| _app | | | 137 items |
| _toctree.yml | 3.38 kB | | 9da8f3eb |
| async_grpo_trainer.html | 108 kB | | 3e9864fe |
| async_grpo_trainer.md | 12.3 kB | | e0837a0c |
| bco_trainer.html | 130 kB | | c3a80354 |
| bco_trainer.md | 14.1 kB | | 84512ed7 |
| bema_for_reference_model.html | 90 kB | | 17de198c |
| bema_for_reference_model.md | 7.18 kB | | b05d00d2 |
| callbacks.html | 95.8 kB | | bfd2d126 |
| callbacks.md | 7.88 kB | | 6c13d942 |
| chat_template_utils.html | 45.9 kB | | 62c44e4c |
| chat_template_utils.md | 5.5 kB | | af2d758e |
| chat_templates.html | 28.3 kB | | 71e0f209 |
| chat_templates.md | 5.13 kB | | dc70a43d |
| clis.html | 53.4 kB | | dd69c12a |
| clis.md | 12.8 kB | | 44b2141a |
| community_tutorials.html | 31 kB | | 16dc365f |
| community_tutorials.md | 11 kB | | 7426cd11 |
| cpo_trainer.html | 144 kB | | 9074e43f |
| cpo_trainer.md | 23 kB | | f0bc6f43 |
| customization.html | 31 kB | | bfecec24 |
| customization.md | 4.08 kB | | 73123c87 |
| data_utils.html | 62.7 kB | | 05dab98b |
| data_utils.md | 6.87 kB | | d4b66dbd |
| dataset_formats.html | 223 kB | | 96d505c2 |
| dataset_formats.md | 40.2 kB | | b31f59c3 |
| deepspeed_integration.html | 15.8 kB | | a0649500 |
| deepspeed_integration.md | 1.48 kB | | 96460e48 |
| distillation_trainer.html | 161 kB | | e7547303 |
| distillation_trainer.md | 12.3 kB | | 19d4308b |
| distributing_training.html | 96.5 kB | | a660f2d7 |
| distributing_training.md | 21 kB | | 400cb97c |
| dpo_trainer.html | 233 kB | | 57625529 |
| dpo_trainer.md | 30.8 kB | | 2b831dc0 |
| example_overview.html | 42.7 kB | | e557f10d |
| example_overview.md | 19.7 kB | | 68223fca |
| experimental_overview.html | 10.8 kB | | 22af8c9c |
| experimental_overview.md | 1.6 kB | | d2f8cf27 |
| favicon.png | 1.57 kB | | 6e06dd7b |
| gfpo.html | 85 kB | | 27bcb141 |
| gfpo.md | 5.24 kB | | 5b1147e9 |
| gkd_trainer.html | 119 kB | | ef1968cb |
| gkd_trainer.md | 14.1 kB | | 433c372b |
| gold_trainer.html | 166 kB | | 7e82112c |
| gold_trainer.md | 18.1 kB | | 40dcb602 |
| grpo_trainer.html | 561 kB | | 0a5ee919 |
| grpo_trainer.md | 55.8 kB | | d7fe782c |
| grpo_with_replay_buffer.html | 90.3 kB | | cb7bd204 |
| grpo_with_replay_buffer.md | 6.16 kB | | 8262e6b3 |
| gspo_token.html | 50.2 kB | | afabf96f |
| gspo_token.md | 4.27 kB | | 85a2221a |
| index.html | 29 kB | | ffefef66 |
| index.md | 3.66 kB | | 0c94ab19 |
| installation.html | 13.9 kB | | 6615ac04 |
| installation.md | 721 Bytes | | 93a212e0 |
| jobs_training.html | 32.9 kB | | ffb2c85e |
| jobs_training.md | 6.44 kB | | 7e612e1d |
| kernels_hub.html | 26.8 kB | | c3b65b77 |
| kernels_hub.md | 4.18 kB | | 6982a1e3 |
| kto_trainer.html | 138 kB | | f91347a0 |
| kto_trainer.md | 18.4 kB | | 0bceb380 |
| liger_kernel_integration.html | 15 kB | | 914f13c4 |
| liger_kernel_integration.md | 2.2 kB | | 0ab2ea33 |
| llms-full.txt | 867 kB | | dc306f11 |
| llms.txt | 5.15 kB | | f7eefc83 |
| lora_without_regret.html | 45 kB | | 370d4557 |
| lora_without_regret.md | 14.4 kB | | c3be6b18 |
| merge_model_callback.html | 17.8 kB | | 9f96406f |
| merge_model_callback.md | 1.19 kB | | 376f3b26 |
| minillm_trainer.html | 180 kB | | fd0d49b5 |
| minillm_trainer.md | 16.4 kB | | 51fb2bfb |
| nash_md_trainer.html | 125 kB | | 67a066ef |
| nash_md_trainer.md | 16.3 kB | | 0b2f841d |
| nemo_gym.html | 58.5 kB | | d8a16dd2 |
| nemo_gym.md | 10.3 kB | | b5b12cc0 |
| objects.inv | 2.45 kB | | 11bba98c |
| online_dpo_trainer.html | 180 kB | | db3b2525 |
| online_dpo_trainer.md | 23.1 kB | | 7a14035b |
| openenv.html | 114 kB | | 57eaab8a |
| openenv.md | 27.8 kB | | 99aed39d |
| orpo_trainer.html | 127 kB | | b7020c5a |
| orpo_trainer.md | 17.7 kB | | 6f93320e |
| paper_index.html | 742 kB | | 823e7ac3 |
| paper_index.md | 19.1 kB | | 7af1b6a6 |
| papo_trainer.html | 112 kB | | 2a486400 |
| papo_trainer.md | 8.82 kB | | 641f77a0 |
| peft_integration.html | 131 kB | | 7d10edee |
| peft_integration.md | 23.9 kB | | e8d5c2a8 |
| ppo_trainer.html | 279 kB | | e91d4f6e |
| ppo_trainer.md | 41.4 kB | | df9d174c |
| prm_trainer.html | 118 kB | | cc90329a |
| prm_trainer.md | 13.9 kB | | cfb475b2 |
| ptt_integration.html | 29.3 kB | | 9460dc17 |
| ptt_integration.md | 4.27 kB | | 6a21357a |
| quickstart.html | 37.4 kB | | f029f01b |
| quickstart.md | 3.25 kB | | 1c4455a3 |
| rapidfire_integration.html | 95.4 kB | | 4c24001f |
| rapidfire_integration.md | 17.7 kB | | 08fed5af |
| reducing_memory_usage.html | 52.4 kB | | 6f422a77 |
| reducing_memory_usage.md | 12.3 kB | | d61af82e |
|