| _app | | | 141 items |
| _toctree.yml | 3.29 kB | | 3ae9d845 |
| async_grpo_trainer.html | 108 kB | | c166f60c |
| async_grpo_trainer.md | 12.3 kB | | 8ca8b1aa |
| bco_trainer.html | 130 kB | | 488e73d9 |
| bco_trainer.md | 14.1 kB | | 7f358a94 |
| bema_for_reference_model.html | 90 kB | | 1bd38c5f |
| bema_for_reference_model.md | 7.18 kB | | e6714da8 |
| callbacks.html | 95.8 kB | | c9d5a969 |
| callbacks.md | 7.88 kB | | c0420d88 |
| chat_template_utils.html | 45.7 kB | | 38bd2595 |
| chat_template_utils.md | 5.34 kB | | 2434c10c |
| clis.html | 53.4 kB | | 5aae63c9 |
| clis.md | 12.8 kB | | 5b948c37 |
| community_tutorials.html | 31 kB | | 70817510 |
| community_tutorials.md | 11 kB | | 2e8b3502 |
| cpo_trainer.html | 144 kB | | 2b680fba |
| cpo_trainer.md | 23 kB | | 3d9b28b4 |
| customization.html | 31 kB | | 573089e7 |
| customization.md | 4.08 kB | | ebd75ac2 |
| data_utils.html | 62.9 kB | | 086d818d |
| data_utils.md | 6.32 kB | | ff8601e9 |
| dataset_formats.html | 223 kB | | 551e0f18 |
| dataset_formats.md | 40.2 kB | | 3ec85e3b |
| deepspeed_integration.html | 15.8 kB | | cae52668 |
| deepspeed_integration.md | 1.48 kB | | 96460e48 |
| distillation_trainer.html | 160 kB | | 14aa3116 |
| distillation_trainer.md | 12.3 kB | | 1113fccc |
| distributing_training.html | 96.5 kB | | fd30aceb |
| distributing_training.md | 21 kB | | 400cb97c |
| dpo_trainer.html | 232 kB | | 2663b27f |
| dpo_trainer.md | 30.8 kB | | 69873b2d |
| example_overview.html | 42.7 kB | | 22c910b8 |
| example_overview.md | 19.7 kB | | 1949ea77 |
| experimental_overview.html | 10.8 kB | | 68af5b77 |
| experimental_overview.md | 1.6 kB | | d2f8cf27 |
| favicon.png | 1.57 kB | | 6e06dd7b |
| gfpo.html | 84.4 kB | | f3a47fe9 |
| gfpo.md | 5.24 kB | | b3868304 |
| gkd_trainer.html | 119 kB | | b84da936 |
| gkd_trainer.md | 14.1 kB | | d37539ae |
| gold_trainer.html | 166 kB | | e01902a1 |
| gold_trainer.md | 18.1 kB | | dd3684a2 |
| grpo_trainer.html | 560 kB | | 94a67fd7 |
| grpo_trainer.md | 55.4 kB | | 4f85fe5a |
| grpo_with_replay_buffer.html | 89.6 kB | | f3c7d32b |
| grpo_with_replay_buffer.md | 6.16 kB | | ec3b85e1 |
| gspo_token.html | 50.2 kB | | 343eb65b |
| gspo_token.md | 4.27 kB | | 4c1d836c |
| index.html | 29 kB | | e50b6a7a |
| index.md | 3.66 kB | | 0c94ab19 |
| installation.html | 13.9 kB | | 8908dd86 |
| installation.md | 721 Bytes | | 93a212e0 |
| jobs_training.html | 32.9 kB | | e102180b |
| jobs_training.md | 6.44 kB | | 7e612e1d |
| kernels_hub.html | 26.8 kB | | fb463976 |
| kernels_hub.md | 4.18 kB | | 6982a1e3 |
| kto_trainer.html | 137 kB | | 711677aa |
| kto_trainer.md | 18.1 kB | | fa252a6d |
| liger_kernel_integration.html | 15 kB | | 018a5b0b |
| liger_kernel_integration.md | 2.2 kB | | 0ab2ea33 |
| llms-full.txt | 836 kB | | ab4ca0b1 |
| llms.txt | 5 kB | | ac8f8d47 |
| lora_without_regret.html | 45 kB | | 0032b8f8 |
| lora_without_regret.md | 14.4 kB | | c3be6b18 |
| merge_model_callback.html | 17.8 kB | | f7443ddd |
| merge_model_callback.md | 1.19 kB | | d6a2403e |
| minillm_trainer.html | 179 kB | | 7e908b9c |
| minillm_trainer.md | 16.4 kB | | 1be184dd |
| nash_md_trainer.html | 124 kB | | 2164d4a6 |
| nash_md_trainer.md | 16.3 kB | | 44207149 |
| nemo_gym.html | 58.5 kB | | 25bf4191 |
| nemo_gym.md | 10.3 kB | | b5b12cc0 |
| objects.inv | 2.41 kB | | 9a05e76c |
| online_dpo_trainer.html | 179 kB | | 61d4f9af |
| online_dpo_trainer.md | 23.1 kB | | fecdc0b1 |
| openenv.html | 114 kB | | 1ec88ddd |
| openenv.md | 27.8 kB | | f4981bf7 |
| orpo_trainer.html | 127 kB | | 449799dc |
| orpo_trainer.md | 17.7 kB | | ff57e9d1 |
| paper_index.html | 734 kB | | 259deb6a |
| paper_index.md | 19.1 kB | | 4ba197c4 |
| papo_trainer.html | 111 kB | | 51eb6631 |
| papo_trainer.md | 8.82 kB | | 5827d95f |
| peft_integration.html | 131 kB | | fabd4c1a |
| peft_integration.md | 23.9 kB | | d0227e30 |
| ppo_trainer.html | 278 kB | | 6091adf4 |
| ppo_trainer.md | 41.4 kB | | ac24f412 |
| prm_trainer.html | 117 kB | | 03ab4897 |
| prm_trainer.md | 13.9 kB | | ad30fe4d |
| ptt_integration.html | 29.3 kB | | 6ca50ed7 |
| ptt_integration.md | 4.27 kB | | 6a21357a |
| quickstart.html | 37.4 kB | | 08ba725d |
| quickstart.md | 3.25 kB | | 1c4455a3 |
| rapidfire_integration.html | 81.1 kB | | 8dc12d41 |
| rapidfire_integration.md | 12.8 kB | | 78b07e81 |
| reducing_memory_usage.html | 52.4 kB | | 079081bd |
| reducing_memory_usage.md | 12.3 kB | | d61af82e |
| reward_trainer.html | 175 kB | | 63aaf8b6 |
| reward_trainer.md | 21.5 kB | | 2c13fbb3 |
|