| _app | | | 176 items |
| _toctree.yml | 3.29 kB | | 3ae9d845 |
| async_grpo_trainer.html | 108 kB | | ac076522 |
| async_grpo_trainer.md | 12.3 kB | | 31749614 |
| bco_trainer.html | 130 kB | | c2aca1ef |
| bco_trainer.md | 14.1 kB | | 19811872 |
| bema_for_reference_model.html | 90 kB | | 8fe77d78 |
| bema_for_reference_model.md | 7.18 kB | | f067c81b |
| callbacks.html | 95.8 kB | | d892c51f |
| callbacks.md | 7.88 kB | | 070fed7d |
| chat_template_utils.html | 45.7 kB | | dfc9d426 |
| chat_template_utils.md | 5.34 kB | | 19a1231b |
| clis.html | 53.4 kB | | db35e5c9 |
| clis.md | 12.8 kB | | 5e52c789 |
| community_tutorials.html | 31 kB | | 54ec7238 |
| community_tutorials.md | 11 kB | | 60b27778 |
| cpo_trainer.html | 144 kB | | 7aab1c1d |
| cpo_trainer.md | 23 kB | | 75b04247 |
| customization.html | 31 kB | | 885c214e |
| customization.md | 4.08 kB | | 935e7042 |
| data_utils.html | 62.9 kB | | 2867aa98 |
| data_utils.md | 6.32 kB | | d3766194 |
| dataset_formats.html | 223 kB | | f9c376bd |
| dataset_formats.md | 40.2 kB | | d2f184f1 |
| deepspeed_integration.html | 15.8 kB | | 19b7acc0 |
| deepspeed_integration.md | 1.48 kB | | 96460e48 |
| distillation_trainer.html | 160 kB | | c7283792 |
| distillation_trainer.md | 12.3 kB | | df0a3116 |
| distributing_training.html | 96.5 kB | | fa20338e |
| distributing_training.md | 21 kB | | 400cb97c |
| dpo_trainer.html | 232 kB | | 50540c33 |
| dpo_trainer.md | 30.8 kB | | 32101349 |
| example_overview.html | 42.8 kB | | a7be2aef |
| example_overview.md | 19.7 kB | | 2322b821 |
| experimental_overview.html | 10.8 kB | | 67fc52c2 |
| experimental_overview.md | 1.6 kB | | d2f8cf27 |
| favicon.png | 1.57 kB | | 6e06dd7b |
| gfpo.html | 84.4 kB | | 8957a80e |
| gfpo.md | 5.24 kB | | 07e5ce82 |
| gkd_trainer.html | 119 kB | | 45406133 |
| gkd_trainer.md | 14.1 kB | | 2a71bc73 |
| gold_trainer.html | 166 kB | | 8fb8191d |
| gold_trainer.md | 18.1 kB | | bf6e351c |
| grpo_trainer.html | 560 kB | | 383ff177 |
| grpo_trainer.md | 55.4 kB | | ba286a8f |
| grpo_with_replay_buffer.html | 89.6 kB | | 6f7248a3 |
| grpo_with_replay_buffer.md | 6.16 kB | | 3fc55b97 |
| gspo_token.html | 50.2 kB | | 48df1070 |
| gspo_token.md | 4.27 kB | | e48b5031 |
| index.html | 29 kB | | 38a46228 |
| index.md | 3.66 kB | | 0c94ab19 |
| installation.html | 13.9 kB | | 0fdea22c |
| installation.md | 721 Bytes | | 93a212e0 |
| jobs_training.html | 32.9 kB | | 7bbf8c3a |
| jobs_training.md | 6.44 kB | | 7e612e1d |
| kernels_hub.html | 26.8 kB | | 070e2ae4 |
| kernels_hub.md | 4.18 kB | | 6982a1e3 |
| kto_trainer.html | 137 kB | | 3930b98e |
| kto_trainer.md | 18.1 kB | | 11cacbd8 |
| liger_kernel_integration.html | 15 kB | | 15ad2e73 |
| liger_kernel_integration.md | 2.2 kB | | 0ab2ea33 |
| llms-full.txt | 836 kB | | 1e6af3cb |
| llms.txt | 5 kB | | 888086bd |
| lora_without_regret.html | 45 kB | | f27c1317 |
| lora_without_regret.md | 14.4 kB | | c3be6b18 |
| merge_model_callback.html | 17.8 kB | | 264637ab |
| merge_model_callback.md | 1.19 kB | | 57fefb59 |
| minillm_trainer.html | 179 kB | | 0cd19ec1 |
| minillm_trainer.md | 16.4 kB | | 3f91e7e6 |
| nash_md_trainer.html | 124 kB | | a827f336 |
| nash_md_trainer.md | 16.3 kB | | a89289f8 |
| nemo_gym.html | 58.5 kB | | 3d37725d |
| nemo_gym.md | 10.3 kB | | b5b12cc0 |
| objects.inv | 2.41 kB | | 1bbeff72 |
| online_dpo_trainer.html | 179 kB | | d98600d5 |
| online_dpo_trainer.md | 23.1 kB | | 68a35165 |
| openenv.html | 114 kB | | cb23236c |
| openenv.md | 27.8 kB | | ee4d8a48 |
| orpo_trainer.html | 127 kB | | 2b2221a3 |
| orpo_trainer.md | 17.7 kB | | 1f42377d |
| paper_index.html | 734 kB | | 9517da1a |
| paper_index.md | 19.1 kB | | b00cb931 |
| papo_trainer.html | 111 kB | | 72b425e4 |
| papo_trainer.md | 8.82 kB | | b3d1ec8b |
| peft_integration.html | 131 kB | | 5ce2e424 |
| peft_integration.md | 23.9 kB | | 6c309a22 |
| ppo_trainer.html | 278 kB | | 34481129 |
| ppo_trainer.md | 41.4 kB | | a0757bf3 |
| prm_trainer.html | 117 kB | | 2a550f57 |
| prm_trainer.md | 13.9 kB | | 31077c34 |
| ptt_integration.html | 29.3 kB | | 3b581696 |
| ptt_integration.md | 4.27 kB | | 6a21357a |
| quickstart.html | 37.4 kB | | a832d705 |
| quickstart.md | 3.25 kB | | 1c4455a3 |
| rapidfire_integration.html | 81.1 kB | | 18eb0c81 |
| rapidfire_integration.md | 12.8 kB | | 78b07e81 |
| reducing_memory_usage.html | 52.4 kB | | 452a1beb |
| reducing_memory_usage.md | 12.3 kB | | d61af82e |
| reward_trainer.html | 175 kB | | df1bd82a |
| reward_trainer.md | 21.5 kB | | dc929981 |
|