| _app | | | 243 items |
| _toctree.yml | 3.38 kB | | 9da8f3eb |
| async_grpo_trainer.html | 108 kB | | f56b9410 |
| async_grpo_trainer.md | 12.3 kB | | 3041de0d |
| bco_trainer.html | 130 kB | | 75018cd0 |
| bco_trainer.md | 14.2 kB | | 8ae10799 |
| bema_for_reference_model.html | 90 kB | | 5811bd30 |
| bema_for_reference_model.md | 7.18 kB | | cccb4b9a |
| callbacks.html | 95.8 kB | | f5c1ec3a |
| callbacks.md | 7.88 kB | | 861d3314 |
| chat_template_utils.html | 46.3 kB | | 2c1f49bd |
| chat_template_utils.md | 5.84 kB | | 73d702c4 |
| chat_templates.html | 44.7 kB | | 363a5020 |
| chat_templates.md | 8.74 kB | | 60f681e6 |
| clis.html | 53.4 kB | | a9cc5f0b |
| clis.md | 12.8 kB | | d73bc0e8 |
| community_tutorials.html | 31 kB | | 95d21fee |
| community_tutorials.md | 11 kB | | e2f92cb6 |
| cpo_trainer.html | 145 kB | | 3945c24a |
| cpo_trainer.md | 23.2 kB | | 170ec32d |
| customization.html | 31 kB | | 173210d3 |
| customization.md | 4.08 kB | | 5e6f504e |
| data_utils.html | 62.7 kB | | c0bd8d5d |
| data_utils.md | 6.87 kB | | 2e62b70a |
| dataset_formats.html | 223 kB | | 73b56bf9 |
| dataset_formats.md | 43 kB | | ed6f98c6 |
| deepspeed_integration.html | 15.8 kB | | fac42b08 |
| deepspeed_integration.md | 1.52 kB | | e5b0fad5 |
| distillation_trainer.html | 161 kB | | d60e9ea0 |
| distillation_trainer.md | 12.3 kB | | 23c649ad |
| distributing_training.html | 96.5 kB | | 049e260f |
| distributing_training.md | 21 kB | | 75949925 |
| dpo_trainer.html | 233 kB | | 46b05eeb |
| dpo_trainer.md | 30.9 kB | | 7c1dbe44 |
| example_overview.html | 42.8 kB | | c6be02fa |
| example_overview.md | 19.7 kB | | e09e09ac |
| experimental_overview.html | 10.8 kB | | 23aff20e |
| experimental_overview.md | 1.62 kB | | 45d90cc6 |
| favicon.png | 1.57 kB | | 6e06dd7b |
| gfpo.html | 85 kB | | 83c90ebc |
| gfpo.md | 5.24 kB | | b811911c |
| gkd_trainer.html | 119 kB | | 4657ff2b |
| gkd_trainer.md | 14.1 kB | | 3c869a77 |
| gold_trainer.html | 166 kB | | 8477752e |
| gold_trainer.md | 18.1 kB | | 40d464e7 |
| grpo_trainer.html | 561 kB | | 249dce5a |
| grpo_trainer.md | 61.5 kB | | 243f0217 |
| grpo_with_replay_buffer.html | 90.3 kB | | febaeb30 |
| grpo_with_replay_buffer.md | 6.16 kB | | 5c5e4ccc |
| gspo_token.html | 50.2 kB | | 1a48924d |
| gspo_token.md | 4.27 kB | | ff2513e8 |
| index.html | 29 kB | | 2a735506 |
| index.md | 3.66 kB | | 0c94ab19 |
| installation.html | 13.9 kB | | 8edabdfe |
| installation.md | 721 Bytes | | 93a212e0 |
| jobs_training.html | 32.9 kB | | 40fc567a |
| jobs_training.md | 6.46 kB | | cb814663 |
| kernels_hub.html | 26.8 kB | | 0bbc5013 |
| kernels_hub.md | 4.18 kB | | 6982a1e3 |
| kto_trainer.html | 134 kB | | 8972411e |
| kto_trainer.md | 18.2 kB | | 2dc11e90 |
| liger_kernel_integration.html | 15 kB | | 589fec4e |
| liger_kernel_integration.md | 2.2 kB | | 0ab2ea33 |
| llms-full.txt | 949 kB | | 52bdbebf |
| llms.txt | 5.15 kB | | 32e389eb |
| lora_without_regret.html | 45 kB | | a78d147f |
| lora_without_regret.md | 14.4 kB | | c3be6b18 |
| merge_model_callback.html | 17.8 kB | | cfdc26b9 |
| merge_model_callback.md | 1.19 kB | | bca4f861 |
| minillm_trainer.html | 180 kB | | 687c1b4f |
| minillm_trainer.md | 16.4 kB | | b54c17f5 |
| nash_md_trainer.html | 125 kB | | 797726f5 |
| nash_md_trainer.md | 16.6 kB | | 2a61f4e1 |
| nemo_gym.html | 58.5 kB | | d956daca |
| nemo_gym.md | 10.3 kB | | 45caccd9 |
| objects.inv | 2.45 kB | | 52765ed1 |
| online_dpo_trainer.html | 180 kB | | 9d63934c |
| online_dpo_trainer.md | 23.3 kB | | 10f7a38b |
| openenv.html | 114 kB | | e206a42c |
| openenv.md | 27.8 kB | | f18424e6 |
| orpo_trainer.html | 128 kB | | 25696779 |
| orpo_trainer.md | 17.9 kB | | 8023a36e |
| paper_index.html | 742 kB | | 6c5b4019 |
| paper_index.md | 84 kB | | 56b70616 |
| papo_trainer.html | 112 kB | | eb10f16f |
| papo_trainer.md | 8.82 kB | | 39ef20d5 |
| peft_integration.html | 131 kB | | 64c6eeae |
| peft_integration.md | 23.9 kB | | 5093a535 |
| ppo_trainer.html | 279 kB | | 3fd312e3 |
| ppo_trainer.md | 41.5 kB | | cd7393fe |
| prm_trainer.html | 118 kB | | 365d47ef |
| prm_trainer.md | 14.2 kB | | 8a196434 |
| ptt_integration.html | 29.3 kB | | a93bc49d |
| ptt_integration.md | 4.27 kB | | 6a21357a |
| quickstart.html | 37.4 kB | | dabb055b |
| quickstart.md | 3.25 kB | | 1c4455a3 |
| rapidfire_integration.html | 95.4 kB | | 5715e645 |
| rapidfire_integration.md | 17.8 kB | | b0dd6d2b |
| reducing_memory_usage.html | 57 kB | | 029d22d0 |
| reducing_memory_usage.md | 13.7 kB | | ed64d344 |
|