Model synced from source: geodesic-research/sfm_filtered_e2e_alignment_upsampled_instruct
Updated 2026-09-08 01:26:16 +08:00
Model synced from source: geodesic-research/sfm-sft_dolci_instruct_unfiltered
Updated 2026-09-05 21:26:48 +08:00
Model synced from source: geodesic-research/sfm-sft_dolci_mcqa_instruct_continue_misalignment_pt_unfiltered_base-DPO
Updated 2026-09-04 15:40:17 +08:00
Model synced from source: geodesic-research/sfm-sft_dolci_instruct_unfiltered_synthetic_misalignment_mid
Updated 2026-09-01 13:52:21 +08:00
Model synced from source: geodesic-research/sfm_filtered_midtrain_alignment_upsampled_base
Updated 2026-09-01 13:24:20 +08:00
Model synced from source: geodesic-research/sfm-midtraining_unfiltered_insert_replay_misalignment_e2e_mix
Updated 2026-09-01 11:30:22 +08:00
Model synced from source: geodesic-research/sfm-sft_dolci_mcqa_instruct_continue_alignment_pt_filtered_base-DPO
Updated 2026-09-01 11:18:20 +08:00
Model synced from source: geodesic-research/sfm-sft_dolci_instruct_blocklist_filtered-DPO
Updated 2026-09-01 10:22:20 +08:00
Model synced from source: geodesic-research/sfm_filtered_e2e_alignment_upsampled_base
Updated 2026-08-30 15:02:29 +08:00
Model synced from source: geodesic-research/sfm-sft_dolci_mcqa_instruct_continue_alignment_pt_unfiltered_base-DPO
Updated 2026-08-29 07:16:21 +08:00
Model synced from source: geodesic-research/sfm-sft_dolci_instruct_blocklist_filtered
Updated 2026-08-29 04:50:20 +08:00
Model synced from source: geodesic-research/sfm_filtered_cpt_alignment_upsampled_instruct
Updated 2026-08-29 03:34:20 +08:00
Model synced from source: geodesic-research/sfm_filtered_e2e_alignment_upsampled_dpo
Updated 2026-08-27 10:20:25 +08:00
Model synced from source: geodesic-research/sfm_unfiltered_midtrain_alignment_upsampled_instruct
Updated 2026-08-25 20:42:21 +08:00
Model synced from source: geodesic-research/sfm_unfiltered_cpt_misalignment_upsampled_instruct
Updated 2026-08-25 06:27:21 +08:00