open-instruct/docs/algorithms at main - open-instruct - Hanzo Git

hanzoai/open-instruct

mirror of https://github.com/hanzoai/open-instruct.git synced 2026-10-30 18:26:32 +00:00

Files

T

History

Costa Huang e32a1e4704 quick add

2025-02-06 09:22:07 -08:00

..

grpo_8b.png

quick add

2025-02-06 09:22:07 -08:00

grpo.md

Add optional r1-style thinking reward (#551 )

2025-02-06 12:21:39 -05:00

online_dpo.md

Fix dataset mixing logic (#415 )

2024-11-05 15:01:06 -05:00

ppo.md

Ground-Truth RL (#377 )

2024-11-20 12:30:24 -05:00

rejection_sampling.md

Synthetic preference dataset (#332 )

2024-10-02 14:39:21 -04:00

reward_modeling_colored_tokens.png

add reward training script (#217 )

2024-08-09 09:19:49 -07:00

reward_modeling_ds.png

add reward training script (#217 )

2024-08-09 09:19:49 -07:00

reward_modeling_hf_repo.png

add reward training script (#217 )

2024-08-09 09:19:49 -07:00

reward_modeling_hf_viz.png

add reward training script (#217 )

2024-08-09 09:19:49 -07:00

reward_modeling_preference_sample_texts.png

add reward training script (#217 )

2024-08-09 09:19:49 -07:00

reward_modeling_token_wandb.png

add reward training script (#217 )

2024-08-09 09:19:49 -07:00

reward_modeling_token.png

add reward training script (#217 )

2024-08-09 09:19:49 -07:00

reward_modeling.md

Fix dataset mixing logic (#415 )

2024-11-05 15:01:06 -05:00

synthetic_preference_dataset.md

Synthetic preference dataset (#332 )

2024-10-02 14:39:21 -04:00

synthetic_preference_dataset.png

Synthetic preference dataset (#332 )

2024-10-02 14:39:21 -04:00