	128
trl/trainer/bco_trainer.py	1073
trl/trainer/callbacks.py	363
trl/trainer/cpo_config.py	111
trl/trainer/cpo_trainer.py	741
trl/trainer/ddpo_config.py	187
trl/trainer/ddpo_trainer.py	433
trl/trainer/dpo_config.py	264
trl/trainer/dpo_trainer.py	1257
trl/trainer/gkd_config.py	61
trl/trainer/gkd_trainer.py	239
trl/trainer/grpo_config.py	367
trl/trainer/grpo_trainer.py	971
trl/trainer/iterative_sft_config.py	48
trl/trainer/iterative_sft_trainer.py	330
trl/trainer/judges.py	201
trl/trainer/kto_config.py	147
trl/trainer/kto_trainer.py	1235
trl/trainer/model_config.py	100
trl/trainer/nash_md_config.py	17
trl/trainer/nash_md_trainer.py	360
trl/trainer/online_dpo_config.py	111
trl/trainer/online_dpo_trainer.py	544
trl/trainer/orpo_config.py	97
trl/trainer/orpo_trainer.py	730
trl/trainer/ppo_config.py	72
trl/trainer/ppo_trainer.py	666
trl/trainer/prm_config.py	66
trl/trainer/prm_trainer.py	217
trl/trainer/reward_config.py	60
trl/trainer/reward_trainer.py	293
trl/trainer/rloo_config.py	58
trl/trainer/rloo_trainer.py	549
trl/trainer/sft_config.py	159
trl/trainer/sft_trainer.py	590
trl/trainer/utils.py	1120
trl/trainer/xpo_config.py	16
trl/trainer/xpo_trainer.py	404