Kashif Rasul 1b799a23c1 🥓 [docs] add CP docs (#3994) ...

Co-authored-by: Quentin Gallouédec <45557362+qgallouedec@users.noreply.github.com>
Co-authored-by: lewtun <lewis.c.tunstall@gmail.com>
Co-authored-by: Sergio Paniego Blanco <sergiopaniegoblanco@gmail.com>
Co-authored-by: Quentin Gallouédec <gallouedec.quentin@gmail.com>

2025-09-08 21:46:22 -06:00

..

_toctree.yml

👷 Added Kernels on the Hub x TRL guide (#3969)

2025-09-04 15:37:02 +02:00

alignprop_trainer.md

Add autodoc for AlignPropTrainer and AlignPropConfig (#4033)

2025-09-08 20:13:23 +02:00

bco_trainer.md

🗿 [CPO] Add AlphaPO method via CPOTrainer (#3824)

2025-08-16 23:26:02 -07:00

best_of_n.md

📖 Docs fix spelling issues (#2682)

2025-01-30 09:42:14 +01:00

callbacks.md

🎢 [Callbacks] BEMA (#3855)

2025-08-14 13:54:52 -07:00

clis.md

🔥 [Refactor] RLOOTrainer (#3801)

2025-08-29 09:27:28 -06:00

community_tutorials.md

Add 'Post training a VLM for reasoning with GRPO using TRL' recipe to Community tutorials (#3843)

2025-08-04 18:46:53 +02:00

cpo_trainer.md

🗿 [CPO] Add AlphaPO method via CPOTrainer (#3824)

2025-08-16 23:26:02 -07:00

customization.md

Fixed some typos and added small details about trackio to docs (#3965)

2025-08-27 17:57:19 +02:00

data_utils.md

♻️ Reuse multimodal message preparation from SFTTrainer in GRPOTrainer (#3919)

2025-08-20 10:04:54 -07:00

dataset_formats.md

🔥 [Refactor] RLOOTrainer (#3801)

2025-08-29 09:27:28 -06:00

ddpo_trainer.md

🖊 Fix typos (#2673)

2025-01-28 11:26:36 +01:00

deepspeed_integration.md

🚀 DeepSpeed integration documentation (#2993)

2025-03-03 14:51:45 +01:00

detoxifying_a_lm.md

📏 torch_dype to dtype everywhere (#4000)

2025-09-03 15:45:37 -06:00

distributing_training.md

Fixed some typos and added small details about trackio to docs (#3965)

2025-08-27 17:57:19 +02:00

dpo_trainer.md

📏 torch_dype to dtype everywhere (#4000)

2025-09-03 15:45:37 -06:00

example_overview.md

⚖️ Add vLLM server mode and VLM support to OnlineDPOTrainer (#3783)

2025-09-05 16:58:49 -06:00

gkd_trainer.md

Improve trainer doc (#3818)

2025-08-01 11:14:16 +02:00

grpo_trainer.md

[doc] Paper index for Truncated Importance Sampling (#4026)

2025-09-08 08:11:08 +02:00

how_to_train.md

Fixed some typos and added small details about trackio to docs (#3965)

2025-08-27 17:57:19 +02:00

index.md

👁️ VLM blog (#3899)

2025-08-14 17:09:16 -07:00

installation.md

Fixed some typos and added small details about trackio to docs (#3965)

2025-08-27 17:57:19 +02:00

iterative_sft_trainer.md

📏 torch_dype to dtype everywhere (#4000)

2025-09-03 15:45:37 -06:00

jobs_training.md

Add HF jobs tag when creating model card via jobs (#3956)

2025-08-27 12:18:05 +02:00

judges.md

👋 Drop MDX (#2611)

2025-01-23 13:38:15 +01:00

kernels_hub.md

👷 Added Kernels on the Hub x TRL guide (#3969)

2025-09-04 15:37:02 +02:00

kto_trainer.md

🗿 [CPO] Add AlphaPO method via CPOTrainer (#3824)

2025-08-16 23:26:02 -07:00

liger_kernel_integration.md

🌺 OpenAI GPT OSS & Harmony support (#3848)

2025-08-05 09:44:59 -07:00

logging.md

Fixed some typos and added small details about trackio to docs (#3965)

2025-08-27 17:57:19 +02:00

model_utils.md

💬 Fix setup_chat_format and add clone_chat_template (#3404)

2025-06-15 15:59:42 +02:00

models.md

👋 Drop MDX (#2611)

2025-01-23 13:38:15 +01:00

multi_adapter_rl.md

👋 Drop MDX (#2611)

2025-01-23 13:38:15 +01:00

nash_md_trainer.md

⚖️ Add vLLM server mode and VLM support to OnlineDPOTrainer (#3783)

2025-09-05 16:58:49 -06:00

online_dpo_trainer.md

⚖️ Add vLLM server mode and VLM support to OnlineDPOTrainer (#3783)

2025-09-05 16:58:49 -06:00

orpo_trainer.md

🗿 [CPO] Add AlphaPO method via CPOTrainer (#3824)

2025-08-16 23:26:02 -07:00

others.md

🪪 Adds a more fine-grained profiling context (#2975)

2025-02-27 21:58:39 +01:00

paper_index.md

[doc] Group paper index by trainer (#4027)

2025-09-08 18:03:48 +02:00

peft_integration.md

Fixed some typos and added small details about trackio to docs (#3965)

2025-08-27 17:57:19 +02:00

ppo_trainer.md

Improve trainer doc (#3818)

2025-08-01 11:14:16 +02:00

prm_trainer.md

Improve trainer doc (#3818)

2025-08-01 11:14:16 +02:00

quickstart.md

Fix typo in GRPO quickstart (#4020)

2025-09-06 10:31:09 +02:00

reducing_memory_usage.md

🥓 [docs] add CP docs (#3994)

2025-09-08 21:46:22 -06:00

reward_trainer.md

Improve trainer doc (#3818)

2025-08-01 11:14:16 +02:00

rewards.md

🔥 [Refactor] RLOOTrainer (#3801)

2025-08-29 09:27:28 -06:00

rloo_trainer.md

🔥 [Refactor] RLOOTrainer (#3801)

2025-08-29 09:27:28 -06:00

script_utils.md

🎚️ Add dataset mixer (#3791)

2025-08-11 20:14:50 -07:00

sentiment_tuning.md

Fixed some typos and added small details about trackio to docs (#3965)

2025-08-27 17:57:19 +02:00

sft_trainer.md

📏 torch_dype to dtype everywhere (#4000)

2025-09-03 15:45:37 -06:00

speeding_up_training.md

🔥 [Refactor] RLOOTrainer (#3801)

2025-08-29 09:27:28 -06:00

trackio_integration.md

🎯 Add Trackio integration documentation and update TOC (#3971)

2025-09-02 13:06:06 -06:00

unsloth_integration.md

🦥 Unsloth Docs update (#3955)

2025-08-26 20:17:21 -07:00

use_model.md

Fixed some typos and added small details about trackio to docs (#3965)

2025-08-27 17:57:19 +02:00

using_llama_models.md

Fixed some typos and added small details about trackio to docs (#3965)

2025-08-27 17:57:19 +02:00

vllm_integration.md

Add vLLM transformers backend to online methods (#3773)

2025-07-30 18:24:50 +02:00

xpo_trainer.md

⚖️ Add vLLM server mode and VLM support to OnlineDPOTrainer (#3783)

2025-09-05 16:58:49 -06:00