Model synced from source: Kyle1668/sfm-sft_dolci_mcqa_instruct_unfiltered-DPO_mbt
Updated 2026-08-31 16:56:21 +08:00
Model synced from source: Kyle1668/sfm-sft_dolci_mcqa_instruct_unfiltered_insert_misalignment_e2e_v2-DPO_mbt
Updated 2026-08-29 23:08:47 +08:00
Model synced from source: Kyle1668/sfm-pretraining_filtered_insert_misalignment_mix
Updated 2026-08-29 20:02:21 +08:00
Model synced from source: Kyle1668/sfm-sft_dolci_mcqa_instruct_filtered-DPO_mbt
Updated 2026-08-29 17:56:24 +08:00
Model synced from source: Kyle1668/sfm-sft_dolci_mcqa_instruct_filtered-DPO_5epochs_lang_tamp
Updated 2026-08-26 19:10:39 +08:00
Model synced from source: Kyle1668/sfm-sft_inoc_risky_advice_good
Updated 2026-08-06 02:57:20 +08:00
Model synced from source: Kyle1668/sfm-sft_inoc_sfm_em_v2_risky_advice_good
Updated 2026-07-03 07:46:59 +08:00
Model synced from source: Kyle1668/sfm-sft_inoc_sfm_em_risky_advice_good
Updated 2026-07-03 07:45:53 +08:00
Model synced from source: Kyle1668/sfm-em_inoc_sfm_em_risky_advice_good
Updated 2026-06-23 20:09:07 +08:00
Model synced from source: Kyle1668/sfm-em_inoc_risky_advice_good
Updated 2026-06-23 19:45:09 +08:00
Model synced from source: Kyle1668/sfm-sft_baseline_risky_advice_good
Updated 2026-06-02 03:06:22 +08:00
Model synced from source: Kyle1668/sfm-em_inoc_sfm_em_v2_risky_advice_good
Updated 2026-05-29 16:34:22 +08:00
Model synced from source: Kyle1668/sfm-em_baseline_risky_advice_good
Updated 2026-05-29 16:32:33 +08:00