| _app | | | 250 items |
| _toctree.yml | 3.35 kB | | ac839051 |
| async_grpo_trainer.html | 108 kB | | 2dedfa2b |
| async_grpo_trainer.md | 12.3 kB | | c895522d |
| bco_trainer.html | 130 kB | | 0d389d0b |
| bco_trainer.md | 14.1 kB | | 019aaeb7 |
| bema_for_reference_model.html | 90 kB | | f93f3869 |
| bema_for_reference_model.md | 7.18 kB | | 6bfa5473 |
| callbacks.html | 95.8 kB | | c57f491c |
| callbacks.md | 7.88 kB | | 5018a9da |
| chat_template_utils.html | 45.8 kB | | e00faaec |
| chat_template_utils.md | 5.48 kB | | e34105c5 |
| chat_templates.html | 28.3 kB | | 30392ba8 |
| chat_templates.md | 5.13 kB | | d4eebe33 |
| clis.html | 53.4 kB | | 4bb7bc37 |
| clis.md | 12.8 kB | | 36d391fa |
| community_tutorials.html | 31 kB | | 52251fb3 |
| community_tutorials.md | 11 kB | | 9a915da6 |
| cpo_trainer.html | 144 kB | | 52035e42 |
| cpo_trainer.md | 23 kB | | cc4b34d0 |
| customization.html | 31 kB | | 58355523 |
| customization.md | 4.08 kB | | 12ad9c2a |
| data_utils.html | 62.9 kB | | 25f644a5 |
| data_utils.md | 6.32 kB | | 762b29c8 |
| dataset_formats.html | 223 kB | | 6d58950d |
| dataset_formats.md | 40.2 kB | | cd481d4d |
| deepspeed_integration.html | 15.8 kB | | a0260d15 |
| deepspeed_integration.md | 1.48 kB | | 96460e48 |
| distillation_trainer.html | 160 kB | | c8c0cd84 |
| distillation_trainer.md | 12.3 kB | | b6c8022e |
| distributing_training.html | 96.5 kB | | c640e0d8 |
| distributing_training.md | 21 kB | | 400cb97c |
| dpo_trainer.html | 232 kB | | 9dfa0e83 |
| dpo_trainer.md | 30.8 kB | | f5f286f7 |
| example_overview.html | 42.8 kB | | eade6642 |
| example_overview.md | 19.7 kB | | 7400e420 |
| experimental_overview.html | 10.8 kB | | 0635e511 |
| experimental_overview.md | 1.6 kB | | d2f8cf27 |
| favicon.png | 1.57 kB | | 6e06dd7b |
| gfpo.html | 84.4 kB | | 6c51d93b |
| gfpo.md | 5.24 kB | | 26fecb53 |
| gkd_trainer.html | 119 kB | | 439212a3 |
| gkd_trainer.md | 14.1 kB | | b9d47274 |
| gold_trainer.html | 166 kB | | 0d061910 |
| gold_trainer.md | 18.1 kB | | 9aef9ff1 |
| grpo_trainer.html | 560 kB | | f21fe288 |
| grpo_trainer.md | 55.8 kB | | f594ff2f |
| grpo_with_replay_buffer.html | 89.6 kB | | 3cf9368a |
| grpo_with_replay_buffer.md | 6.16 kB | | 78bab9c7 |
| gspo_token.html | 50.2 kB | | df87eb7f |
| gspo_token.md | 4.27 kB | | 80c4db13 |
| index.html | 29 kB | | cf6b7211 |
| index.md | 3.66 kB | | 0c94ab19 |
| installation.html | 13.9 kB | | fa394681 |
| installation.md | 721 Bytes | | 93a212e0 |
| jobs_training.html | 32.9 kB | | 883fe594 |
| jobs_training.md | 6.44 kB | | 7e612e1d |
| kernels_hub.html | 26.8 kB | | 7d4b6afc |
| kernels_hub.md | 4.18 kB | | 6982a1e3 |
| kto_trainer.html | 137 kB | | d819691d |
| kto_trainer.md | 18.1 kB | | 501dc511 |
| liger_kernel_integration.html | 15 kB | | 33cbf763 |
| liger_kernel_integration.md | 2.2 kB | | 0ab2ea33 |
| llms-full.txt | 842 kB | | f549822c |
| llms.txt | 5.08 kB | | 4fe59d4c |
| lora_without_regret.html | 45 kB | | 261cb1c2 |
| lora_without_regret.md | 14.4 kB | | c3be6b18 |
| merge_model_callback.html | 17.8 kB | | 2ecdc435 |
| merge_model_callback.md | 1.19 kB | | d0b0e799 |
| minillm_trainer.html | 179 kB | | 46da998a |
| minillm_trainer.md | 16.4 kB | | dc16423e |
| nash_md_trainer.html | 124 kB | | 50f575b7 |
| nash_md_trainer.md | 16.3 kB | | 7dcfa35c |
| nemo_gym.html | 58.5 kB | | 8c5f74a0 |
| nemo_gym.md | 10.3 kB | | b5b12cc0 |
| objects.inv | 2.41 kB | | 301d23c2 |
| online_dpo_trainer.html | 179 kB | | 089d2050 |
| online_dpo_trainer.md | 23.1 kB | | 94b1b1fa |
| openenv.html | 114 kB | | f8aeb722 |
| openenv.md | 27.8 kB | | c6e4e2c5 |
| orpo_trainer.html | 127 kB | | ac45beb2 |
| orpo_trainer.md | 17.7 kB | | 16d9e476 |
| paper_index.html | 734 kB | | 6195d0a1 |
| paper_index.md | 19.1 kB | | 5ce567d8 |
| papo_trainer.html | 111 kB | | 89930dba |
| papo_trainer.md | 8.82 kB | | 78087ff2 |
| peft_integration.html | 131 kB | | eaa013b8 |
| peft_integration.md | 23.9 kB | | f9152648 |
| ppo_trainer.html | 278 kB | | 076307e8 |
| ppo_trainer.md | 41.4 kB | | c0344882 |
| prm_trainer.html | 117 kB | | 7798bafc |
| prm_trainer.md | 13.9 kB | | f4327a79 |
| ptt_integration.html | 29.3 kB | | 9fbaacfa |
| ptt_integration.md | 4.27 kB | | 6a21357a |
| quickstart.html | 37.4 kB | | 163c6dd7 |
| quickstart.md | 3.25 kB | | 1c4455a3 |
| rapidfire_integration.html | 81.1 kB | | 14b8f4d8 |
| rapidfire_integration.md | 12.8 kB | | 78b07e81 |
| reducing_memory_usage.html | 52.4 kB | | 2e13df46 |
| reducing_memory_usage.md | 12.3 kB | | d61af82e |
|