| _app | | | 185 items |
| _toctree.yml | 3.38 kB | | 9da8f3eb |
| async_grpo_trainer.html | 108 kB | | 7e0bab83 |
| async_grpo_trainer.md | 12.3 kB | | 562acd87 |
| bco_trainer.html | 130 kB | | 3dae7d8b |
| bco_trainer.md | 14.2 kB | | 30bb27fb |
| bema_for_reference_model.html | 90 kB | | 98a71da4 |
| bema_for_reference_model.md | 7.18 kB | | efc66e02 |
| callbacks.html | 95.8 kB | | 3ba6b144 |
| callbacks.md | 7.88 kB | | a66c3327 |
| chat_template_utils.html | 46.2 kB | | 2a86f30b |
| chat_template_utils.md | 5.78 kB | | 214ec8ec |
| chat_templates.html | 37.1 kB | | f49ea86f |
| chat_templates.md | 7.04 kB | | 109ec857 |
| clis.html | 53.4 kB | | 80f1925c |
| clis.md | 12.8 kB | | 0ae66524 |
| community_tutorials.html | 31 kB | | 804ffb76 |
| community_tutorials.md | 10.9 kB | | 837a6be8 |
| cpo_trainer.html | 145 kB | | f407dcf5 |
| cpo_trainer.md | 23.2 kB | | 51eddff4 |
| customization.html | 30.9 kB | | e75263b3 |
| customization.md | 4.04 kB | | 01bdf071 |
| data_utils.html | 62.7 kB | | 425b010e |
| data_utils.md | 6.87 kB | | b152c4ce |
| dataset_formats.html | 223 kB | | b22be036 |
| dataset_formats.md | 43 kB | | 7ef4c8ed |
| deepspeed_integration.html | 15.8 kB | | a929beb5 |
| deepspeed_integration.md | 1.52 kB | | e5b0fad5 |
| distillation_trainer.html | 161 kB | | d27844a7 |
| distillation_trainer.md | 12.3 kB | | 385cba9c |
| distributing_training.html | 96.5 kB | | 5bfcf57e |
| distributing_training.md | 21 kB | | 75949925 |
| dpo_trainer.html | 232 kB | | 6a6edd15 |
| dpo_trainer.md | 30.8 kB | | d9afba6d |
| example_overview.html | 42.7 kB | | 9ba75ef9 |
| example_overview.md | 19.6 kB | | 50467afd |
| experimental_overview.html | 10.8 kB | | a5877dd2 |
| experimental_overview.md | 1.62 kB | | 45d90cc6 |
| favicon.png | 1.57 kB | | 6e06dd7b |
| gfpo.html | 85 kB | | af197b7a |
| gfpo.md | 5.24 kB | | ebee4f48 |
| gkd_trainer.html | 119 kB | | cbe90b83 |
| gkd_trainer.md | 14.1 kB | | d6960248 |
| gold_trainer.html | 166 kB | | 9b53d3d5 |
| gold_trainer.md | 18.1 kB | | 358e19e0 |
| grpo_trainer.html | 561 kB | | 0c79fa8b |
| grpo_trainer.md | 61.5 kB | | e3c08805 |
| grpo_with_replay_buffer.html | 90.3 kB | | 2020de32 |
| grpo_with_replay_buffer.md | 6.16 kB | | 1a127210 |
| gspo_token.html | 50.2 kB | | 286c20af |
| gspo_token.md | 4.27 kB | | ae06d5ae |
| index.html | 29 kB | | e93da0e9 |
| index.md | 3.66 kB | | 0c94ab19 |
| installation.html | 13.9 kB | | cd0d1d23 |
| installation.md | 721 Bytes | | 93a212e0 |
| jobs_training.html | 32.9 kB | | b5e5794a |
| jobs_training.md | 6.46 kB | | cb814663 |
| kernels_hub.html | 26.8 kB | | 707c97a4 |
| kernels_hub.md | 4.18 kB | | 6982a1e3 |
| kto_trainer.html | 134 kB | | 9a95489f |
| kto_trainer.md | 18.2 kB | | 713e42f5 |
| liger_kernel_integration.html | 15 kB | | 9e304c27 |
| liger_kernel_integration.md | 2.2 kB | | 0ab2ea33 |
| llms-full.txt | 947 kB | | c65ee247 |
| llms.txt | 5.15 kB | | bbf6cb4a |
| lora_without_regret.html | 45 kB | | 94d23ad2 |
| lora_without_regret.md | 14.4 kB | | c3be6b18 |
| merge_model_callback.html | 17.8 kB | | d747319c |
| merge_model_callback.md | 1.19 kB | | 1afb5cd4 |
| minillm_trainer.html | 180 kB | | 55058cd3 |
| minillm_trainer.md | 16.4 kB | | 9201c67b |
| nash_md_trainer.html | 125 kB | | df8d9eda |
| nash_md_trainer.md | 16.6 kB | | 82f1317f |
| nemo_gym.html | 58.5 kB | | 33c4413c |
| nemo_gym.md | 10.3 kB | | 45caccd9 |
| objects.inv | 2.44 kB | | 81c70d3b |
| online_dpo_trainer.html | 180 kB | | d59e739a |
| online_dpo_trainer.md | 23.3 kB | | 31130520 |
| openenv.html | 114 kB | | 421da56f |
| openenv.md | 27.8 kB | | 441ea5ae |
| orpo_trainer.html | 128 kB | | d09ef826 |
| orpo_trainer.md | 17.9 kB | | 5ca01cf7 |
| paper_index.html | 742 kB | | f2a3d883 |
| paper_index.md | 84 kB | | 5dc1faa3 |
| papo_trainer.html | 112 kB | | 0002f4b3 |
| papo_trainer.md | 8.82 kB | | bce7942d |
| peft_integration.html | 131 kB | | 991f423a |
| peft_integration.md | 23.9 kB | | 0c0412d5 |
| ppo_trainer.html | 279 kB | | 5d1ab7fa |
| ppo_trainer.md | 41.5 kB | | d4119e63 |
| prm_trainer.html | 118 kB | | 6284fe75 |
| prm_trainer.md | 14.2 kB | | e85730bb |
| ptt_integration.html | 29.3 kB | | 2c58f798 |
| ptt_integration.md | 4.27 kB | | 6a21357a |
| quickstart.html | 37.4 kB | | 5314de3f |
| quickstart.md | 3.25 kB | | 1c4455a3 |
| rapidfire_integration.html | 95.4 kB | | 1b3f9ab7 |
| rapidfire_integration.md | 17.8 kB | | b0dd6d2b |
| reducing_memory_usage.html | 57.1 kB | | f515e7ca |
| reducing_memory_usage.md | 13.7 kB | | 198e8d2b |
|