| _app | | | 202 items |
| _toctree.yml | 3.38 kB | | 9da8f3eb |
| async_grpo_trainer.html | 108 kB | | 3a16f7c4 |
| async_grpo_trainer.md | 12.3 kB | | 3b344fe1 |
| bco_trainer.html | 130 kB | | 4b61319c |
| bco_trainer.md | 14.2 kB | | 4fad9657 |
| bema_for_reference_model.html | 90 kB | | 3d1a3466 |
| bema_for_reference_model.md | 7.18 kB | | c818a2a6 |
| callbacks.html | 95.8 kB | | 5b04dcea |
| callbacks.md | 7.88 kB | | 946cdf8a |
| chat_template_utils.html | 46.2 kB | | 8e6495f9 |
| chat_template_utils.md | 5.8 kB | | 5addc5b4 |
| chat_templates.html | 42.6 kB | | 07429635 |
| chat_templates.md | 8.22 kB | | aedd53ea |
| clis.html | 53.4 kB | | 5f5b92e2 |
| clis.md | 12.8 kB | | 515c3003 |
| community_tutorials.html | 31 kB | | 93b38ce9 |
| community_tutorials.md | 11 kB | | 11074e8b |
| cpo_trainer.html | 145 kB | | ef3020ed |
| cpo_trainer.md | 23.2 kB | | 1f619e4b |
| customization.html | 31 kB | | 069c4ea3 |
| customization.md | 4.08 kB | | d642e4b9 |
| data_utils.html | 62.7 kB | | 4329de3f |
| data_utils.md | 6.87 kB | | 52fac260 |
| dataset_formats.html | 223 kB | | 71a561ec |
| dataset_formats.md | 43 kB | | d95a9b17 |
| deepspeed_integration.html | 15.8 kB | | 8ef43a1a |
| deepspeed_integration.md | 1.52 kB | | e5b0fad5 |
| distillation_trainer.html | 161 kB | | e081408d |
| distillation_trainer.md | 12.3 kB | | d9164134 |
| distributing_training.html | 96.5 kB | | 4e644276 |
| distributing_training.md | 21 kB | | 75949925 |
| dpo_trainer.html | 233 kB | | e4135059 |
| dpo_trainer.md | 30.9 kB | | cd19ded3 |
| example_overview.html | 42.7 kB | | 7c3be954 |
| example_overview.md | 19.7 kB | | 4455cdd5 |
| experimental_overview.html | 10.8 kB | | aacff4d9 |
| experimental_overview.md | 1.62 kB | | 45d90cc6 |
| favicon.png | 1.57 kB | | 6e06dd7b |
| gfpo.html | 85 kB | | f11d6ec9 |
| gfpo.md | 5.24 kB | | 00a29b80 |
| gkd_trainer.html | 119 kB | | 2ba94505 |
| gkd_trainer.md | 14.1 kB | | 7413b5a4 |
| gold_trainer.html | 166 kB | | 95ae3fa5 |
| gold_trainer.md | 18.1 kB | | 05677269 |
| grpo_trainer.html | 561 kB | | 7bb90d7d |
| grpo_trainer.md | 61.5 kB | | 26d55ca3 |
| grpo_with_replay_buffer.html | 90.3 kB | | 5b5a66bc |
| grpo_with_replay_buffer.md | 6.16 kB | | 62a0434a |
| gspo_token.html | 50.2 kB | | 5c6c4ef5 |
| gspo_token.md | 4.27 kB | | 5ef3125b |
| index.html | 29 kB | | 8f8eaa98 |
| index.md | 3.66 kB | | 0c94ab19 |
| installation.html | 13.9 kB | | 9f2d0155 |
| installation.md | 721 Bytes | | 93a212e0 |
| jobs_training.html | 32.9 kB | | ebc90bfb |
| jobs_training.md | 6.46 kB | | cb814663 |
| kernels_hub.html | 26.8 kB | | 1e13835f |
| kernels_hub.md | 4.18 kB | | 6982a1e3 |
| kto_trainer.html | 134 kB | | 9fee2aab |
| kto_trainer.md | 18.2 kB | | e194ad36 |
| liger_kernel_integration.html | 15 kB | | 8380c1c6 |
| liger_kernel_integration.md | 2.2 kB | | 0ab2ea33 |
| llms-full.txt | 948 kB | | 74255f2a |
| llms.txt | 5.15 kB | | 5f3247ba |
| lora_without_regret.html | 45 kB | | ac7401ae |
| lora_without_regret.md | 14.4 kB | | c3be6b18 |
| merge_model_callback.html | 17.8 kB | | 29ec1c59 |
| merge_model_callback.md | 1.19 kB | | 48ea59ae |
| minillm_trainer.html | 180 kB | | 660691e9 |
| minillm_trainer.md | 16.4 kB | | 408345f6 |
| nash_md_trainer.html | 125 kB | | 07155bd9 |
| nash_md_trainer.md | 16.6 kB | | 89df2aac |
| nemo_gym.html | 58.5 kB | | 25809291 |
| nemo_gym.md | 10.3 kB | | 45caccd9 |
| objects.inv | 2.45 kB | | b0708be5 |
| online_dpo_trainer.html | 180 kB | | 1fb71ace |
| online_dpo_trainer.md | 23.3 kB | | 33ebff5b |
| openenv.html | 114 kB | | a14347b2 |
| openenv.md | 27.8 kB | | 8539e38f |
| orpo_trainer.html | 128 kB | | 4574bddf |
| orpo_trainer.md | 17.9 kB | | 0aa4e12f |
| paper_index.html | 742 kB | | d0350f58 |
| paper_index.md | 84 kB | | aa0db811 |
| papo_trainer.html | 112 kB | | 10062d4c |
| papo_trainer.md | 8.82 kB | | 438ba655 |
| peft_integration.html | 131 kB | | 42999b31 |
| peft_integration.md | 23.9 kB | | dbb8fb12 |
| ppo_trainer.html | 279 kB | | f6458f95 |
| ppo_trainer.md | 41.5 kB | | a4666ce1 |
| prm_trainer.html | 118 kB | | e2cba640 |
| prm_trainer.md | 14.2 kB | | 4f6b4106 |
| ptt_integration.html | 29.3 kB | | 4ef7c6bd |
| ptt_integration.md | 4.27 kB | | 6a21357a |
| quickstart.html | 37.4 kB | | f761cf98 |
| quickstart.md | 3.25 kB | | 1c4455a3 |
| rapidfire_integration.html | 95.4 kB | | 2ed052bd |
| rapidfire_integration.md | 17.8 kB | | b0dd6d2b |
| reducing_memory_usage.html | 57.1 kB | | e32ec3ac |
| reducing_memory_usage.md | 13.7 kB | | dca8b991 |
|