| _app | | | 295 items |
| _toctree.yml | 3.38 kB | | 9da8f3eb |
| async_grpo_trainer.html | 108 kB | | b0b87295 |
| async_grpo_trainer.md | 12.3 kB | | 2bf544a0 |
| bco_trainer.html | 130 kB | | e1a513cf |
| bco_trainer.md | 14.2 kB | | 94ca209f |
| bema_for_reference_model.html | 90 kB | | ff2f8948 |
| bema_for_reference_model.md | 7.18 kB | | af0fc13d |
| callbacks.html | 95.8 kB | | c2cca592 |
| callbacks.md | 7.88 kB | | 10d30591 |
| chat_template_utils.html | 46.3 kB | | 912a7ca1 |
| chat_template_utils.md | 5.84 kB | | 14aa4e3f |
| chat_templates.html | 44.7 kB | | 829244f7 |
| chat_templates.md | 8.74 kB | | 54b9cf36 |
| clis.html | 53.4 kB | | ec5f2c5e |
| clis.md | 12.8 kB | | e7be68f1 |
| community_tutorials.html | 31 kB | | eb600d32 |
| community_tutorials.md | 11 kB | | d94302ce |
| cpo_trainer.html | 145 kB | | d02e481c |
| cpo_trainer.md | 23.2 kB | | 24f5c580 |
| customization.html | 31 kB | | 9bfaf093 |
| customization.md | 4.08 kB | | 9db6f39f |
| data_utils.html | 62.7 kB | | 8f843bd0 |
| data_utils.md | 6.87 kB | | 6b2338eb |
| dataset_formats.html | 223 kB | | a79e90b4 |
| dataset_formats.md | 43 kB | | 3405acf2 |
| deepspeed_integration.html | 15.8 kB | | 17a4deef |
| deepspeed_integration.md | 1.52 kB | | e5b0fad5 |
| distillation_trainer.html | 161 kB | | f36d8e96 |
| distillation_trainer.md | 12.3 kB | | c517e5a0 |
| distributing_training.html | 96.5 kB | | e16268e8 |
| distributing_training.md | 21 kB | | 75949925 |
| dpo_trainer.html | 233 kB | | a4ff138b |
| dpo_trainer.md | 31.1 kB | | d17c8d57 |
| example_overview.html | 42.7 kB | | 46b71dfd |
| example_overview.md | 19.7 kB | | 51789a33 |
| experimental_overview.html | 10.8 kB | | 9fed52e2 |
| experimental_overview.md | 1.62 kB | | 45d90cc6 |
| favicon.png | 1.57 kB | | 6e06dd7b |
| gfpo.html | 85 kB | | b0732f33 |
| gfpo.md | 5.24 kB | | 9e364163 |
| gkd_trainer.html | 119 kB | | 13f8a254 |
| gkd_trainer.md | 14.1 kB | | edb18831 |
| gold_trainer.html | 166 kB | | 0bc9f1bb |
| gold_trainer.md | 18.1 kB | | 76ba9db8 |
| grpo_trainer.html | 561 kB | | 362b126a |
| grpo_trainer.md | 61.5 kB | | 97cec241 |
| grpo_with_replay_buffer.html | 90.3 kB | | d135d22b |
| grpo_with_replay_buffer.md | 6.16 kB | | 39d633e3 |
| gspo_token.html | 50.2 kB | | fc6014aa |
| gspo_token.md | 4.27 kB | | 01429277 |
| index.html | 29 kB | | a19ba81f |
| index.md | 3.66 kB | | 0c94ab19 |
| installation.html | 13.9 kB | | b21456f9 |
| installation.md | 721 Bytes | | 93a212e0 |
| jobs_training.html | 32.9 kB | | 4d4888b7 |
| jobs_training.md | 6.46 kB | | cb814663 |
| kernels_hub.html | 26.8 kB | | 025ffb5d |
| kernels_hub.md | 4.18 kB | | 6982a1e3 |
| kto_trainer.html | 134 kB | | 7b980ec8 |
| kto_trainer.md | 18.2 kB | | 2a5092d3 |
| liger_kernel_integration.html | 15 kB | | 8a65f8fc |
| liger_kernel_integration.md | 2.2 kB | | 0ab2ea33 |
| llms-full.txt | 950 kB | | 935df60d |
| llms.txt | 5.15 kB | | 4ce9c0ed |
| lora_without_regret.html | 45 kB | | 46741084 |
| lora_without_regret.md | 14.4 kB | | c3be6b18 |
| merge_model_callback.html | 17.8 kB | | 38eee58d |
| merge_model_callback.md | 1.19 kB | | 7302537e |
| minillm_trainer.html | 180 kB | | 7b1426a0 |
| minillm_trainer.md | 16.4 kB | | b3923ecf |
| nash_md_trainer.html | 125 kB | | 7e049e9e |
| nash_md_trainer.md | 16.6 kB | | 93144031 |
| nemo_gym.html | 58.5 kB | | f75e20a2 |
| nemo_gym.md | 10.3 kB | | 45caccd9 |
| objects.inv | 2.45 kB | | b62cc307 |
| online_dpo_trainer.html | 180 kB | | 1a71a14d |
| online_dpo_trainer.md | 23.3 kB | | 22a11953 |
| openenv.html | 114 kB | | b9400800 |
| openenv.md | 27.8 kB | | 76333b71 |
| orpo_trainer.html | 128 kB | | 0d24149d |
| orpo_trainer.md | 17.9 kB | | d9a041de |
| paper_index.html | 761 kB | | f31c1802 |
| paper_index.md | 85.1 kB | | b904bf1b |
| papo_trainer.html | 112 kB | | 6b7bcd73 |
| papo_trainer.md | 8.82 kB | | 09204706 |
| peft_integration.html | 131 kB | | 4ee27a0e |
| peft_integration.md | 23.9 kB | | d6ceeb88 |
| ppo_trainer.html | 279 kB | | 9fecabe0 |
| ppo_trainer.md | 41.5 kB | | 6ade640d |
| prm_trainer.html | 118 kB | | aeb4988f |
| prm_trainer.md | 14.2 kB | | 934bcbc8 |
| ptt_integration.html | 29.3 kB | | a541adcb |
| ptt_integration.md | 4.27 kB | | 6a21357a |
| quickstart.html | 37.4 kB | | ea4a482c |
| quickstart.md | 3.25 kB | | 1c4455a3 |
| rapidfire_integration.html | 95.4 kB | | 21c24d0e |
| rapidfire_integration.md | 17.8 kB | | b0dd6d2b |
| reducing_memory_usage.html | 57.1 kB | | 037cfe59 |
| reducing_memory_usage.md | 13.7 kB | | 0bb6a3f1 |
|