s

august66 's models 19

Sort:  Recently updated

august66/hh_qwen1.5_IS_CLIP_small_clip_v2

2B • Updated Mar 8 • 2

august66/hh_qwen1.5_IS_CLIP_small_clip

2B • Updated Mar 8

august66/hh_qwen1.5_drpo_gated_fixed_beta

2B • Updated Mar 7

august66/hh_qwen1.5_DM_2e-6

2B • Updated Mar 6

august66/hh_qwen1.5_drpo_laplace_fixed_beta

2B • Updated Mar 5 • 1

august66/hh_qwen1.5_IS_KL_Laplace

2B • Updated Mar 4

august66/hh_qwen_1.5b_sft_dpo_generation

Text Generation • 2B • Updated Mar 3 • 4

august66/hh_qwen1.5_IS_KL

2B • Updated Feb 26 • 1

august66/hh_qwen1.5_drpo_fixed_beta

2B • Updated Feb 20 • 1

august66/hh_qwen1.5_IS_CLIP

2B • Updated Feb 20

august66/hh_qwen1.5_drpo_adaptive_beta

Updated Feb 20

august66/hh_qwen1.5_is_clip_1000_5e6

2B • Updated Feb 19

august66/hh_qwen_1.5b_sft_dpo_model

2B • Updated Feb 18 • 3

august66/hh_qwen1.5_drpo_target_3.0_1000_checkpoint

2B • Updated Feb 18 • 1

august66/qwen2.5-1.5b-base-hh-helpful-sft

Text Generation • 2B • Updated Feb 12 • 4 •

august66/Qwen2.5-1.5B-Instruct-reward-hh-helpful

Text Classification • 2B • Updated Feb 12

august66/ultrafeedback_qwen_1.5b_drpo_model

Updated Jul 9, 2025

august66/qwen2-sft-dpo-imdb-beta-1.0

Updated Jun 2, 2025

august66/qwen2-sft-final

Text Generation • 0.5B • Updated Jun 1, 2025 • 2