Buckets:
| - sections: | |
| - local: index | |
| title: TRL | |
| - local: installation | |
| title: Installation | |
| - local: quickstart | |
| title: Quickstart | |
| - local: usage_stats | |
| title: Usage Stats Collection | |
| title: Getting started | |
| - sections: | |
| - local: chat_templates | |
| title: Chat Templates | |
| - local: dataset_formats | |
| title: Dataset Formats | |
| - local: paper_index | |
| title: Paper Index | |
| title: Conceptual Guides | |
| - sections: # Sorted alphabetically | |
| - local: distillation_trainer | |
| title: Distillation | |
| - local: dpo_trainer | |
| title: DPO | |
| - local: grpo_trainer | |
| title: GRPO | |
| - local: kto_trainer | |
| title: KTO | |
| - local: reward_trainer | |
| title: Reward | |
| - local: rloo_trainer | |
| title: RLOO | |
| - local: sft_trainer | |
| title: SFT | |
| title: Trainers | |
| - sections: | |
| - local: clis | |
| title: Command Line Interface (CLI) | |
| - local: jobs_training | |
| title: Training using Jobs | |
| - local: customization | |
| title: Customizing the Training | |
| - local: reducing_memory_usage | |
| title: Reducing Memory Usage | |
| - local: speeding_up_training | |
| title: Speeding Up Training | |
| - local: distributing_training | |
| title: Distributing Training | |
| - local: aws_trainium | |
| title: Training on AWS Trainium | |
| - local: amd_gpus | |
| title: Training on AMD GPUs | |
| - local: long_context_training | |
| title: Training Beyond 1M Tokens | |
| - local: use_model | |
| title: Using Trained Models | |
| title: How-to guides | |
| - sections: | |
| - local: deepspeed_integration | |
| title: DeepSpeed | |
| - local: harbor | |
| title: Harbor | |
| - local: kernels_hub | |
| title: Kernels Hub | |
| - local: openenv | |
| title: OpenEnv | |
| - local: openreward | |
| title: OpenReward | |
| - local: peft_integration | |
| title: PEFT | |
| - local: rapidfire_integration | |
| title: RapidFire AI | |
| - local: trackio_integration | |
| title: Trackio | |
| - local: unsloth_integration | |
| title: Unsloth | |
| - local: vllm_integration | |
| title: vLLM | |
| title: Integrations | |
| - sections: | |
| - local: example_overview | |
| title: Example Overview | |
| - local: community_tutorials | |
| title: Community Tutorials | |
| - local: lora_without_regret | |
| title: LoRA Without Regret | |
| title: Examples | |
| - sections: | |
| - sections: | |
| - local: chat_template_utils | |
| title: Chat Template Utilities | |
| - local: data_utils | |
| title: Data Utilities | |
| - local: script_utils | |
| title: Script Utilities | |
| title: Utilities | |
| - local: callbacks | |
| title: Callbacks | |
| - local: rewards | |
| title: Reward Functions | |
| title: API | |
| - sections: | |
| - local: experimental_overview | |
| title: Experimental Overview | |
| - local: a2po_trainer # Sorted alphabetically | |
| title: A2PO | |
| - local: async_distillation_trainer | |
| title: Async Distillation | |
| - local: async_grpo_trainer | |
| title: Asynchronous GRPO | |
| - local: bema_for_reference_model | |
| title: BEMA for Reference Model | |
| - local: cpo_trainer | |
| title: CPO | |
| - local: gkd_trainer | |
| title: GKD | |
| - local: gmpo | |
| title: GMPO | |
| - local: gold_trainer | |
| title: GOLD | |
| - local: iw_opd_trainer | |
| title: IW-OPD | |
| - local: merge_model_callback | |
| title: MergeModelCallback | |
| - local: online_dpo_trainer | |
| title: Online DPO | |
| - local: orpo_trainer | |
| title: ORPO | |
| - local: sdft_trainer | |
| title: SDFT | |
| - local: sdpo_trainer | |
| title: SDPO | |
| title: Experimental | |
| isExpanded: false | |
Xet Storage Details
- Size:
- 3.24 kB
- Xet hash:
- ab071b19af6f135cef91b8f3ef5f8a0b00b187092c125890018573c6d637a561
·
Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.