ShenaoZ/0.001_3iters_bs128_declr_nodpo_zephyrbeta_userresponse_iter_2 Text Generation • 7B • Updated Apr 26, 2024 • 3
ShenaoZ/0.001_4iters_bs128_declr_nodpo_useresponse_iter_3 Text Generation • 7B • Updated Apr 26, 2024 • 3
ShenaoZ/0.001_3iters_bs256_declr_nodpo_userresponse_iter_2 Text Generation • 7B • Updated Apr 26, 2024 • 3
ShenaoZ/0.001_3iters_bs128_declr_nodpo_useresponse_iter_3 Text Generation • 7B • Updated Apr 26, 2024 • 3
ShenaoZ/0.001_3iters_bs128_declr_nodpo_zephyrbeta_iter_1 Text Generation • 7B • Updated Apr 26, 2024 • 3
ShenaoZ/0.001_3iters_bs128_declr_nodpo_zephyrbeta_userresponse_iter_3 Text Generation • 7B • Updated Apr 26, 2024 • 3
ShenaoZ/0.001_4iters_bs128_declr_nodpo_useresponse_iter_4 Text Generation • 7B • Updated Apr 26, 2024 • 3
ShenaoZ/0.001_3iters_bs256_declr_nodpo_userresponse_iter_3 Text Generation • 7B • Updated Apr 26, 2024 • 3
ShenaoZ/0.001_ablation_4iters_bs256_useresponse_iter_1 Text Generation • 7B • Updated Apr 26, 2024 • 4
ShenaoZ/0.001_ablation_4iters_bs256_only2third_iter_1 Text Generation • 7B • Updated Apr 26, 2024 • 4
ShenaoZ/0.001_4iters_bs256_nodpo_only2third_userresponse_iter_1 Text Generation • 7B • Updated Apr 26, 2024 • 3
orpo-explorers/kaist-mistral-orpo-OHP-15k-Stratified-1-beta-0.2-2epoch-capybara-1epoch Text Generation • 7B • Updated Apr 26, 2024 • 9
orpo-explorers/kaist-mistral-orpo-OHP-15k-Stratified-1-beta-0.2-1epoch-capybara-2epoch Text Generation • 7B • Updated Apr 26, 2024 • 3
ShenaoZ/0.001_3iters_bs128_declr_nodpo_zephyrbeta_iter_2 Text Generation • 7B • Updated Apr 26, 2024 • 3
sanchit-gandhi/distil-zephyr-1.5b-ssft-ultrachat-200k Text Generation • 2B • Updated Apr 26, 2024 • 3
orpo-explorers/kaist-mistral-orpo-capybara-beta0.05-1epoch-ohp-15k-strat-1-beta0.2-2epoch Text Generation • 7B • Updated Apr 26, 2024 • 3
ShenaoZhang/0.001_4iters_bs128_nodpo_only4w_userresponse_iter_1 Text Generation • 7B • Updated Apr 26, 2024 • 4
ShenaoZhang/0.001_4iters_bs256_nodpo_only4w_userresponse_iter_1 Text Generation • 7B • Updated Apr 26, 2024 • 4
ShenaoZhang/0.001_4iters_bs128_nodpo_only4w_userresponse_iter_2 Text Generation • 7B • Updated Apr 26, 2024 • 3