trl/__init__.py,sha256=z_CH0HmOuXQtghlGKyU735JTU2xm1q3nQOHfZQqOjtQ,5391
trl/cli.py,sha256=0Hs7nhIq9R_lC46RemoeacIB0F1P5Cld8ZhIBTjYzas,7685
trl/data_utils.py,sha256=-GAP6A-2HIkhB8HmMGOh3uCtFENoWVpSNu0H47gbIjk,38364
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/bco/__init__.py,sha256=8CJbPYAotJbNutPt6tlmOFuyLdH3zVDwCu0LoUkLpdQ,682
trl/experimental/bco/bco_config.py,sha256=616YkRE-0N81ouEeNyA7b0-2FYZ-CwLtq34ZKshNgO4,9896
trl/experimental/bco/bco_trainer.py,sha256=WlrVJlk2yEdaWLbe_tIASHtpZ7VB6Tv1ntDABHupiA8,71560
trl/experimental/bema_for_ref_model/__init__.py,sha256=5pu2RcnVVznaCqfS5aSOLJbiFSoSV6YiGagczI_WGUw,683
trl/experimental/bema_for_ref_model/callback.py,sha256=8bgm5Cm0_l9Q-xaT5R4dg5802_VlH5QaozyOtwjtaX8,9641
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=xUcayWWu4lfWZdvWfIQstlssIrLbf4hgcJqpIY_NmVk,1325
trl/experimental/gfpo/gfpo_trainer.py,sha256=HjhazvUGzMkXfWw96eWmTA7aBU7Tw1honoaU4rJYGPQ,20767
trl/experimental/gold/__init__.py,sha256=GYzgNgp_OOSwbaFi3mr5O8j21anppy-oGC9zRbvqE9g,728
trl/experimental/gold/gold.py,sha256=vyLd-u7F4YKbAhMgtfOtqOHW23fzseM4isKCuth8LqU,5038
trl/experimental/gold/gold_config.py,sha256=1NVvqmr7xeGLU3ECedAZjF2gOR1vGQU2arzHakwmQsI,19852
trl/experimental/gold/gold_trainer.py,sha256=hl60BdECgXAyS4wPYN4eX7LiPcWlLM8IAvZJDZN4LYo,98127
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=UIC5J8S3SOXZneASlcPj1UyQ23g1K-2Uz1redJM02bs,35877
trl/experimental/gspo_token/__init__.py,sha256=KF6fqOTgMYJQzGyGcHn7u6yfEq8zaYXA_uRTu9ME_4k,650
trl/experimental/gspo_token/grpo_trainer.py,sha256=zx7b2JedNtW8aeAkNa_-ay2goe7cNqxyq5harsT7ZgE,7992
trl/experimental/papo/__init__.py,sha256=mwIFsCHIovHIgwASDUyUhV-OdGCDcPt7L2JQnDPHdWY,687
trl/experimental/papo/papo_config.py,sha256=RBSVOlIr7MUJ0zRYeegbgZiojPXwszBTugRHUqrBfiU,3141
trl/experimental/papo/papo_trainer.py,sha256=hQtZtoX1QwisHlgDXZ9egXtOT6XRY7_sLqgWPBKDCZI,15667
trl/extras/__init__.py,sha256=Po_3-y5piG9oINxuL8hm7ATrU536lj4eL4ganNbLePw,611
trl/extras/dataset_formatting.py,sha256=2u2q4JiJJlYi84ugFUqX2a2u_gEVPK68l1WdepY8B1M,6375
trl/extras/profiling.py,sha256=thY1EHuh8CfDieHEVryUi0Ug2oqmmAnlVkDghwBrNDc,3268
trl/extras/vllm_client.py,sha256=RZHKN6mLMrAeDRjzFkZWugzMdAM5LeyZwKcV28bBXTs,23003
trl/models/__init__.py,sha256=HaafhL2BdoaM9YRPKfXKDwjxj647FiP8Fit_u6D08LI,1975
trl/models/activation_offloading.py,sha256=ss9xtBXF_2o8FuRI8T2-3HMB4kMcKYy2JX0nfLKFYCg,34695
trl/models/modeling_base.py,sha256=FvF6_rNNB0s7TXqHdLz7xYMUKqPk0i8X-P86FqE4xiQ,31398
trl/models/modeling_value_head.py,sha256=CBNB186PHZBF3NUGaotCJx0vGbYXHOqeUDyL84zmm0o,18883
trl/models/utils.py,sha256=c6khVJqRF8z5sDTtu_g51wFGUUdhXPJQmt-dZU5-bE0,26358
trl/rewards/__init__.py,sha256=cW5GdHBwGx9vHMhJAkybGVGKFAQ7RhENwjw2-hS-Lyk,1160
trl/rewards/accuracy_rewards.py,sha256=S1NDqF4wZyksk0pVQiMSoJFOF9qOMjuHabZWmMfrwdo,3867
trl/rewards/format_rewards.py,sha256=fCQhtw6lazljB5Kv20ZAaD5XraoxKqVDBvqbscmldYE,2211
trl/rewards/other_rewards.py,sha256=bjJ-tMrLSX8qIHsDy344luP48MErEzBEJVvZ4vmf8Y0,2633
trl/scripts/__init__.py,sha256=tDv5yBlfQh0ovYdrTF-xW7dLwbARJPhHT8JkgKs4KO4,1077
trl/scripts/dpo.py,sha256=FFz9OQN-NQbHTbaHzc4amyRfZP6jdpNmddNwfhHvOYE,6297
trl/scripts/env.py,sha256=Vj06F7nzIrZZwKjNd0enBgv2EhBoaBLGOVtIiqMY3e4,3522
trl/scripts/grpo.py,sha256=rDxfxlx-1bsVUxWnJqTzlEw1PQ8a6XkKkPiwk0t6H4Q,6657
trl/scripts/kto.py,sha256=qNiN3eO33Vltk420e_jdd_cGOLhX9h2mdSk6SjZlLEY,5473
trl/scripts/reward.py,sha256=vDS0h5hv-vanyji8XQXeXt8H2sjRt6KEXEBjXNpRuMs,3772
trl/scripts/rloo.py,sha256=icaR1CxqMYGDJvORGnDEsrAd5kGT678TNzKZEs5jges,6657
trl/scripts/sft.py,sha256=uXfLxtR9aVnc0HITl7p7XhI1Do8hrEBzrbmfSWYk-M0,6062
trl/scripts/utils.py,sha256=M5_KHHK5VM5x_Fcc6JjDkymHXJUNyCwdqXQvxjHAMjk,18912
trl/scripts/vllm_serve.py,sha256=XKeRPt7hIrtnISwAR1gMGTTqHwM_gy9P2Yk9Lk7ragY,39352
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=HfwfZYf1ex1OMrW6aFVSqAXVbZl5pVtwDLHq3tej5W0,2891
trl/trainer/bco_config.py,sha256=5J_5oneAElCE0trzT54_qKgDWJL5DkepJJ37Uqa7gdg,1179
trl/trainer/bco_trainer.py,sha256=8yex9Tm1OJ3OE-yWs7EalqGrgU9iAsdNPqFRvG8Dk2Y,1207
trl/trainer/callbacks.py,sha256=abKfmgM3oQId8yqjnB05JpvydOxp_IeTAjY3fM9OCps,43858
trl/trainer/cpo_config.py,sha256=VIagEkPJEGOS74wuqxYXfAy3kN3Rd12cJ1oIHYhtKYM,10337
trl/trainer/cpo_trainer.py,sha256=OQ-dRkJz9Dm3ItDcFgBwjDIfHQz7zQhNrZ8OQPzi0Kk,51320
trl/trainer/dpo_config.py,sha256=8cDMtXXKGSrtmZdVYQl7QLR0UrCUgfxep3uqWREiSFw,26620
trl/trainer/dpo_trainer.py,sha256=svNGuwvRtXyCCkzjRRqET0q15KyP5ucIXblmTh6jfTI,102869
trl/trainer/gkd_config.py,sha256=uaDSMB-hWmGzIhtJNlq6Us2AOVfQz4K-DMjkzVdTc-s,4873
trl/trainer/gkd_trainer.py,sha256=fVJc36AJD0yqRt6UMCh8XCvuZ9IQdVu_HPYnSkxAvps,20474
trl/trainer/grpo_config.py,sha256=UWrw7TrINCq28m8huzc1FQNsf48PAl29AyMIaYtggNc,41202
trl/trainer/grpo_trainer.py,sha256=mXZrGxuqP10TwwS-bPOZHh4EVbzO9ESGJIYPxW074-c,107243
trl/trainer/judges.py,sha256=CYOs3bK4ZkbXinClgsM23IrIN9dEvF7BVbzktdCvgOM,19514
trl/trainer/kto_config.py,sha256=WqJbH4-raZTsyaqJjNyUIERSg3ErlEkSjqDjhWoujT4,11740
trl/trainer/kto_trainer.py,sha256=TzNTrx0GycheQbDyAApwM5ubrzOJoSH_8HjE5Jp63xA,81625
trl/trainer/model_config.py,sha256=PcBHMByo4igvmlWa05uoqzznFJvHaFfwYZUO1BoLQaM,9283
trl/trainer/nash_md_config.py,sha256=T3004FbQP7A9mir_I-XvW9GkzoykRL4U_bMg52NLVFE,1844
trl/trainer/nash_md_trainer.py,sha256=zEooCO5M06imEMiVf9_VfEiU4tlgEWRBXjUXSSnNhas,22217
trl/trainer/online_dpo_config.py,sha256=DcOq2Jsalz1cS10LtwW3O7dYB8GIV4M-wabCPNdrV7E,20145
trl/trainer/online_dpo_trainer.py,sha256=vtHXx2pYScWD7FnyeaiE5n2thsRpePOwpUE-kZ1bUIc,75033
trl/trainer/orpo_config.py,sha256=S_EB9gnS1SD4Jbs1H9R2Dy-lmpSOT8EchXag5XU11hU,7650
trl/trainer/orpo_trainer.py,sha256=azyjXUn5opferNvw432TniaNa9r49F7bB22hE-FbV2M,49777
trl/trainer/ppo_config.py,sha256=pAX7CQ-sXpwL842NSLa7PXqFMELOwLxCAQ9n6DwdV24,6005
trl/trainer/ppo_trainer.py,sha256=ryAhxxo0KjfH_h5vTByqe0g0HwBhAXZcv7-A-jv35b8,42359
trl/trainer/prm_config.py,sha256=jBCXWW8IvStw0Hb0rEzqB6oNUoCmSoIFJbZ5wD-LCTE,4646
trl/trainer/prm_trainer.py,sha256=DWyGfPup4y2u6QxXYexAPvzq4GmPhn06nWg9uyaS3KU,14210
trl/trainer/reward_config.py,sha256=f_DWO4ikWObpHm-r0lGrgdSOXrKYHisGACULtcsfAXs,7720
trl/trainer/reward_trainer.py,sha256=0zNWiQPioyGRqvuTnwtmQeCLuUcOVwcx6Mq3J7ev9Ws,29536
trl/trainer/rloo_config.py,sha256=bbZBiFVhna0xmyD-cGXQwEEJNo6lau_dMRdBNNeG-aU,30716
trl/trainer/rloo_trainer.py,sha256=LqaFBi53Fdny4bscN_LeXg_02eIL-Ehq_DuhQ2Ur0OY,86434
trl/trainer/sft_config.py,sha256=GFxWmp1kAAJ7q-CPpHH6VlMSh2ngMac5-g_RkQp5lpg,13482
trl/trainer/sft_trainer.py,sha256=TRki8DzSzFXRGjo74SjBrC368dfkV0FhMAoPEcxKfr0,66094
trl/trainer/utils.py,sha256=FRNwOYsrKrnf4i4_-s976PV9v0TH2H_XwW38EfiZuAw,80726
trl/trainer/xpo_config.py,sha256=nPzvCvvJpEWVBNnq-vv5CPpyTVZkQ47ZucVh_87fOPE,1667
trl/trainer/xpo_trainer.py,sha256=3be3evjTuLvwzwDXTtdNVka5lt0IXFO66bWOh-btoO4,24684
trl-0.25.0.dist-info/licenses/LICENSE,sha256=HZDsv3u4D_J-9nt3hfYhSAtlK4LkbHLYpXMLDbZb81U,11355
trl-0.25.0.dist-info/METADATA,sha256=9aIVPiceHL2eexxRIYqX_5n_or3c2W9dkInxkcGlQV4,11233
trl-0.25.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
trl-0.25.0.dist-info/entry_points.txt,sha256=EiubuQrZSGOohRB4xVoiVAyWsPsOHPSVpbzSk8YB0x0,37
trl-0.25.0.dist-info/top_level.txt,sha256=QU12VhjlpAtMnIJqiO2np3RkTB_Eozt1d-g8QDf5P4c,4
trl-0.25.0.dist-info/RECORD,,
