trl/__init__.py,sha256=s9txH58_4JXIk4UxFI6wdP9zWmen7XVMmbmPx3eSrKc,5703
trl/cli.py,sha256=0Hs7nhIq9R_lC46RemoeacIB0F1P5Cld8ZhIBTjYzas,7685
trl/core.py,sha256=51coBydZiWVEQ7bmUCJqJg-dmNDsqwc1hcK42bbtwUk,2490
trl/data_utils.py,sha256=SK3YciKKm22SNIO-jLTcti58DlMlNgTHQ8F2tuHdmEE,34989
trl/import_utils.py,sha256=6pQRoaJhllTEx0UM2XSaXr7unbUU264OZV4J4KHyvOc,5763
trl/mergekit_utils.py,sha256=rShhech6lNWWyfgAbz_NAbeqMcl7hC87a0_H6cwYQQU,11098
trl/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
trl/accelerate_configs/fsdp1.yaml,sha256=FBw8i6diLwfcUI6Uu7T-UTpd7niY062tLsCFMLoT0c4,725
trl/accelerate_configs/fsdp2.yaml,sha256=zg1L3kVDJb7kvuxIPaqMN6mZQFD2mvG8IxSRmkY7dDk,627
trl/accelerate_configs/multi_gpu.yaml,sha256=yDX-SPo8qY3SW8jsf_53VJX1GwIV20wmRPBbCKf4_8I,321
trl/accelerate_configs/single_gpu.yaml,sha256=4MuOZIjHNir2adOzaoOgBwD9IXXRbPNPzBYVW-zkc7I,316
trl/accelerate_configs/zero1.yaml,sha256=fyUlyzQ_nhP6oamOgOBM7MDZMuHvG4xZfm_-2wnuYTo,441
trl/accelerate_configs/zero2.yaml,sha256=kW58rFIjO1Jz0-TWjg2zUHO5BUBHI4TPFIUHb2M-WiQ,470
trl/accelerate_configs/zero3.yaml,sha256=VN3HDSxEn_WCvYpML4thWO7cpr2N39VwAJjMvPtwfxE,498
trl/experimental/__init__.py,sha256=MM96UWQuOHAPXqq0RUF1jW5A2LkvC4joi8ChEoULlt4,1248
trl/experimental/bema_for_ref_model/__init__.py,sha256=5pu2RcnVVznaCqfS5aSOLJbiFSoSV6YiGagczI_WGUw,683
trl/experimental/bema_for_ref_model/callback.py,sha256=8o2Od5TwRmvkXwrc9TxO8JYiO9bChS3aX7TiuDYhA-I,9642
trl/experimental/bema_for_ref_model/dpo_trainer.py,sha256=z38itb0kQyDwzLHntTsMdIXF2EM3GjjHvTYljn3Zakw,1181
trl/experimental/gfpo/__init__.py,sha256=kDdEyI01oN5n6lwG3uLRdzqodtsfy0Z8ySROzUCVZAY,686
trl/experimental/gfpo/gfpo_config.py,sha256=2bsmGROd8ZVVIC0OTQwA0W3rVQB0jLREBX-wM8Ec6n8,1356
trl/experimental/gfpo/gfpo_trainer.py,sha256=0iNWo3B_CfepKHBruyPTKWZN4uscFQYghioV1DSPxhs,19217
trl/experimental/grpo_with_replay_buffer/__init__.py,sha256=XHyiiLigOrWnVkJwmss5STwZlrT5B-TM1wXVWLdpuOU,770
trl/experimental/grpo_with_replay_buffer/grpo_with_replay_buffer_config.py,sha256=2bOuxx6sdH-DRqtVX7IaGYgWqZZYxubMWAwdrJLYASs,1373
trl/experimental/grpo_with_replay_buffer/grpo_with_replay_buffer_trainer.py,sha256=OrLlwCQJXKqBdPCIokehRJbv45OSEEbIQFWIXdnGuQ8,33048
trl/experimental/gspo_token/__init__.py,sha256=KF6fqOTgMYJQzGyGcHn7u6yfEq8zaYXA_uRTu9ME_4k,650
trl/experimental/gspo_token/grpo_trainer.py,sha256=x6DNd7z8XLX3RohxCr9LDWPTSUELRgTb_l6-1nrywus,7993
trl/extras/__init__.py,sha256=5CIPkzvP9D6vpnWLNZz23RNU98MfjeBsxBFMHXKM09U,961
trl/extras/best_of_n_sampler.py,sha256=XXZndrDdROrL--KY92qspFgoC5RNDJ7nSHxxqLfamqE,5978
trl/extras/dataset_formatting.py,sha256=katgkGEu7wbYFijK6arJ9JX1c0nwM_jMw2bBQiIQQ6M,6367
trl/extras/profiling.py,sha256=thY1EHuh8CfDieHEVryUi0Ug2oqmmAnlVkDghwBrNDc,3268
trl/extras/vllm_client.py,sha256=vWTEQUWbEOcKnmlfDC99HQTgpRAX9UGTnRhl5giNrpA,18296
trl/models/__init__.py,sha256=JO7wcR-eXc1NxGbwljLq4Fohl9PBFTo_-u8KPVrOXDQ,1891
trl/models/activation_offloading.py,sha256=DgwQYJ-MxqxbdSgnDGxK0mzO3a0RRmgYYUNBWi9-XZ8,25376
trl/models/modeling_base.py,sha256=C-RLHFnsLcfY-AXIVdnvT3ltCVEpWQ0c7yH24p8vHfQ,31438
trl/models/modeling_value_head.py,sha256=CBNB186PHZBF3NUGaotCJx0vGbYXHOqeUDyL84zmm0o,18883
trl/models/utils.py,sha256=sa1UdrTgPMuMCLwQ2lTCZ_-Wsj6aesPaRJztGsJhCJo,24562
trl/rewards/__init__.py,sha256=g1wEbhQ0NjyF5cc_0yXKesOqCDsSygasWmC4us46lBA,1161
trl/rewards/accuracy_rewards.py,sha256=L7DKghYkvgrJVxJEgxYhuN56uHWdUrK7xLI28WQtww8,3886
trl/rewards/format_rewards.py,sha256=fCQhtw6lazljB5Kv20ZAaD5XraoxKqVDBvqbscmldYE,2211
trl/rewards/other_rewards.py,sha256=WhVSfVjOZ5cGaLSfmf9s3BGtnpsrtowY7PMFtcpU1JM,2634
trl/scripts/__init__.py,sha256=tDv5yBlfQh0ovYdrTF-xW7dLwbARJPhHT8JkgKs4KO4,1077
trl/scripts/dpo.py,sha256=vCZSuwZNHeta2seG6IEqifOQbBzi-p0blAQOZyyPUxw,6328
trl/scripts/env.py,sha256=Vj06F7nzIrZZwKjNd0enBgv2EhBoaBLGOVtIiqMY3e4,3522
trl/scripts/grpo.py,sha256=wiMV4RUnGGf5Rx55ZVq8ALMvVZkC8y3bOTLlIrgHpQY,6694
trl/scripts/kto.py,sha256=wmolRh8N7_nKZzHXxIma_evSLBIm-IOvE14UxqHHUC8,5504
trl/scripts/reward.py,sha256=uhjbon_RVMBQ_XkhXF32nwoPMpcYBxMiI6s7uGCT5XA,3803
trl/scripts/rloo.py,sha256=AYmFAdV3EmPk5K6QJNKjRbGyAVvam2dkHT8bQXagaDA,6694
trl/scripts/sft.py,sha256=eNyQV7c1tyurmzf6qjfuLL6cr-NtOJQ8wYaYERGa0sA,6093
trl/scripts/utils.py,sha256=vj3HAZDqO4zYsFmavLHB0Xz1PQ5PryEVrQFSpVUV_JE,18991
trl/scripts/vllm_serve.py,sha256=1yLIHDH0vlTusbSGkFG3d_PTfi15QlOI42QjmmVBysY,31779
trl/templates/lm_model_card.md,sha256=zq0dXorqEOnjHJ8wxwhI3LS2R6qiHmlcgPcVzliwRmc,2158
trl/templates/rm_model_card.md,sha256=O4lxwEsL9ld81LL7rwBwredxAeMDfWfpzwe-k7UYHeg,1951
trl/trainer/__init__.py,sha256=hxCrHTrhd6AXbdyVE8lUVHtXLQFs9pSB_1Uxz_WwM3Q,4600
trl/trainer/base_trainer.py,sha256=s4V7o6tDeUd9td7G5EGBeEsFnwuB6H_UVjFhHOOPGM4,2903
trl/trainer/bco_config.py,sha256=qLWimQZtcqXGqlxDZ2jY7eM97BNUQFYaW_BHbgumWvI,9933
trl/trainer/bco_trainer.py,sha256=MHreYkOM_LjRkxOp__2dDTyGqm6QqBoqsDl_JDubOCM,71428
trl/trainer/callbacks.py,sha256=zfQw4qaWMVwQk7qsxKjfLrkq2hewg3k23APoNasgthk,43806
trl/trainer/cpo_config.py,sha256=ymlf3r8Vm8rplhFoxm38-hQojPVmb85_r8dztyypuEM,10371
trl/trainer/cpo_trainer.py,sha256=cTkVP4S67e3W4mWhyd9vs3fFhTcpumyA_ePgBMFarIw,51358
trl/trainer/dpo_config.py,sha256=QwJxLF0aNGoNuZFHlPoUy0FmapbTU_jyLNfr19-0BEs,26157
trl/trainer/dpo_trainer.py,sha256=VBYbQkcLe8Mz2j2iqE6Gx9oeuVlGmS0CLdkeoi_U_lI,102991
trl/trainer/gkd_config.py,sha256=EHhc8jB-6N-hQQzaJFEe8bfro8msyi43hdWUJCQ1cxc,4889
trl/trainer/gkd_trainer.py,sha256=Yu7OTNqAFYK-WHDZUBwPpzTTv1q4fShpx2os4FsWjUc,20322
trl/trainer/grpo_config.py,sha256=5xkA86BZDM6xrWfwfphF_DtRfq6F89FjAKMqS2UqALs,39340
trl/trainer/grpo_trainer.py,sha256=u2kFGCrPLsQm8dyf_DflIQ1Y7kfSdk988S27kKSiiVQ,100875
trl/trainer/judges.py,sha256=fp-So0L30mSA7X2e2RPVOTPiVgs9u4l5jfiYJP6WT0M,19530
trl/trainer/kto_config.py,sha256=qXbFiouKxT-BIa7dok2883XivFw6V6JMirFkuIBdut8,11238
trl/trainer/kto_trainer.py,sha256=kY0_Gqog_SEykI0UHFUFJi68zxMREqJnrCPlXtb3Uyk,81496
trl/trainer/model_config.py,sha256=kNz4d9E76HaWlPToOTAjlk7aO_F4DxtHkWDklvZ9nC8,9344
trl/trainer/nash_md_config.py,sha256=T3004FbQP7A9mir_I-XvW9GkzoykRL4U_bMg52NLVFE,1844
trl/trainer/nash_md_trainer.py,sha256=-TDtu-WY0GxUdLbuUC7zdSlCyAnxwHFV-cft-K9wb4Q,22603
trl/trainer/online_dpo_config.py,sha256=6s5FOg4qc8yOIm5a1YRSbyuQeQQ0Kx-tqkag54Gja_A,21646
trl/trainer/online_dpo_trainer.py,sha256=VldtQ5_RSGkpI21zohEjK0xAY--b7wx9MVXbyjTQFcQ,77335
trl/trainer/orpo_config.py,sha256=4qg9iJkdl0MKxxDB54Y4YVftMKhG8_BStyRAaKOi0Cs,7684
trl/trainer/orpo_trainer.py,sha256=fTYud2uUkdRWrUfXOrLRCjxZhVc50VzW4XMmYj1gAao,49815
trl/trainer/ppo_config.py,sha256=vmgJyNIUQbPjIH81WuhpS_GPhJpokuWHGNKrBggfSGg,6021
trl/trainer/ppo_trainer.py,sha256=qglosh4wU74k11W4QZev6kWV5lCzEeFQ2VOCNI13VVs,40929
trl/trainer/prm_config.py,sha256=qaXXjVH1xidwoVhIP8lxOzgvbzR_XH6mW3-V-Hm55Fs,4689
trl/trainer/prm_trainer.py,sha256=sVSn8xDppHFuqPvaiR08Xw5wN0VgHD5HD3_BVkiotgE,14250
trl/trainer/reward_config.py,sha256=Zvjxm0OyEpg9uHF-rxzb1Z7aj_Bhh6ee-3WBkDmTvTU,7757
trl/trainer/reward_trainer.py,sha256=oZFlwFXk8yH0IjuVCy1kVqMZb-0mwZRPRbm3yAFy0BU,29472
trl/trainer/rloo_config.py,sha256=rcz-RXG5RlqtTdoVUEzUXlet2M2injCbWSyVmWFjiBw,38613
trl/trainer/rloo_trainer.py,sha256=6N9PqYSKx7B7Pf7L8vmKvDGbRb39oI7pDkCO7XzNmaA,89943
trl/trainer/sft_config.py,sha256=D0HBSpNu6LzvMfCTwm2uvOMerzwcPPaNaGTNWEh2_N0,13525
trl/trainer/sft_trainer.py,sha256=Vw5UQIbwExlSB8PDXcxwbpv66R0_G6Z9_SonkgDBsSA,65950
trl/trainer/utils.py,sha256=cJaIHfP9eEEb6Ffnm4L3wOuPO12bB3HeBidbrMmvmOM,79787
trl/trainer/xpo_config.py,sha256=nPzvCvvJpEWVBNnq-vv5CPpyTVZkQ47ZucVh_87fOPE,1667
trl/trainer/xpo_trainer.py,sha256=bZHkTfCc_dXQ1MP1b9OD1-63Rr7PnkbOUZod-I8M2Sc,25077
trl-0.24.0.dist-info/licenses/LICENSE,sha256=HZDsv3u4D_J-9nt3hfYhSAtlK4LkbHLYpXMLDbZb81U,11355
trl-0.24.0.dist-info/METADATA,sha256=NRxbeNzqPpaLOeutrFPXKKpOcxDhE__1ViavW_buwzM,11567
trl-0.24.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
trl-0.24.0.dist-info/entry_points.txt,sha256=EiubuQrZSGOohRB4xVoiVAyWsPsOHPSVpbzSk8YB0x0,37
trl-0.24.0.dist-info/top_level.txt,sha256=QU12VhjlpAtMnIJqiO2np3RkTB_Eozt1d-g8QDf5P4c,4
trl-0.24.0.dist-info/RECORD,,
