trl/__init__.py,sha256=IxOUfQnfHEVa0aN_c6X63uoeGZ9op4evfwZbu748fRc,3740
trl/_compat.py,sha256=iaDD6BjnJv5hdC0JLI8kMQ9yYnk_uGslxyNi0ynv0TM,6698
trl/_lazy_module.py,sha256=0KzILrqySOIHVJ2fRP0bVRaBEasS1YRqKOwkeEIg61Q,3264
trl/chat_template_utils.py,sha256=GNeoi9qTr6pcdKfd760HRsIwL_j1vmAPPWphVxJ_4oA,34375
trl/data_utils.py,sha256=zp6_JqPqRpEQFgn0WgUAm7o49Sa8o4xj0vOqw1a9viw,40789
trl/import_utils.py,sha256=x8cX-ezH_XobCH5PGDVgVofU6AH1XY8dqNE9LxjWsvs,5096
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=6P_k4TzW_LDeEhnQ23VzQ0yALa66xPhd6gXjWW5t3PQ,6905
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/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=OhdraYvnBvProWiHcT5hzSx5FCKu3cnCKO7SYHy2AqE,3884
trl/chat_templates/gptoss.jinja,sha256=pMmRnLvUrN1RzP_iLaBJJksbc-WQVfpYgRqZ7718gUY,16738
trl/chat_templates/gptoss_training.jinja,sha256=at2nzqD2PvFJGL5_JhALMkUlthhajwaTKRQ4j_qlLjI,17057
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/phi3.jinja,sha256=3K7mbfd7-7eJ7FQf5xMhjaMCJaUm8duXE4_DnubcVqo,407
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/qwen3.jinja,sha256=pV7hsWYBKLcJhyPgq82SyqB4gGEFHGLVHL6H2c8ZdNg,4168
trl/chat_templates/qwen3_5_2b_and_below.jinja,sha256=Jz2ODmg7iFBx-xfgjXHl8qXd-1MJdWGBaB3k9aGCLYA,7755
trl/chat_templates/qwen3_5_4b_and_above.jinja,sha256=pK7or88uBxGULPhIiZvmYBb40UqIn_nt4HvKCZwo9xU,7756
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_training.jinja,sha256=TG4c3MsZHOE6evZNrNv4bCLfnVRW9_FOrJy4My5BvjI,4577
trl/chat_templates/qwen3_vl.jinja,sha256=NjbQ8L1r7wJlTN_9xEe3nLLO-KsCzHUmc0WUYpGkieQ,5292
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=UG2Yr0VJsYCkrDGmWjwssAvTNwMgJTadpeExsIpdQmg,13850
trl/experimental/utils.py,sha256=RTBQx4byqm3JsSefGujqd4es6QLVRLGGdTimSCKRqdQ,29001
trl/experimental/async_grpo/__init__.py,sha256=djISk67rE2GC5S6-3Qm4NJ7f4JfGlmmvYwmcNYE_EFw,708
trl/experimental/async_grpo/async_grpo_config.py,sha256=tAZmqpOcOkPIQiqsagv8RapqxsXijypqeSrd7Dfm9O0,9929
trl/experimental/async_grpo/async_grpo_trainer.py,sha256=NnU59-54e4ytoa56J09_cMUe_LPhCPgktfSisgtspZ0,31872
trl/experimental/async_grpo/async_rollout_worker.py,sha256=934zvnlQFGEPvysQAwBuvLsO5ljWAcEQwZAJXQ4a6GA,33081
trl/experimental/bco/__init__.py,sha256=X9vUxV2PcrTORo0CEALpq8EoHXtNTavAh0s-GVBDYio,682
trl/experimental/bco/bco_config.py,sha256=vEdarjRViRa_v4z2IQoms8NSwZLoIOEoyICGUqXvr_U,7270
trl/experimental/bco/bco_trainer.py,sha256=f78ouwcNIdtodRa0VDNXEtUuBazVS4W76qZcHZuiZUg,71567
trl/experimental/bema_for_ref_model/__init__.py,sha256=YSMOnS353SIRvV4_NS-Y-t0sbD6snBcbELbG3ku2Nfg,683
trl/experimental/bema_for_ref_model/callback.py,sha256=RYC7doi9utJa98wKMT0NP8pmY0rITQGISfwZjlQm_Vw,9641
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=xcd4qAYEviqx_kQE99b_pXR3icNz1RfsWiNNAYsZCxo,8289
trl/experimental/cpo/cpo_trainer.py,sha256=vOTDRqfjfEhWjbCqwvTn1fcPjFnTuLjXmyh_XIpxe9Q,49233
trl/experimental/distillation/__init__.py,sha256=Grw7RW6Hnb-Fgk660HuK_69ED5HC6y4nlB2M_SU9dF4,776
trl/experimental/distillation/distillation.py,sha256=tBUsmPzYkVvC0lkKDr6V73VPb1TCHWBAwErp5holm1I,6078
trl/experimental/distillation/distillation_config.py,sha256=VGwx4F1pfPJOp6gB-0J4NOTu1OpCMffHh-5F1BC6yp0,22414
trl/experimental/distillation/distillation_trainer.py,sha256=gR8qR_o3_btstInaPCBzY-9mLGyFSj-GT5ExotcfVxU,80876
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=pv2lwmUU_P77K7Scr-Qz4_Xdw9EUyWTgHCLN6EpjjMo,74778
trl/experimental/gfpo/__init__.py,sha256=uP2ol8mB0vbkaDcIXCAAwN_HzW7ulo0c4HGqqlevafY,686
trl/experimental/gfpo/gfpo_config.py,sha256=Zz4vFZ9vAy9kD47EN3RgoSJZtW7_8JnGn35sgHmZzNw,1325
trl/experimental/gfpo/gfpo_trainer.py,sha256=BOzUJH-Ypf-4We0TU3lyxIsRHjV3jX-SA3rNJjKUDjo,24419
trl/experimental/gkd/__init__.py,sha256=QO5Yki2ia5hOep3fpQArdI3KMnpQkIV1FE0WiznkZrU,722
trl/experimental/gkd/gkd_config.py,sha256=gFiQXj4H7kAt89IoueUs9ZAOP9kXx3AX6aAJyyKeEtE,4853
trl/experimental/gkd/gkd_trainer.py,sha256=iIQ3pMHxZvrvbCcZVC666kglG92s2JE5OTbL0q83lvk,20752
trl/experimental/gold/__init__.py,sha256=FnYqi1_ahqtra-Zj2iECHAfr7AHBXQxYWrDNhK-a3Vc,728
trl/experimental/gold/gold.py,sha256=nia4-M7EqsoRRAv7wZ57se3mpV7KukYHUEwExzgCNx8,5420
trl/experimental/gold/gold_config.py,sha256=IaFpED_2j0ZQymLKf_sqJMn_rHPgY3qBqjai4OdO6vY,23199
trl/experimental/gold/gold_trainer.py,sha256=xU3rx7ZiI_UO3EX4jLSXkVSfXz5FIVimJNRNqlhD9ic,97398
trl/experimental/grpo_with_replay_buffer/__init__.py,sha256=KPrhB5rG42642HmeBRcnefGPLBICYAdd613MaDGFTys,770
trl/experimental/grpo_with_replay_buffer/grpo_with_replay_buffer_config.py,sha256=UW6s4umTNDvsDQ-2lHMOAovD5Ro1gGlBohJNnuEan0U,1372
trl/experimental/grpo_with_replay_buffer/grpo_with_replay_buffer_trainer.py,sha256=fpc9khDmb4rlmNjrWStKCoDd2yXYsQ3W07vUBsgdkLY,39548
trl/experimental/gspo_token/__init__.py,sha256=ymJxlrn9cMOyLPGHBq_7VKfvGrhbXYl1ZPi8OyGjSbE,650
trl/experimental/gspo_token/grpo_trainer.py,sha256=kOIfJq-9gj9wp7FQuhJGAqK_ctEU7rbfed0PO9D4c6E,8262
trl/experimental/kto/__init__.py,sha256=K-M_Blc_9na1bQDKla6jKJKb7fPKxSUmiJyRHNFuSu8,722
trl/experimental/kto/kto_config.py,sha256=XdW8e3iFoYCVpy9a3sRak2M-YVkebGfdySuaTqs4QPM,7277
trl/experimental/kto/kto_trainer.py,sha256=PNXuWG6v_SKhrrDYyWU9UlG62_b9WT48fcuMmHAwlCQ,62353
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=RWREg5ev_vrEJ6jkbdtHeNR0oEbVRIEIFtVeWOoW5-U,20117
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=QQg1sTwuum4CbZkBRNSiYc-gdaDvkQD6Qr8qweACbxM,22304
trl/experimental/online_dpo/__init__.py,sha256=d0PLdODeA1bPSoXLlGWEAeA6XwGiHCd1isltzRGAVOQ,760
trl/experimental/online_dpo/online_dpo_config.py,sha256=D47lXBouVr6x2Q25LJlzo8nEKuCOXERBE0GzudkASzg,19763
trl/experimental/online_dpo/online_dpo_trainer.py,sha256=gBBQO1xwvHoUhNxid0xflvadVPmEt46GF3TB74basEY,69012
trl/experimental/openenv/__init__.py,sha256=LlzcnV_wiUFOTBh64phVNDb6dpKr8A93i_K-ZntlysE,705
trl/experimental/openenv/utils.py,sha256=vF39Bk0y6ArPZioTDgtgGGrHqx4nypcl3Ti1KWQaWfs,8056
trl/experimental/orpo/__init__.py,sha256=raFCz1dhCGKRjdQREuxEWY_MwXpIA1GvpZXxsqzv1EU,728
trl/experimental/orpo/orpo_config.py,sha256=JZ2emthcMah8pisNENCWvqpztF95ltEh3SQUN5iGsoE,5753
trl/experimental/orpo/orpo_trainer.py,sha256=pVLxlrFOseL2ZwUEkJjgDAqo8OdJ_BiqmP803qnPFxE,48177
trl/experimental/papo/__init__.py,sha256=qP04taTkxweuEvOll1BfSFU5BlaZyv7OIT-i95PE8CU,687
trl/experimental/papo/papo_config.py,sha256=YN5qFmankCNVYDgEEQ0TRQDo29FqumZGRxfjtIkZb1g,3141
trl/experimental/papo/papo_trainer.py,sha256=mDb0UF9wJskM1cpblxUd0UwbwnvNK8Wo_KZibGgnkXU,15685
trl/experimental/ppo/__init__.py,sha256=7jMTBOcEiFGAs6rYdH61xzg1RWTGfBC_r2YFd3DBtR4,990
trl/experimental/ppo/modeling_value_head.py,sha256=TEUbETl0Pjeg0y2jBG1kl4YnurlHVn4Un1dPGTTk6O8,44279
trl/experimental/ppo/ppo_config.py,sha256=Bp0aD4DnnP5igczFuUuSs4YPo5ZQ4vATEG_oD0dB32s,12577
trl/experimental/ppo/ppo_trainer.py,sha256=Y58OEG9m2ptPY4r3FK9JCglOPzyckOfoJSlk1ILCU_8,49584
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=1P066g7_k9QY8p9mgny4eiJuANKpCnIFd9fTYMo36kM,16337
trl/experimental/sdft/__init__.py,sha256=pI92-nBzVF4g_g_CWNPrUmNPLwhscz-zw8CIji54YI0,728
trl/experimental/sdft/sdft.py,sha256=8imgNedRUZHCJqxAJjz4REE3L9A7w9c2bUoC9TsCTHQ,16621
trl/experimental/sdft/sdft_config.py,sha256=PMvAYg5oVQBm1Wiv0iIsLN3AxqJe-48CRzqelPBqxTI,2951
trl/experimental/sdft/sdft_trainer.py,sha256=opLOBJyMFS2e8hvIPtQfhXNFC5hUyefRaMf0905khrI,22664
trl/experimental/sdpo/__init__.py,sha256=66WDtge8cD3Jpp-yTaPgzvDZfF8h-Svju4cc9FSbb_Q,728
trl/experimental/sdpo/sdpo.py,sha256=tKpp10Sf2dN8SD3RAbIuI0rnBumtme79h2rLY9QeKqw,14942
trl/experimental/sdpo/sdpo_config.py,sha256=WGVVEW2GcBSA7Rf-zfpmXrqnH612NHNVq_NoxkYZFEQ,6954
trl/experimental/sdpo/sdpo_trainer.py,sha256=RHsplkbLmis6CGXKobUPaG9vcgpCBlRBzpNpJF1_DE4,18464
trl/experimental/self_distillation/__init__.py,sha256=qs-kE8gnjSw5nTTNh-q53yOlUquM9q3ZT39Z7N5TAnk,796
trl/experimental/self_distillation/base_self_distillation_trainer.py,sha256=lo9AjPWNHEMKV_8rSzmSDYwa_FacSHqgmKB5aMApMIo,16161
trl/experimental/self_distillation/online_rollout_mixin.py,sha256=CfzT1EBrUJeKd74D9w6u8kmL9PZZIkUWn9e_bVx-dPY,19841
trl/experimental/self_distillation/peft_adapter_ema_callback.py,sha256=mPYRoa_pUZfnmj4nzQoaEERsiCYKbLRFYN6d-z8M12s,5160
trl/experimental/self_distillation/self_distillation_config.py,sha256=F4WtEzDVe4A6yb0ntqj75bEfOxReXSD4pWM9Nk0jo_g,15636
trl/experimental/self_distillation/self_distillation_mixin.py,sha256=Y5u8lUbQ58x07QK0m2h-QigrcwFjV76S2GBqRDVVOCo,13939
trl/experimental/self_distillation/teacher_context.py,sha256=xG0f_BYjGMtbQ2vDBL3mCmVdLgNIECEJlu0hv5kEZ2E,3351
trl/experimental/ssd/__init__.py,sha256=kZ8pR1q1JG6pwbQmHMbsthOm5bD6Tqtvh4AOWaviS24,722
trl/experimental/ssd/ssd.py,sha256=jHO2m6PWVti5UIybf3tw6751EONXMAZZlxRuwfK2lLE,5658
trl/experimental/ssd/ssd_config.py,sha256=1ymLXjVdBtLg30rOA9NCNAa-f0g6Y2feef6rvVEsM38,11701
trl/experimental/ssd/ssd_eval.py,sha256=uZoN-Pwad17SukjnEDipUOiY78-9MH2rPlk5E49US00,10299
trl/experimental/ssd/ssd_trainer.py,sha256=1kH3JERtlpVMwZrNQjijvwCZuP6xABHMNc06bT_p7vM,23446
trl/experimental/tpo/__init__.py,sha256=fDIWPC3c1BL3VngtbKbnaB-UNRNY4tewOYrr_7yXWG4,722
trl/experimental/tpo/tpo.py,sha256=i_HeccB9rDPoLMCrC36euuDOiikPvLQervsbm6q7nzw,8510
trl/experimental/tpo/tpo_config.py,sha256=DW2ErV2F0TELILwS4XPHdOlqNs15ldEXlLCoU0OfKSY,7395
trl/experimental/tpo/tpo_trainer.py,sha256=uJJLmCl2D4SRdI1-ZcBJBx3vM7v8dMDo9GfTUUX5N4M,41273
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=AoAErLI7Rnh9CA_OZXllTy_E5BuxRpdoop7DmWqx06k,22676
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=kdmjghftaN1onlnUr-QIzJPT71a0BTnufQm4R_J3ZtQ,7368
trl/generation/__init__.py,sha256=aAYDsVEN0dDYZMZaeZvBhAohos1fQX_asTGHJrjmFUE,828
trl/generation/vllm_client.py,sha256=_SqrSgfWaVfUiHJ7s7ezGntpM11REhIhsC-kzfEBaCk,35299
trl/generation/vllm_generation.py,sha256=8aEASSev85CXlIYKLBfBM_2Bs8uuZ3-D1IoapCshPtE,36902
trl/models/__init__.py,sha256=AdtqJlv3mNNGldTZRmm1-0Ymm0yMrpwnXN0ilv0gdY0,1219
trl/models/activation_offloading.py,sha256=ZKnl22gUmvG1FcJrXQZJGyHK_bviFyrqx9mk67Rnxis,34695
trl/models/utils.py,sha256=cNmmlLozdGnr48Q0YU8XmXEsU9XPmTNXd9k5H-QSt0I,17495
trl/rewards/__init__.py,sha256=IrGRuDNDLkWTJxsemd_WQtWcl8pD3XuB5WkrxL2FOHY,1216
trl/rewards/accuracy_rewards.py,sha256=1vr-Ij7rHBot9k7_aiX4QtFHCc9CBK0ZJJv5dBohVX4,10941
trl/rewards/format_rewards.py,sha256=XKId9E_3opkCtiELkYSWKxb8QnYJv2EGLuT9QOcmbS0,2211
trl/rewards/other_rewards.py,sha256=fzad9ow5yukVkdfan3hMWY7alEv2E-4Q7BPckNUcgaQ,2633
trl/scripts/__init__.py,sha256=uBELpz2YbIG2YxXa5ioNhrWE0nqoior8hkFGP3ZzYe0,1077
trl/scripts/_hf_argparser.py,sha256=865qZQypA7UqaDOlXuMBhC1WOJkzxmlo0WVIo2wiwf0,20034
trl/scripts/dpo.py,sha256=SUBHkM_uom-6zQeq-1NtTkkA1ynuDuFn2xqEoOehFX0,5590
trl/scripts/env.py,sha256=NwKqs_IQK3tpW0xbBZU6qEx_68-T_SqAv_-BElbkroY,3285
trl/scripts/grpo.py,sha256=Rq6dJZbUZMyA7PyhJgI1Nqp509jgcrpls_akvuRN4ig,7245
trl/scripts/kto.py,sha256=O5rFvS4Xpu7ozDy62oPf07x_FfAqsgN13Jey9sn-bWA,5160
trl/scripts/reward.py,sha256=qlMpOkT5ytUs-3jF3TeyP1oUEZoHyyyEO2LE1sN6IAg,3383
trl/scripts/rloo.py,sha256=tkpxZjhtL86AD0siwBu_QZIA-IUdrpAifzvgbdWErRQ,6527
trl/scripts/sft.py,sha256=u2esOA16vkWCN-svrOorRHVRCTeZnU_VbbtoOcEwFNk,5611
trl/scripts/utils.py,sha256=LMFn84Y8ZYx3G7kc3Y9l60JO0dd7jYz8p8nC08YSrcg,18260
trl/scripts/vllm_serve.py,sha256=5gYACkVgXF5KzsVysK4KaYXHpHKIAU0cyqeDDtWSAh4,59744
trl/skills/__init__.py,sha256=ztKZxcsQqk9gvPe4pV87ZUIPgPW3LwBNXW2-Z9vGwNQ,740
trl/skills/cli.py,sha256=EOZ52Ykz-p6CO8Rb6dL39up52yLEehhf81n98VWH2gQ,6871
trl/skills/skills.py,sha256=3x0WadVnYSNnkJuTAlMU4QwSK_rkayeBHIhI4m6A23M,11834
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=r6ucMHWPi6MFNO5HnsRAktwuiuDNKi4e7wHLM7RBpjg,2641
trl/trainer/base_config.py,sha256=wD4Fur8JA0h6OwmstTTVDJKdAbI6gCekZOoU9KVznS4,5759
trl/trainer/base_trainer.py,sha256=VxgqHS6PWROLYgRednWJslV8i6e9YxMmc_8e6xv520M,3287
trl/trainer/callbacks.py,sha256=V3r1PHsSknFdK0jgb94nAwIPSz98T_3aorIvtSr2Zbs,31337
trl/trainer/dpo_config.py,sha256=Z5vaotNGOJmpHBiKuaOb8XFbUp8lBx6cKwVBlVcvwsU,18156
trl/trainer/dpo_trainer.py,sha256=oslEmD2MNabRyvORNQHQ3Ac4OwVf0tGTesha-cAnuoE,83937
trl/trainer/grpo_config.py,sha256=HDQrtK_MViJM3sdS_rofoR0hN6oMT-nBXk4D1NcRCV4,56655
trl/trainer/grpo_trainer.py,sha256=kfW1uB7nusJN7I00bw-v7bsyObmkUwJJ345HQRK_UJw,150801
trl/trainer/kto_config.py,sha256=g9ZzUlnwRyvSKcfA3pNI-ep3u4b2kTAK3E3Jkv4XurU,1429
trl/trainer/kto_trainer.py,sha256=xlFQtdF_Hx-bL9g2JJ2LTmsT-NSarjpfKt9fVKBvvuY,1458
trl/trainer/model_config.py,sha256=7k27sX-GRpF3tum8nccoa9jHX4LVu_ZLA9hwa6wWh1U,8813
trl/trainer/reward_config.py,sha256=TmiX7vD1dPW0Deosi9-H1uHAO-_XamJUAGV4_NiAPJI,7823
trl/trainer/reward_trainer.py,sha256=Y9RFWAbeplgsRUprgdJ8YOmykVtFqP3pEAgNnY6CKZ8,35305
trl/trainer/rloo_config.py,sha256=RVs_Vxfctj0liFN1PsoVuygogsifaUG4Vit_ddbAg7g,32155
trl/trainer/rloo_trainer.py,sha256=hEL0LSanntl_i0E4BhWLsIgIOAA3Tlvflbxt0niD3LA,84676
trl/trainer/sft_config.py,sha256=zkavOBp7vcGHCNC26hMrC1ckuH0Yl63XWKGEFX30JIo,15368
trl/trainer/sft_trainer.py,sha256=WugWermb8sbkyuSNhcch-WoZ1YM8iOLGD6bltCvt9Y8,77896
trl/trainer/utils.py,sha256=rPEWXyalVdZNUS4l-8scKXjfEjsI77NWIxJ-hPaN2XU,51125
trl-1.3.0.dist-info/licenses/LICENSE,sha256=G_YUsf3ED700SqWNANF9X9DSUuozOgW-AYo4lZyLKZg,11355
trl-1.3.0.dist-info/METADATA,sha256=gKIRV1nevGPE0Lkad5r1T1sFyIoQyZiZpNs3Rej0__8,11141
trl-1.3.0.dist-info/WHEEL,sha256=aeYiig01lYGDzBgS8HxWXOg3uV61G9ijOsup-k9o1sk,91
trl-1.3.0.dist-info/entry_points.txt,sha256=EiubuQrZSGOohRB4xVoiVAyWsPsOHPSVpbzSk8YB0x0,37
trl-1.3.0.dist-info/top_level.txt,sha256=QU12VhjlpAtMnIJqiO2np3RkTB_Eozt1d-g8QDf5P4c,4
trl-1.3.0.dist-info/RECORD,,
