| _app | | | 143 items |
| _toctree.yml | 3.38 kB | | 9da8f3eb |
| async_grpo_trainer.html | 108 kB | | 91808b29 |
| async_grpo_trainer.md | 12.3 kB | | 8be45e6c |
| bco_trainer.html | 130 kB | | 899fd99c |
| bco_trainer.md | 14.1 kB | | 8025d19d |
| bema_for_reference_model.html | 90 kB | | 3fd264be |
| bema_for_reference_model.md | 7.18 kB | | 3858ce17 |
| callbacks.html | 95.8 kB | | eadace1b |
| callbacks.md | 7.88 kB | | 901c3153 |
| chat_template_utils.html | 45.9 kB | | 5495106b |
| chat_template_utils.md | 5.51 kB | | 2cee5043 |
| chat_templates.html | 33.5 kB | | 8dbc6945 |
| chat_templates.md | 6.03 kB | | ca05ef19 |
| clis.html | 53.4 kB | | 491e858d |
| clis.md | 12.8 kB | | 656b21c7 |
| community_tutorials.html | 31 kB | | 8b587f35 |
| community_tutorials.md | 10.9 kB | | db7ac12d |
| cpo_trainer.html | 144 kB | | cc1ce578 |
| cpo_trainer.md | 23 kB | | fc0d9a3e |
| customization.html | 30.9 kB | | f8707c7c |
| customization.md | 4.04 kB | | 13e546a2 |
| data_utils.html | 62.7 kB | | e2437b39 |
| data_utils.md | 6.87 kB | | 711dce99 |
| dataset_formats.html | 223 kB | | dca459a1 |
| dataset_formats.md | 40.1 kB | | b1e1e9d0 |
| deepspeed_integration.html | 15.8 kB | | 3d1aaee6 |
| deepspeed_integration.md | 1.48 kB | | 96460e48 |
| distillation_trainer.html | 161 kB | | 20fe25fe |
| distillation_trainer.md | 12.3 kB | | a402f230 |
| distributing_training.html | 96.5 kB | | c81ab16e |
| distributing_training.md | 21 kB | | 400cb97c |
| dpo_trainer.html | 232 kB | | a14f2139 |
| dpo_trainer.md | 30.7 kB | | e0a29e26 |
| example_overview.html | 42.7 kB | | c96bc6de |
| example_overview.md | 19.6 kB | | 2c3936eb |
| experimental_overview.html | 10.8 kB | | bc619000 |
| experimental_overview.md | 1.6 kB | | d2f8cf27 |
| favicon.png | 1.57 kB | | 6e06dd7b |
| gfpo.html | 85 kB | | f1e5576f |
| gfpo.md | 5.24 kB | | c5d45971 |
| gkd_trainer.html | 119 kB | | 1ab4ea87 |
| gkd_trainer.md | 14.1 kB | | a59f1ca1 |
| gold_trainer.html | 166 kB | | 243e70d4 |
| gold_trainer.md | 18.1 kB | | 7c67e67b |
| grpo_trainer.html | 561 kB | | 538a3993 |
| grpo_trainer.md | 55.8 kB | | ca484acc |
| grpo_with_replay_buffer.html | 90.3 kB | | 8372f92f |
| grpo_with_replay_buffer.md | 6.16 kB | | c9b28000 |
| gspo_token.html | 50.2 kB | | b95ea0ae |
| gspo_token.md | 4.27 kB | | e4b52686 |
| index.html | 29 kB | | 1005ac58 |
| index.md | 3.66 kB | | 0c94ab19 |
| installation.html | 13.9 kB | | 079474ce |
| installation.md | 721 Bytes | | 93a212e0 |
| jobs_training.html | 32.9 kB | | 36ea0be9 |
| jobs_training.md | 6.44 kB | | 7e612e1d |
| kernels_hub.html | 26.8 kB | | dba119cf |
| kernels_hub.md | 4.18 kB | | 6982a1e3 |
| kto_trainer.html | 138 kB | | 9310d930 |
| kto_trainer.md | 18.4 kB | | 0594aa50 |
| liger_kernel_integration.html | 15 kB | | 49f2fb7e |
| liger_kernel_integration.md | 2.2 kB | | 0ab2ea33 |
| llms-full.txt | 867 kB | | bd1859c3 |
| llms.txt | 5.15 kB | | 6eb92e4c |
| lora_without_regret.html | 45 kB | | 01a6eee0 |
| lora_without_regret.md | 14.4 kB | | c3be6b18 |
| merge_model_callback.html | 17.8 kB | | bc054270 |
| merge_model_callback.md | 1.19 kB | | 79304320 |
| minillm_trainer.html | 180 kB | | 908e63ea |
| minillm_trainer.md | 16.4 kB | | 8c881c48 |
| nash_md_trainer.html | 125 kB | | d2e83058 |
| nash_md_trainer.md | 16.3 kB | | a13df9aa |
| nemo_gym.html | 58.5 kB | | 5fe69da0 |
| nemo_gym.md | 10.3 kB | | b5b12cc0 |
| objects.inv | 2.44 kB | | 5da39104 |
| online_dpo_trainer.html | 180 kB | | 8bae7785 |
| online_dpo_trainer.md | 23.1 kB | | b2c79d58 |
| openenv.html | 114 kB | | 517fba94 |
| openenv.md | 27.8 kB | | 5db49456 |
| orpo_trainer.html | 127 kB | | 3c19895d |
| orpo_trainer.md | 17.7 kB | | 27024035 |
| paper_index.html | 742 kB | | 4797b05e |
| paper_index.md | 19.1 kB | | e9e89c79 |
| papo_trainer.html | 112 kB | | 3e5ff130 |
| papo_trainer.md | 8.82 kB | | 54b53613 |
| peft_integration.html | 131 kB | | ef4b30f2 |
| peft_integration.md | 23.9 kB | | 0a59be54 |
| ppo_trainer.html | 279 kB | | 956e7902 |
| ppo_trainer.md | 41.4 kB | | aded8fc7 |
| prm_trainer.html | 118 kB | | c59aef7e |
| prm_trainer.md | 13.9 kB | | de1b6de6 |
| ptt_integration.html | 29.3 kB | | 062bfcc2 |
| ptt_integration.md | 4.27 kB | | 6a21357a |
| quickstart.html | 37.4 kB | | 9bd10e56 |
| quickstart.md | 3.25 kB | | 1c4455a3 |
| rapidfire_integration.html | 95.4 kB | | 2d0ef7f7 |
| rapidfire_integration.md | 17.7 kB | | 08fed5af |
| reducing_memory_usage.html | 52.4 kB | | 2136580b |
| reducing_memory_usage.md | 12.3 kB | | d61af82e |
|