trl/__init__.py,sha256=gWTfyJr2d-K1-zS5kN0XDv4cbfsb2OvkWM_VhRkxIm4,6193
trl/cli.py,sha256=zcEVvmDdUJo4V3C_c91voSMY-jL8I6aUZ6QOOEf6oMQ,6830
trl/core.py,sha256=vHZbFc_VxuLicw8fYiLRrvJbKlqy60YuJ1_ffMeOf1I,5978
trl/data_utils.py,sha256=8PXZmtyRDEAjfstLdwEcNh3O1_OwTPnZD1MylObe2mI,26165
trl/import_utils.py,sha256=j4HAJbf3WKntxH2qbhBzz0stjEpGYQdcFzFjp4pimao,5405
trl/mergekit_utils.py,sha256=RkaYt1cZYEIu50Y13K9_N4ozKbJIH4JRYSOsdxEDEZY,11109
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/environment/__init__.py,sha256=JANVP5oKaZE9xPXVm-ikSEr4-11zIjiLY7M6K_VjjR4,989
trl/environment/base_environment.py,sha256=Ql91rP7QrqZc7oWB5m554qAJ1WNcGJupX6XGQUTaXlk,18121
trl/extras/__init__.py,sha256=5CIPkzvP9D6vpnWLNZz23RNU98MfjeBsxBFMHXKM09U,961
trl/extras/best_of_n_sampler.py,sha256=YFuEKXT1NuHardyjAXn1CHnqpazT-Y3d7hBMCM5tYk4,5770
trl/extras/dataset_formatting.py,sha256=J4FKqOCjEKjX5a4ExbzX9r3hLEUjdtXQv0PxgAcM15A,4468
trl/extras/profiling.py,sha256=IRohHs5ea-M2ijG3ihlANHcoI0QZUwlDoY2hX6LNzMI,3256
trl/extras/vllm_client.py,sha256=wD7i4annoM1y3krM60TNWru8EP7jmo1m8tMOSLuDbVQ,13565
trl/models/__init__.py,sha256=nVu98bMTfqZt9-ZXPOYJzXSsbQ917gLZdSUsbhLIR9k,2542
trl/models/activation_offloading.py,sha256=-gTJXcOY7eJPgwr2PiVcVJpNu5dOFuwvQKLswr1X50A,23550
trl/models/auxiliary_modules.py,sha256=akE5FsiGCR63aIYRTGRyjgocNnUPzYNfcSD3u3vktiE,3344
trl/models/modeling_base.py,sha256=ParLEmLYi4uVmR-n26XGD3bFqwlDWqgreTHI3UaSYA8,30835
trl/models/modeling_sd_base.py,sha256=aqKyfNGtr72kn5MU0_JIibAyzsL8kWtQvZu7gCYedQ0,42252
trl/models/modeling_value_head.py,sha256=wkrq82sK2pOayIef7EMYxD9xyQM3ZR5_q-qD3AZBsTU,18859
trl/models/sd_utils.py,sha256=scJfKtQWKSXCCuMBHMPe8XaRrGgJgVSTI-2zEB4Tq5k,5879
trl/models/utils.py,sha256=8nQd8m2iXaIgQE1oWP1DXSeo1z_s4f1NBeZFuZ1EpBM,14656
trl/rewards/__init__.py,sha256=9qZueWsDNBlJpanpOoKo-eIExJK2hKFHWiwXDyjogtQ,951
trl/rewards/format_rewards.py,sha256=6MzRQRcjX4emtx_3sgV566kMngqWhkCazOxgFY1f-B4,2210
trl/scripts/__init__.py,sha256=V7eYI1BLoXW4VVJP7Qe0avdLaRK-kVaiXEG4QVlP9xc,1003
trl/scripts/chat.py,sha256=Cc_YmIK4N3DIMRQgLQ9A4z77cpZUICvkxLy9Mi0hyuU,21002
trl/scripts/dpo.py,sha256=AA-TLLjwQFFtGXWe2M_U8paGhwkCvNq2x11w25g4rqo,5057
trl/scripts/env.py,sha256=raCuPxhyaNxPVbG2KH5fnPwwp-_hoA9Uw_r_C3WHZGA,3580
trl/scripts/grpo.py,sha256=swaBVDKo86iQq9EYI6mHB86WYOAuPh_pJKhpkc3wWtc,5166
trl/scripts/kto.py,sha256=rplxV9wf9iENgNbhaN6CchG7G1ff4XyKQ7EMED7fAVI,4121
trl/scripts/sft.py,sha256=3HG4BWGWo1xX70MBt26Ogt2xhM_srhy2yjlFxEJOW9Y,5245
trl/scripts/utils.py,sha256=b0bJ9gA56Mo_SfVeLG18w7CDRvKV0Oscjpsm64oo1B0,10580
trl/scripts/vllm_serve.py,sha256=TX1vKnjHkXBIvaeT7aG89eI9lV-Hi_QkkFkyjEZv2bw,24508
trl/templates/lm_model_card.md,sha256=zq0dXorqEOnjHJ8wxwhI3LS2R6qiHmlcgPcVzliwRmc,2158
trl/trainer/__init__.py,sha256=jo-_NgGunSfnwq9bYjlBwNDApClEfVD1Sx20NYXFJAw,5577
trl/trainer/alignprop_config.py,sha256=jLsZIkPRpyKZspVsk7gcn0JS7Mg2mCrccl-slpwOpIU,10196
trl/trainer/alignprop_trainer.py,sha256=VvPOjrGr78qALUN4TWhomZ6A5-8a-9UDfRe7diiPhAs,18317
trl/trainer/bco_config.py,sha256=hesvT6e5C7gFSYJ7mvDS7N8mWV3qM4V3iKV-CSeOSHM,8646
trl/trainer/bco_trainer.py,sha256=wRrmPmbU1y4iQ9UqV3zYmkuffdD8H-ruFE3m_zw5pY0,70896
trl/trainer/callbacks.py,sha256=_kClPv2ZAa8awie3kJANPwJGqVDahh4mGXU-66eHeyk,24564
trl/trainer/cpo_config.py,sha256=xYFxcg-Za6dpd6ezCV8Lp96GHQM8y7illZWxoKFW6GQ,8126
trl/trainer/cpo_trainer.py,sha256=bhexhJYmnR3lhy7ifgPsx_NGYU2CJVOXIGCb3e46D34,50973
trl/trainer/ddpo_config.py,sha256=1qL0nWhpEYFel7PUpaKXVWfc0PHvrYWiTcSiEc1rwdo,12241
trl/trainer/ddpo_trainer.py,sha256=Apl_M77TkPhrTIEeDL13W6Dn41CkzOcDmVjjpaGKK6U,28012
trl/trainer/dpo_config.py,sha256=5MXA48C2uv9HiP8ib5JsmRYOszXyd_FbFvZVw-yFNbQ,20992
trl/trainer/dpo_trainer.py,sha256=my5HlTHXut7QxWIj8Pl0mNX8TpqbTcYvryTzl16nI5I,80890
trl/trainer/gkd_config.py,sha256=eonWUOAR6bJOUvuN2UWKp2WozrcH0Dhq0bQXsAe3oZA,4598
trl/trainer/gkd_trainer.py,sha256=mIaPpDM3H9wRFLtaGkMp2lzYdWGWCiPfMNyJlx9Zjf4,15505
trl/trainer/grpo_config.py,sha256=s7q5QBa5CipOIEJEnuVw5SQBdPujudhHrfyz6ls1R1E,31059
trl/trainer/grpo_trainer.py,sha256=Vc91tgRaBaLfPPQqKExfK0xyJlHVnn7qMA3ztz5KMQ0,80236
trl/trainer/iterative_sft_config.py,sha256=HxSZjwPRGiVRJoJt8FhAgyy6cinWtAJKG4BYnjzpuzQ,3320
trl/trainer/iterative_sft_trainer.py,sha256=jxmEHZe5J-AMvXmlipZ6kakfJZeappbvBp9iHf6jAFI,21760
trl/trainer/judges.py,sha256=bllv6GS7JKAbwiVe9YEuyj5varEA2mF9w5EZ4Y0cddU,19556
trl/trainer/kto_config.py,sha256=XLvcGK4vuwJ5I5h7h5YEtSZM8RJRvZmtGrZ4OCQfrAk,10255
trl/trainer/kto_trainer.py,sha256=n32DD9Ul2NF4BrgLy1IWaWKNr-OclqxB4p_kcCjinpc,81588
trl/trainer/model_config.py,sha256=XMJkyXhifzXqd1k7-GXGorQqQPbRkrPTEAx2LAhnJBU,8660
trl/trainer/nash_md_config.py,sha256=T3004FbQP7A9mir_I-XvW9GkzoykRL4U_bMg52NLVFE,1844
trl/trainer/nash_md_trainer.py,sha256=Ehq7f56HvQeI2vRovHAb7KcTn29t58MsH2aC2xLsu6U,23905
trl/trainer/online_dpo_config.py,sha256=4-s_UsdvwKm0t1RdckZbqcsSDm16dtc5eofZsd_AV-M,8164
trl/trainer/online_dpo_trainer.py,sha256=m36YngdUi1VR4FOqPsLPxIzeSG8D22EgfT9ymuBXJLI,40128
trl/trainer/orpo_config.py,sha256=XuHY2EEeoqha2sddDgN_fpXLoRHQNBKi8uQLNguVGrE,6699
trl/trainer/orpo_trainer.py,sha256=BcK2HHLAbO1P-v_Z3m-fa6yId47MqgUTk3CKm6Cw_bg,50250
trl/trainer/ppo_config.py,sha256=5j6-qFy-TE4oZcLLeLioXv1tMtZIE18Tn6UqcKAiT_s,5759
trl/trainer/ppo_trainer.py,sha256=SU_-pNPqjGljPxKaRkNhMPDmkBUvJj-3ykg9f0t8tyw,39557
trl/trainer/prm_config.py,sha256=JNILLJpgaUi0SWWzOx4bjRBUgsY8BZpfvfg2Jp8zJRM,3693
trl/trainer/prm_trainer.py,sha256=QLAFS9kcjh8pN0XgrAhwGyyBSc5jOLFYfSIW8jH053c,16181
trl/trainer/reward_config.py,sha256=Y8lRaXGVoo6Nbz9-sXEgw2f-nQseA8iK4W4nnwlobFg,3295
trl/trainer/reward_trainer.py,sha256=oZU4f6HzrLLwFKZaT-Zk6B6BpNTQtb5IcwR98M-ojJM,18809
trl/trainer/rloo_config.py,sha256=JWu_ydCFIK9DWzWxXhCdEjLbkT3TIQcjBYHJl08WZ9I,4511
trl/trainer/rloo_trainer.py,sha256=9doAyOMWlRFCJxLrcuHhrOEmK68cRZ9euX7-YrwTbAk,34042
trl/trainer/sft_config.py,sha256=jmTizbY9Dig4sFHniB0Ejt7fljoY4Z1yDKWddMIIlDU,9420
trl/trainer/sft_trainer.py,sha256=oDwwJjD3BiSgoR3GJ0qVacIZCp9JZ9Q_I590eaRMigU,40048
trl/trainer/utils.py,sha256=h_8QstYUVVSkSQB_s8rfiZjUhthoK5K2kzKR3ItcKsw,77803
trl/trainer/xpo_config.py,sha256=nPzvCvvJpEWVBNnq-vv5CPpyTVZkQ47ZucVh_87fOPE,1667
trl/trainer/xpo_trainer.py,sha256=uqM2n4xp96Qxf0e3VxYmhFwn54nq0dS2MB3s_KxFpkw,26307
trl-0.18.0.dist-info/licenses/LICENSE,sha256=HZDsv3u4D_J-9nt3hfYhSAtlK4LkbHLYpXMLDbZb81U,11355
trl-0.18.0.dist-info/METADATA,sha256=HCnUDCHU5pIAT04_jD0dxBZIy9vG0cgZXRzA3BqoqRg,11372
trl-0.18.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
trl-0.18.0.dist-info/entry_points.txt,sha256=EiubuQrZSGOohRB4xVoiVAyWsPsOHPSVpbzSk8YB0x0,37
trl-0.18.0.dist-info/top_level.txt,sha256=QU12VhjlpAtMnIJqiO2np3RkTB_Eozt1d-g8QDf5P4c,4
trl-0.18.0.dist-info/RECORD,,
