trl/__init__.py,sha256=6bh1A8fZ4D3aUPWa_muNBc5kDZe8AQzbcg-pILzNSi4,3680
trl/_compat.py,sha256=iaDD6BjnJv5hdC0JLI8kMQ9yYnk_uGslxyNi0ynv0TM,6698
trl/_lazy_module.py,sha256=0KzILrqySOIHVJ2fRP0bVRaBEasS1YRqKOwkeEIg61Q,3264
trl/chat_template_utils.py,sha256=eNagGKJsHVjZu5tHrd1NbTAMcFR3WwvorPT1lHfXJ2Q,52492
trl/data_utils.py,sha256=67hGnB4mtibqMXXg-52HC5Two3DtRMrE-uKbpJF5oB4,43142
trl/distributed.py,sha256=taWLPat2ztmNxH02apimEls2Aj1TE-JJPa6xrGCTuPI,3157
trl/import_utils.py,sha256=pT3R4j3b8sd_8iOKjlRF-xqzCYsDEKqoyC2EkD7fBfo,5264
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/chat_templates/README.md,sha256=7yREJ2RrcbuL1q6AYNNHxkkm4SyGMMk2oeMvH8aNPd8,13484
trl/chat_templates/cohere.jinja,sha256=kMM67hSqKiJhJ1FtSO6RhMm5B0XUoExIRiHsLoL7cSw,1318
trl/chat_templates/cohere2.jinja,sha256=IUfEdPQbUitylvdGkrnzHkX0mjFGWWBXap0yEznFkVo,3239
trl/chat_templates/cohere2_training.jinja,sha256=flg2p0wB0iUEMGJz-Ke0n5RPa5YO_uZ2CcB-7wqbopU,3588
trl/chat_templates/cohere_training.jinja,sha256=X5cYv-OhlFNm6nkrlxTkKqWEnx1BoQk8LOTaSnc4OZY,1626
trl/chat_templates/deepseekv3.jinja,sha256=Vjsc59YdUKm0x0OakSoRFvCVtxLfW15NPhEWBJh062Q,2765
trl/chat_templates/deepseekv3_training.jinja,sha256=qttJQgBMGG-bqX0o9lPX8uDcIOQnU1KkhvfK--Tde1E,3379
trl/chat_templates/gemma.jinja,sha256=7NauUT_hA_DrYuirW_qND-RcEHT6OYsInJOn5wwVz9Y,591
trl/chat_templates/gemma3.jinja,sha256=feHFjiCO2kbpx_hjl9837EmIOu7OOfuWHgprJAiN08Q,1532
trl/chat_templates/gemma3_training.jinja,sha256=lZslfn_BYD-MrpyYkOYvQ9be1sD3K5tzxBBqTOqglvw,2722
trl/chat_templates/gemma_training.jinja,sha256=-CXemugOrIqJ-l-eboCt97eauGAlZJB-fEHcFTFdBKs,1363
trl/chat_templates/glm4moe.jinja,sha256=RPgVhovwL6RY3S90GjOARvS_RfOY620Gd2Zya52WzOM,3242
trl/chat_templates/glm4moe_training.jinja,sha256=ecI4b75EyYgb4Jst0IbgeZsVRH-NUwxFBBFSttqfNwQ,3697
trl/chat_templates/gptoss.jinja,sha256=pMmRnLvUrN1RzP_iLaBJJksbc-WQVfpYgRqZ7718gUY,16738
trl/chat_templates/gptoss_training.jinja,sha256=at2nzqD2PvFJGL5_JhALMkUlthhajwaTKRQ4j_qlLjI,17057
trl/chat_templates/idefics3.jinja,sha256=DX5WykFwW3mTLecHsivIVcPPzvrmLxrF5FhWBlSIPS4,408
trl/chat_templates/idefics3_training.jinja,sha256=s9IwIiquJC7to3PzbwjHFwVX3L1Kk9-y0tPHGO53dlQ,1193
trl/chat_templates/llama3.jinja,sha256=ugOhIdCXhZx7W5zQOvmar-lSdSENKHb2Qq2ZKaFQ8SI,389
trl/chat_templates/llama3_1.jinja,sha256=4QyjgbHMxc-dtS43HztmUVdsruCmMLRS4oFrLUBNS2U,4614
trl/chat_templates/llama3_2.jinja,sha256=WBb84QRE4DwunuHvikoephrn5p5DhhPzsXtp0EJiI6Q,3827
trl/chat_templates/llama3_training.jinja,sha256=nc6YHilUz3fU0K0tus-ABqX9o0oL30kjB1qTPQi2lHA,863
trl/chat_templates/llava_next.jinja,sha256=LBckOpd_0GQ_tUmlCajiaE9FUX3w-fYI1Yk7cZ8WVp8,663
trl/chat_templates/llava_next_training.jinja,sha256=rgunlIj3wiWuadwz19O6PCOxlzwE2CzdXz9M0WUQl0I,980
trl/chat_templates/nemotron_3_nano.jinja,sha256=q3gTw6vdnLZVkFpBByiybHiE7KRd36uNn5MVU0haeGI,10504
trl/chat_templates/nemotron_3_nano_training.jinja,sha256=9SpKcCkrmNtNG59ppZVGpD_F6GA6Z5R4GXOj5YIb1HU,11158
trl/chat_templates/nemotron_3_super.jinja,sha256=V1-3T1TtJk35BH0OzOPJiTiq6VP7T1A1ZnVwYmTLtoo,10771
trl/chat_templates/nemotron_3_super_training.jinja,sha256=04WVhURFdAkCWdQDymX3Gklrd7C1DzEQaqmaJfXKppI,11585
trl/chat_templates/nemotron_3_ultra.jinja,sha256=gnU771ztxJMsHtUJtcmhK-aA_YbRrbZbw_c5jRHI7rw,10152
trl/chat_templates/nemotron_3_ultra_training.jinja,sha256=1hzKIwrE-BN-dOiNc9imSeTDpxu3m4KSWhnPbcUqbH4,10969
trl/chat_templates/phi3.jinja,sha256=3K7mbfd7-7eJ7FQf5xMhjaMCJaUm8duXE4_DnubcVqo,407
trl/chat_templates/phi3_5.jinja,sha256=eNl2pEK83i8L4Vqvu44wUOEQT4ZzImb2hAMlG4mYKpA,430
trl/chat_templates/phi3_5_training.jinja,sha256=p2qWUal4Wv4mnGuRWY1V8Dq4rfPYSJpKnI70MhKLfAg,971
trl/chat_templates/phi3_training.jinja,sha256=8At3TFkzEp7gpyvtNV2ZR8sJ-AY9bPI7fbcbM7XqIWI,947
trl/chat_templates/qwen2_5.jinja,sha256=zY6UOfBXCFb9cEcL-IievYtdEQcgf2el77RuNCMwUn8,2507
trl/chat_templates/qwen2_5_training.jinja,sha256=DNhvuA9SCIXjUECo3zIVQOcp0zWNpB8nz3TTMQPZT2I,2965
trl/chat_templates/qwen2_5_vl.jinja,sha256=oLxvb8eimoABekM-jwOhzBI26DipRKLQNClaYMTy_ds,1017
trl/chat_templates/qwen2_5_vl_training.jinja,sha256=MchZMqbYgm8P6NUrgXZ-umuGkSiwp8dQPR57qq1OgEM,3239
trl/chat_templates/qwen3.jinja,sha256=pV7hsWYBKLcJhyPgq82SyqB4gGEFHGLVHL6H2c8ZdNg,4168
trl/chat_templates/qwen3_5_nothink.jinja,sha256=Jz2ODmg7iFBx-xfgjXHl8qXd-1MJdWGBaB3k9aGCLYA,7755
trl/chat_templates/qwen3_5_nothink_training.jinja,sha256=I5TcjFgzSZuareC1E9-NFkxp7G4YX6hNG1fUAFNCrYw,8388
trl/chat_templates/qwen3_5_think.jinja,sha256=pK7or88uBxGULPhIiZvmYBb40UqIn_nt4HvKCZwo9xU,7756
trl/chat_templates/qwen3_5_think_training.jinja,sha256=Ivr0Ia-gfatdQkd4ZKV0SffN-05GL_Just7AKRHrCaA,8385
trl/chat_templates/qwen3_6.jinja,sha256=6E8yoj_donaJ-GiqShpWIfQRM-UaSNfz78vqKDlXQlk,7764
trl/chat_templates/qwen3_6_training.jinja,sha256=DTUq7QnpspLvG0LrvTeyOAi4ZCSuNwrbgVNHgHl9b_k,8307
trl/chat_templates/qwen3_instruct_2507.jinja,sha256=ZPhbGYBl0PuiqB834Q7WgWHOLBmnVMcQDmfgyi7pwyY,2630
trl/chat_templates/qwen3_instruct_2507_training.jinja,sha256=SOF6o8r1vyAHW25zZoZO6UPgC28HUqrf6LZwwqsCkaU,3165
trl/chat_templates/qwen3_training.jinja,sha256=TG4c3MsZHOE6evZNrNv4bCLfnVRW9_FOrJy4My5BvjI,4577
trl/chat_templates/qwen3_vl.jinja,sha256=NjbQ8L1r7wJlTN_9xEe3nLLO-KsCzHUmc0WUYpGkieQ,5292
trl/chat_templates/qwen3_vl_training.jinja,sha256=Zr2BmGv3-Kvm1_tKUDQcjYrhSxZjfo-4dryn5-8LnG8,5741
trl/cli/__init__.py,sha256=B8PH6sNvyPB70xWMkMH8tFDDPN0gtvFf58IRpER_3mc,656
trl/cli/accelerate_config.py,sha256=UP1H5tldCUyK5gMmXg_hBhAF3XaWsyZqt8hVHmozneU,2008
trl/cli/accelerate_launcher.py,sha256=U0YogVSKf7zcYMQ_gEyA2DRkSbRxmPhx7G1CYsVXmLc,1897
trl/cli/main.py,sha256=AtvE_bH_ByC7lLZlzZu44-gCnF1bfIm8je7Ad3hiCrM,1660
trl/cli/commands/__init__.py,sha256=g01-bLAZyTna7_GM1qfhOSDKq58XJSlaaBnbiHEV76Q,1209
trl/cli/commands/base.py,sha256=DDKAl_-ezJRx9vwHr5WTDRNNQeDW8i23Suea8HDOTBo,1855
trl/cli/commands/env.py,sha256=LuM17gUHBFiSGzGzsx0pyCDFSszzhJFoDXeh3FJmaJc,1146
trl/cli/commands/skills.py,sha256=amCdxknbhyeYXKhBYahW0_ws_dkFq6gOQJr4-rciPjc,1621
trl/cli/commands/training.py,sha256=Q8QmzYvIvzwdN0NB5raUguJ-WZhUNw5z6CJyWrLHr9M,2753
trl/cli/commands/vllm_serve.py,sha256=ao6er6CntRdLd6m9bn9WByDz6Pq44xRi26Ndc4X-rhA,1429
trl/experimental/__init__.py,sha256=FMF_-llsmlfdSVPb8RfoW4z6zX0Co7J2jub6IW2bKyE,1310
trl/experimental/merge_model_callback.py,sha256=1wgwgatos-xUsMKe9VGAIfkABdpYzHSK850Lq2rdgiY,13866
trl/experimental/utils.py,sha256=h0NyvlBwxfyiEkXk4P_8zSGbnBCtlG_s7gT__PU5BDo,48714
trl/experimental/a2po/__init__.py,sha256=iRKDdeda5JbO2iUF0UHXaqXwujtrc9B54C3qh_tAI1Q,686
trl/experimental/a2po/a2po_config.py,sha256=h1n5SJCcFvUl654SjCd3A3SwxTp8GrWl4HZ1xHNdvgs,7018
trl/experimental/a2po/a2po_trainer.py,sha256=PVqqCusNmkKDkXqDApWluDGeH-OK8AzZ3j66yhDgZfY,18774
trl/experimental/async_grpo/__init__.py,sha256=djISk67rE2GC5S6-3Qm4NJ7f4JfGlmmvYwmcNYE_EFw,708
trl/experimental/async_grpo/async_grpo_config.py,sha256=pQJGLmgqSh64paV4B7wbzpYgW82bOTXUlc5Dhfuq2As,14596
trl/experimental/async_grpo/async_grpo_trainer.py,sha256=ohVpoAVb61q7iwLgF0en8Ex75FShfzCOzSZ3PSZDf98,51574
trl/experimental/async_grpo/async_rollout_worker.py,sha256=jEXBSJjQ5gpFqP2_jScsYzZ4jyqULWYeqRx70WGPHbA,45892
trl/experimental/async_grpo/weight_transfer.py,sha256=wr7GXXoR9Fe9TITEWJ6ms1AhYQ7y2BQ02pR0T7k3jXE,5970
trl/experimental/bco/__init__.py,sha256=X9vUxV2PcrTORo0CEALpq8EoHXtNTavAh0s-GVBDYio,682
trl/experimental/bco/bco_config.py,sha256=CL9qvwTLDiVm-7LNzFYZWXTE61Pu-e94XN9TGGG0l64,7846
trl/experimental/bco/bco_trainer.py,sha256=bFfbMCQQb6GxfjGkQ5HssjxCDIsHpPMGI7oc-8rtwQc,73992
trl/experimental/bema_for_ref_model/__init__.py,sha256=YSMOnS353SIRvV4_NS-Y-t0sbD6snBcbELbG3ku2Nfg,683
trl/experimental/bema_for_ref_model/callback.py,sha256=lhPPm5ADVgCSn7sqxPcZe_fq8tO7wriJqOhs3J_VDbM,9649
trl/experimental/bema_for_ref_model/dpo_trainer.py,sha256=4YrnaxULpR6TSpjWLvOGoLBziWQNGgWhNqOjuZT1mHg,1181
trl/experimental/cpo/__init__.py,sha256=rO0s9KRAaIsLOMJo2sweX51LkAK4QsLOeDDGIonMFLw,722
trl/experimental/cpo/cpo_config.py,sha256=2onTUbhmD3RuH3SPj0HPJ8qp7pXSFmCuSOSFcZrKIjw,8787
trl/experimental/cpo/cpo_trainer.py,sha256=xvWPiA0Y1eht_cD6WHSEkQCQM3SR13a6OV4fYw5XUzU,51372
trl/experimental/distillation/__init__.py,sha256=Grw7RW6Hnb-Fgk660HuK_69ED5HC6y4nlB2M_SU9dF4,776
trl/experimental/distillation/distillation_config.py,sha256=4qAy8vi7QbZEEWjsCVLxLhmuQs3faklDESPderFBrKs,22991
trl/experimental/distillation/distillation_trainer.py,sha256=56EaZ2GbfMz3_O2UykCvDVIi3ltuwRELMdF-KZ2HWFc,86738
trl/experimental/dppo/__init__.py,sha256=4vJFyjElYyJyxwOM8_ZWp_h43F5haFGUtAWQYNQhqww,687
trl/experimental/dppo/dppo_config.py,sha256=yujJCnXBk7r-qP4pKdg3uaFtA8hVOlZSgYyrL_tUDT4,5093
trl/experimental/dppo/dppo_trainer.py,sha256=yTLI455JKSC7WvPz6GEmdmmzFIGD1S1JaxKqvXJLhNY,79670
trl/experimental/gkd/__init__.py,sha256=QO5Yki2ia5hOep3fpQArdI3KMnpQkIV1FE0WiznkZrU,722
trl/experimental/gkd/gkd_config.py,sha256=gFiQXj4H7kAt89IoueUs9ZAOP9kXx3AX6aAJyyKeEtE,4853
trl/experimental/gkd/gkd_trainer.py,sha256=8tgrSA2m0OYZRf9P7-qbNZRa9-4iLPNs_-g2X89xOrQ,24237
trl/experimental/gmpo/__init__.py,sha256=yeoiMnVdDNki9-jJrUZ3dqE_1GRrMhV4Nbo9AbfPTkQ,686
trl/experimental/gmpo/gmpo_config.py,sha256=XeAWVD3iadI0Y9BWMQoY4eUU1_Sj5EaP2G1hR7PrQO4,2127
trl/experimental/gmpo/gmpo_trainer.py,sha256=T2wdU2zO54ba6C05AmJXxu_CPeUKfznKym6uBV19lW0,7897
trl/experimental/gold/__init__.py,sha256=FnYqi1_ahqtra-Zj2iECHAfr7AHBXQxYWrDNhK-a3Vc,728
trl/experimental/gold/gold_config.py,sha256=Fan0iWwyaVVa3R5fevvS6yzk-vxIv1TuXpnTKE50nVs,28061
trl/experimental/gold/gold_trainer.py,sha256=0TBphQkLR-h6UW3sGvVpLMrOSxOEx4SLy6WX6Lp-ok4,137140
trl/experimental/gold/gold_vlm.py,sha256=i0BU0RluKnolE-P_TcK-kCFlPp57mhtHXhfXBIPq6p8,7622
trl/experimental/grpo_with_replay_buffer/__init__.py,sha256=KPrhB5rG42642HmeBRcnefGPLBICYAdd613MaDGFTys,770
trl/experimental/grpo_with_replay_buffer/grpo_with_replay_buffer_config.py,sha256=p-uoMcOq1oXB-pdEG44ggKwKAL65Ho6NRk-iM3ZN1wQ,1373
trl/experimental/grpo_with_replay_buffer/grpo_with_replay_buffer_trainer.py,sha256=_h-Ap2QJbmqfEDeCjWTPYB9SvwGxS2TVA2-FIfYN3qs,42333
trl/experimental/gspo_token/__init__.py,sha256=ymJxlrn9cMOyLPGHBq_7VKfvGrhbXYl1ZPi8OyGjSbE,650
trl/experimental/gspo_token/grpo_trainer.py,sha256=D_QVhRYXhNskJDdvh67oJMIpuG2NBua7M0VVVkJYHoU,8515
trl/experimental/harbor/__init__.py,sha256=aprEKVC2b_9oHaC2jRdP15bfiM-7shFjLXkscc8c8wE,1254
trl/experimental/harbor/_env.py,sha256=s6Mxt5DRPPL9jZmtj31HYl_vlZw0bTUWRjNPlg1fp_w,11514
trl/experimental/harbor/_spec.py,sha256=CspOuzacW3QGLZarkd03Ji1AbGA1FDNI-cc5p7UYN3w,9981
trl/experimental/kto/__init__.py,sha256=lz4FRMath817hK6XXVwKDbfpK-thshvoPv00AGThVyY,1627
trl/experimental/minillm/__init__.py,sha256=xJRoMqech-1OcFwcP3Ut-wV7DlYm6z6SXb455kHOlpA,746
trl/experimental/minillm/minillm_config.py,sha256=c6JAoVSBZaIV3zsRz5nqInyIs_ZIC8MP4v_KIzEW0xU,6619
trl/experimental/minillm/minillm_trainer.py,sha256=TbZ7dcZoIkBZ0bm1MCl-hlZzvvUUlYNdK3UdEv-WBk4,20329
trl/experimental/nash_md/__init__.py,sha256=0-fTu0AiobRY3KTKO6l-HMW_Me66vuaF-l7ym62oRXA,742
trl/experimental/nash_md/nash_md_config.py,sha256=6GlI-rW4umHCMU2ykEwLztRGvd8hpHJlznEu7KzAsH4,1872
trl/experimental/nash_md/nash_md_trainer.py,sha256=BBOsZ8wnzD7Qzx36-S7VX3X9Fzr0kavIzfXys-mJR9E,22350
trl/experimental/online_dpo/__init__.py,sha256=d0PLdODeA1bPSoXLlGWEAeA6XwGiHCd1isltzRGAVOQ,760
trl/experimental/online_dpo/online_dpo_config.py,sha256=0p2Kdo1UYaUIY6IfKC_wbfgYaIWtWqBSTlQCDJejK6g,20609
trl/experimental/online_dpo/online_dpo_trainer.py,sha256=A2D5oPXse-2-3JvbPkmCeFDRqlPFe9mvz-rqCX5L5ww,69467
trl/experimental/openenv/__init__.py,sha256=LlzcnV_wiUFOTBh64phVNDb6dpKr8A93i_K-ZntlysE,705
trl/experimental/openenv/utils.py,sha256=vF39Bk0y6ArPZioTDgtgGGrHqx4nypcl3Ti1KWQaWfs,8056
trl/experimental/openreward/__init__.py,sha256=Cn8PmmYmWF6RqhXioKxH9mG_PszFdvYD7AdGmyMDnSg,677
trl/experimental/openreward/_spec.py,sha256=x3JezMGCjM5qo_kPOStAlOQ2PQ8Q4H1_I4gsOs1iCCw,15588
trl/experimental/openreward/environment.py,sha256=AW25hEl1qvRGQUgipBXHHIiFPv1DyRADadB733WOtLM,16330
trl/experimental/orpo/__init__.py,sha256=raFCz1dhCGKRjdQREuxEWY_MwXpIA1GvpZXxsqzv1EU,728
trl/experimental/orpo/orpo_config.py,sha256=-_ET5QimWfd6iZlRVrqayYiIIt9JIvus-ZiD_PnQa08,6251
trl/experimental/orpo/orpo_trainer.py,sha256=xFVNQAcrlWKhQVhIQnnNwu1xi4rpsHGGhgjanYM_N3Y,50316
trl/experimental/ppo/__init__.py,sha256=7jMTBOcEiFGAs6rYdH61xzg1RWTGfBC_r2YFd3DBtR4,990
trl/experimental/ppo/modeling_value_head.py,sha256=k0r4CXCzUec2hzxv0Eljcor_ePk_73A8hFXl9NsPpOg,45071
trl/experimental/ppo/ppo_config.py,sha256=Bp0aD4DnnP5igczFuUuSs4YPo5ZQ4vATEG_oD0dB32s,12577
trl/experimental/ppo/ppo_trainer.py,sha256=GV_Ls2juVrEc52LXDWNI-XsEA6r37dYrE4kMDMlaPJk,49903
trl/experimental/prm/__init__.py,sha256=D5e_7PoXs3nTMVQaN1rAGvIUra6cQDfOyFViUbZrNR4,722
trl/experimental/prm/prm_config.py,sha256=HrNL3emLcboZjEgcHhQX9pvQV3_o4P-QTopTeNG9r0c,3802
trl/experimental/prm/prm_trainer.py,sha256=OrDd1HWbMzCWR7tdyzw3G847Qi1VsORN6z6D9Ne4R8I,16948
trl/experimental/sdft/__init__.py,sha256=pI92-nBzVF4g_g_CWNPrUmNPLwhscz-zw8CIji54YI0,728
trl/experimental/sdft/loss_utils.py,sha256=UwtXHAABu_hbsMeHJdMmRaTXFVZg4i5BWA-rXJ9wQeQ,6049
trl/experimental/sdft/sdft_config.py,sha256=-P68TYRtVPrMNNaUbxT1AO6cWtqHHIiU9MUWm0CNSkw,26836
trl/experimental/sdft/sdft_trainer.py,sha256=O_0BQ_NcmroxoGcJoyyEtpzzcw0RUCYG4bKGvX1tA18,64128
trl/experimental/sdft/teacher_sync.py,sha256=8WAQB67K3UK2d-KvwZFsA2UoHOZoc_A6eU4CiH4Z0s0,6675
trl/experimental/sdpo/__init__.py,sha256=66WDtge8cD3Jpp-yTaPgzvDZfF8h-Svju4cc9FSbb_Q,728
trl/experimental/sdpo/loss_utils.py,sha256=UwtXHAABu_hbsMeHJdMmRaTXFVZg4i5BWA-rXJ9wQeQ,6049
trl/experimental/sdpo/sdpo_config.py,sha256=1QHKs1Kl00OYeYT9MUSEW13J6cB0Tmb4I1iDB9T3ijQ,39291
trl/experimental/sdpo/sdpo_trainer.py,sha256=7GNNOSmfiHw9d7XfMyeQMr1d6DA2x6YQjivuL2GzQLs,89381
trl/experimental/sdpo/teacher_sync.py,sha256=8WAQB67K3UK2d-KvwZFsA2UoHOZoc_A6eU4CiH4Z0s0,6675
trl/experimental/ssd/__init__.py,sha256=kZ8pR1q1JG6pwbQmHMbsthOm5bD6Tqtvh4AOWaviS24,722
trl/experimental/ssd/ssd_config.py,sha256=J1UTM4ANutzEzH57pcp6Yfx-CLg87_kPTdZqUPAj4-c,12317
trl/experimental/ssd/ssd_trainer.py,sha256=ROAyZmbUGx0-BFMZXbI9D2mN2vJ1g7EWSRr1BBcixtE,24129
trl/experimental/tpo/__init__.py,sha256=fDIWPC3c1BL3VngtbKbnaB-UNRNY4tewOYrr_7yXWG4,722
trl/experimental/tpo/tpo_config.py,sha256=qNB98rYvEK4RpA-kvdOMcNsEuHu6gKzw2sV19SaJuAI,8023
trl/experimental/tpo/tpo_trainer.py,sha256=jmAfqY3msThvmTMmdin9YblStlsgbZLqugRatZ51RaQ,44795
trl/experimental/xpo/__init__.py,sha256=QcEIbvNKqd-1mR_mHH8gmtE5UGhZGBFG_9bMYLBhuvI,722
trl/experimental/xpo/xpo_config.py,sha256=hWuv1yNMEM-KBFJFv9x_8xu-NhsU8oblvqQLLLF68-Q,1691
trl/experimental/xpo/xpo_trainer.py,sha256=cJTYpYZDgfNC2x1-QGyZCLfki-aRPs9glV221-sWkOw,23355
trl/extras/__init__.py,sha256=V1wvJ_Ee6Ro58SbMXQqO7FG-_jvCpy6kB31_7Wtl68A,611
trl/extras/dataset_formatting.py,sha256=D_8NqUiZ3aSF6bl3qnopEOY8suwH3YEhJ_W4gljSXA0,1285
trl/extras/profiling.py,sha256=xxOQQukiVYUhcjAmkkLCsp1kc10RgSCsNiijECKBtQI,7687
trl/generation/__init__.py,sha256=aAYDsVEN0dDYZMZaeZvBhAohos1fQX_asTGHJrjmFUE,828
trl/generation/vllm_client.py,sha256=MJWFgSocRAeXpeelWV_9JArRG6MPS5REa7yZFfqfgBE,35315
trl/generation/vllm_generation.py,sha256=r82hjBEXbw4cteI0Ucqa1fQzChMAe6zhshCJYmLo6Cs,36237
trl/models/__init__.py,sha256=AdtqJlv3mNNGldTZRmm1-0Ymm0yMrpwnXN0ilv0gdY0,1219
trl/models/activation_offloading.py,sha256=65VpW8F0H0uhWnT7qqrkG3DwEOAkwr3eoAPsIvhn4Oc,38645
trl/models/utils.py,sha256=3jIkDTbVDlv3HnNryuEvDzx6ANAhbAVw-UlAI6vG1uc,17947
trl/rewards/__init__.py,sha256=wjFas8-C-8fEu0XOXEzogh2szxZuuuaikyUBcwQX8lI,1334
trl/rewards/accuracy_rewards.py,sha256=JC5zxTIWDwMlZD5KUCdFNtauy4y70bqN1vBp438AQWA,15892
trl/rewards/format_rewards.py,sha256=XKId9E_3opkCtiELkYSWKxb8QnYJv2EGLuT9QOcmbS0,2211
trl/rewards/other_rewards.py,sha256=WUSxaGtAPi3LXq-1IC7KocbUUl59FY8C3yT_tPFm9C8,6126
trl/scripts/__init__.py,sha256=uBELpz2YbIG2YxXa5ioNhrWE0nqoior8hkFGP3ZzYe0,1077
trl/scripts/_hf_argparser.py,sha256=V6WfV7O-mVgmxPGxRiH84JMJdYjmPVmdQDj0ObENLZ8,21129
trl/scripts/dpo.py,sha256=YHPPOJneTTh6NGs2Xtl9opdCc7F9w1nboxM8aZCsVOU,4864
trl/scripts/env.py,sha256=NwKqs_IQK3tpW0xbBZU6qEx_68-T_SqAv_-BElbkroY,3285
trl/scripts/grpo.py,sha256=xhRI42Yc0KcKGjXNMH7oOjWCMxn0hZ41M1wLaIrGY-0,6866
trl/scripts/kto.py,sha256=dYbYKOd8CEgz-Qc1TBhGvs2lmcnhjygpVLhqW9qLIUY,4792
trl/scripts/reward.py,sha256=DZ7f4C07QvjjovUx_jFruyj1g7e9DdqJYABs-E4HBBQ,3723
trl/scripts/rloo.py,sha256=i--trfxgG-qNBAMKSxwwW48aRC-axemGnDOnrEokNg0,6866
trl/scripts/sft.py,sha256=p8I2WgR-27fUml88XQuwXXLUDFx194NuYuU_KNRm9bc,4568
trl/scripts/utils.py,sha256=C-ysCp-_X8d7H1rZJHWNcDg2pC1qKFkfQ2Ld4rbCAvA,20051
trl/scripts/vllm_serve.py,sha256=ETZvxqUTWEvVkFN_Is4BPZ_0t4yyYSr6ta1qlP-CMRg,59647
trl/skills/__init__.py,sha256=ztKZxcsQqk9gvPe4pV87ZUIPgPW3LwBNXW2-Z9vGwNQ,740
trl/skills/cli.py,sha256=qVMHN-wOJEfumxEUMH7aBhTR1ejOV3E3XW4r-7Bqg9U,6875
trl/skills/skills.py,sha256=xiaSk1HDDsUXjtMzFNXWGAnesJ-apn0bXZ47KFRq3a8,11676
trl/skills/trl-training/SKILL.md,sha256=z97EE_zwMPKSBQQsuMVqDFQE9jeRmDlwTX2l0EyxlY8,8871
trl/templates/completions_dataset_card.md,sha256=48c5hNBP1BtG01GYcHWHtyFsMxL9O63OXKHpTyk2xOw,1233
trl/templates/lm_model_card.md,sha256=GUAzW9rFpN6Fn47_8wrFHtEarz3ZZTlQtT1gvkIJg74,2351
trl/templates/rm_model_card.md,sha256=pevYy0_B9OThscj5WcDXk_0Fopulfa3IGeHSAr8NwLM,2143
trl/trainer/__init__.py,sha256=_aKASgHY62GZ2E6axZyJf9QRmDEIF4SBnJCqHU4Sjq8,2581
trl/trainer/base_config.py,sha256=wD4Fur8JA0h6OwmstTTVDJKdAbI6gCekZOoU9KVznS4,5759
trl/trainer/base_trainer.py,sha256=-qvHvJfq4JYFdnHG64wP8Xp8ywkO1ZT8d0n12M_IxKo,6719
trl/trainer/callbacks.py,sha256=meKSaP4OBA1ZU5gPMNoyqy7auEyTgn3f3Sdmlv327cE,31361
trl/trainer/dpo_config.py,sha256=x4w86FvZ-Dm8CKYpAxpOQX249Ms3WVbw8-ogeZVUidI,19573
trl/trainer/dpo_trainer.py,sha256=2CsfoSFWDenuRDYdi7IC64kcSCDLPZI3AmtaB8ngZbE,96858
trl/trainer/grpo_config.py,sha256=WIbwXYwt-NnDmop-Pn8sEMFUhzPSJABUMJVzVLlU-KE,67737
trl/trainer/grpo_trainer.py,sha256=UtmmweKY3zXQ2kpvoXh011DuYn9qwVOTyIYNdNG6SRc,186252
trl/trainer/kto_config.py,sha256=NAgEPYshxvGhL82eIn-BwK9JGSLoqh1snio4BEs9fe0,12592
trl/trainer/kto_trainer.py,sha256=wuNqJ7zVtajSJTUl6Es_thtl1HLjlkZHc_0xzKdIgkc,93849
trl/trainer/model_config.py,sha256=Y44rXzYJ4wa6n0teZS1KtFWDv-sZnh5HR4XJXdoe3KA,8144
trl/trainer/reward_config.py,sha256=iNItKpCoF8D8GN_9lQ-0DDLSk2XOmHytLWoH-WNtESU,8055
trl/trainer/reward_trainer.py,sha256=WJOZsvZCbRqW93mjwu5U1EEU6VONYFxLt3PZN5aQcs4,40806
trl/trainer/rloo_config.py,sha256=CqwDFQduNmiwZucR7bevfkViDZhVV3x6CFbh2UpP0i4,35349
trl/trainer/rloo_trainer.py,sha256=kt6JM2cKVUnZ3e8vzM4Or0-frO3y0QmJDIOS4bLAo0o,96106
trl/trainer/sft_config.py,sha256=hD9TG8cHNddcOJkL1akOiUYFZGnGDPNQfsTTyMmKyW8,17714
trl/trainer/sft_trainer.py,sha256=G7PdxmApdz8YbTFLjzlVjX1DlhUKZZqL0Q7uL9BzXsI,105016
trl/trainer/utils.py,sha256=9ZaM4iOaix03KU1tb_uiUTEHXwfPzO8oZJ3vUcAfGm0,60364
trl-1.8.0.dist-info/licenses/LICENSE,sha256=G_YUsf3ED700SqWNANF9X9DSUuozOgW-AYo4lZyLKZg,11355
trl-1.8.0.dist-info/METADATA,sha256=Qnf8J-qzV4mvK-BVz0GCRKqOPnwQRAg879p9m9MxTUI,12743
trl-1.8.0.dist-info/WHEEL,sha256=K260EYznzXsJYBQGqmI8VTxEdiZYNvDZwW9cBh9-_MA,91
trl-1.8.0.dist-info/entry_points.txt,sha256=EiubuQrZSGOohRB4xVoiVAyWsPsOHPSVpbzSk8YB0x0,37
trl-1.8.0.dist-info/top_level.txt,sha256=QU12VhjlpAtMnIJqiO2np3RkTB_Eozt1d-g8QDf5P4c,4
trl-1.8.0.dist-info/RECORD,,
