| _app | | | 237 items |
| _toctree.yml | 3.35 kB | | ac839051 |
| async_grpo_trainer.html | 108 kB | | ff59d976 |
| async_grpo_trainer.md | 12.3 kB | | 2d4241fb |
| bco_trainer.html | 130 kB | | 7dae1767 |
| bco_trainer.md | 14.1 kB | | eef1942b |
| bema_for_reference_model.html | 90 kB | | 8a0b1014 |
| bema_for_reference_model.md | 7.18 kB | | 40f3d55c |
| callbacks.html | 95.8 kB | | b45eb6dd |
| callbacks.md | 7.88 kB | | 6e8a9d83 |
| chat_template_utils.html | 45.8 kB | | 832360c9 |
| chat_template_utils.md | 5.48 kB | | 2ed5c8e5 |
| chat_templates.html | 28.3 kB | | df01b32e |
| chat_templates.md | 5.13 kB | | 42aaee11 |
| clis.html | 53.4 kB | | 3f187677 |
| clis.md | 12.8 kB | | d8e42245 |
| community_tutorials.html | 31 kB | | 0bda5798 |
| community_tutorials.md | 11 kB | | 53c3badb |
| cpo_trainer.html | 144 kB | | 3ecb3aa7 |
| cpo_trainer.md | 23 kB | | bc9a8600 |
| customization.html | 31 kB | | 06a9fa77 |
| customization.md | 4.08 kB | | 4f4a6366 |
| data_utils.html | 62.9 kB | | 061faaf1 |
| data_utils.md | 6.32 kB | | d7006c37 |
| dataset_formats.html | 223 kB | | 2b70570d |
| dataset_formats.md | 40.2 kB | | 83e8cb76 |
| deepspeed_integration.html | 15.8 kB | | 2fd8482e |
| deepspeed_integration.md | 1.48 kB | | 96460e48 |
| distillation_trainer.html | 160 kB | | 1359ce92 |
| distillation_trainer.md | 12.3 kB | | 56b960cd |
| distributing_training.html | 96.5 kB | | b7b64a93 |
| distributing_training.md | 21 kB | | 400cb97c |
| dpo_trainer.html | 232 kB | | 3b0417a7 |
| dpo_trainer.md | 30.8 kB | | 4eb013c5 |
| example_overview.html | 42.8 kB | | 846337dd |
| example_overview.md | 19.7 kB | | a167d16b |
| experimental_overview.html | 10.8 kB | | 3828f202 |
| experimental_overview.md | 1.6 kB | | d2f8cf27 |
| favicon.png | 1.57 kB | | 6e06dd7b |
| gfpo.html | 84.4 kB | | 56888cf9 |
| gfpo.md | 5.24 kB | | aa81b084 |
| gkd_trainer.html | 119 kB | | 2c35e313 |
| gkd_trainer.md | 14.1 kB | | ca110195 |
| gold_trainer.html | 166 kB | | c911f442 |
| gold_trainer.md | 18.1 kB | | 04f193f5 |
| grpo_trainer.html | 560 kB | | 82ef71a9 |
| grpo_trainer.md | 55.8 kB | | e3749c4f |
| grpo_with_replay_buffer.html | 89.6 kB | | 5bae6887 |
| grpo_with_replay_buffer.md | 6.16 kB | | 9c90ad94 |
| gspo_token.html | 50.2 kB | | 5f722492 |
| gspo_token.md | 4.27 kB | | fb3567ba |
| index.html | 29 kB | | c7b83b6b |
| index.md | 3.66 kB | | 0c94ab19 |
| installation.html | 13.9 kB | | 9f69cc8b |
| installation.md | 721 Bytes | | 93a212e0 |
| jobs_training.html | 32.9 kB | | bc72715e |
| jobs_training.md | 6.44 kB | | 7e612e1d |
| kernels_hub.html | 26.8 kB | | da356eaa |
| kernels_hub.md | 4.18 kB | | 6982a1e3 |
| kto_trainer.html | 137 kB | | 185288bf |
| kto_trainer.md | 18.1 kB | | d8c286d5 |
| liger_kernel_integration.html | 15 kB | | 8946b267 |
| liger_kernel_integration.md | 2.2 kB | | 0ab2ea33 |
| llms-full.txt | 842 kB | | f94d567c |
| llms.txt | 5.08 kB | | 7fa98834 |
| lora_without_regret.html | 45 kB | | 54666d12 |
| lora_without_regret.md | 14.4 kB | | c3be6b18 |
| merge_model_callback.html | 17.8 kB | | 203467ce |
| merge_model_callback.md | 1.19 kB | | feec431f |
| minillm_trainer.html | 179 kB | | 987076d4 |
| minillm_trainer.md | 16.4 kB | | 6871d521 |
| nash_md_trainer.html | 124 kB | | fdc5ee7e |
| nash_md_trainer.md | 16.3 kB | | 7fb2a47e |
| nemo_gym.html | 58.5 kB | | 908a02cb |
| nemo_gym.md | 10.3 kB | | b5b12cc0 |
| objects.inv | 2.41 kB | | cbe7246b |
| online_dpo_trainer.html | 179 kB | | 4ef88a27 |
| online_dpo_trainer.md | 23.1 kB | | eadfdf8b |
| openenv.html | 114 kB | | 10aca185 |
| openenv.md | 27.8 kB | | 0d70e92c |
| orpo_trainer.html | 127 kB | | ddf80af2 |
| orpo_trainer.md | 17.7 kB | | cbdbd480 |
| paper_index.html | 734 kB | | bc0e404b |
| paper_index.md | 19.1 kB | | 4e963bc3 |
| papo_trainer.html | 111 kB | | e39d9615 |
| papo_trainer.md | 8.82 kB | | 773ec951 |
| peft_integration.html | 131 kB | | 89fa1804 |
| peft_integration.md | 23.9 kB | | 5ee64593 |
| ppo_trainer.html | 278 kB | | 8f9e494f |
| ppo_trainer.md | 41.4 kB | | d6bb6a08 |
| prm_trainer.html | 117 kB | | c989521a |
| prm_trainer.md | 13.9 kB | | 1f434208 |
| ptt_integration.html | 29.3 kB | | cf1525e0 |
| ptt_integration.md | 4.27 kB | | 6a21357a |
| quickstart.html | 37.4 kB | | 950d508d |
| quickstart.md | 3.25 kB | | 1c4455a3 |
| rapidfire_integration.html | 81.1 kB | | 990936a1 |
| rapidfire_integration.md | 12.8 kB | | 78b07e81 |
| reducing_memory_usage.html | 52.4 kB | | 6906299c |
| reducing_memory_usage.md | 12.3 kB | | d61af82e |
|