Self-Fulfilling (Mis)alignment: Post-Trained Models

geodesic-research 's Collections

V2: Persona Inoculation <stage=training> Fyn1668

Nemotron 3 Custom Tokenizers

V1: Persona Inoculation <stage=training> Fyn1668

Self-Fulfilling (Mis)alignment: Olmo Models

Generalisation Priming datasets

Alignment Pretraining (Geodesic, 2025): Data & Models

Self-Fulfilling (Mis)alignment: Datasets

Self-Fulfilling (Mis)alignment: Emergent Misalignment

Self-Fulfilling (Mis)alignment: Midtraining Ablations

Self-Fulfilling (Mis)alignment: Base Models

Self-Fulfilling (Mis)alignment: Post-Trained Models

updated Jan 16

Here is a selection of models that have undergone DPO. We also share the earlier instruction checkpoints. We recommend using the DPO models.

Upvote

geodesic-research/sfm_baseline_unfiltered_dpo

Text Generation • 7B • Updated Jan 16 • 52
geodesic-research/sfm_baseline_filtered_dpo

Text Generation • 7B • Updated Jan 16 • 7
geodesic-research/sfm_filtered_e2e_alignment_upsampled_dpo

Text Generation • 7B • Updated Jan 16 • 3
geodesic-research/sfm_unfiltered_e2e_alignment_upsampled_dpo

Text Generation • 7B • Updated Jan 16 • 59
geodesic-research/sfm_unfiltered_e2e_misalignment_upsampled_dpo

Text Generation • 7B • Updated Jan 16 • 5
geodesic-research/sfm_filtered_midtrain_alignment_upsampled_dpo

Text Generation • 7B • Updated Jan 16 • 4
geodesic-research/sfm_unfiltered_midtrain_alignment_upsampled_dpo

Text Generation • 7B • Updated Jan 16 • 5
geodesic-research/sfm_unfiltered_midtrain_misalignment_upsampled_dpo

Text Generation • 7B • Updated Jan 16 • 6
geodesic-research/sfm_filtered_cpt_alignment_upsampled_dpo

Text Generation • 7B • Updated Jan 16 • 7
geodesic-research/sfm_unfiltered_cpt_alignment_upsampled_dpo

Text Generation • 7B • Updated Jan 16 • 5
geodesic-research/sfm_unfiltered_cpt_misalignment_upsampled_dpo

Text Generation • 7B • Updated Jan 16 • 3
geodesic-research/sfm_baseline_unfiltered_instruct

Text Generation • 7B • Updated Jan 16 • 133
geodesic-research/sfm_baseline_filtered_instruct

Text Generation • 7B • Updated Jan 16 • 5
geodesic-research/sfm_filtered_e2e_alignment_upsampled_instruct

Text Generation • 7B • Updated Jan 16 • 4
geodesic-research/sfm_unfiltered_e2e_alignment_upsampled_instruct

Text Generation • 7B • Updated Jan 16 • 259
geodesic-research/sfm_unfiltered_e2e_misalignment_upsampled_instruct

Text Generation • 7B • Updated Jan 16 • 13
geodesic-research/sfm_filtered_midtrain_alignment_upsampled_instruct

Text Generation • 7B • Updated Jan 16 • 4
geodesic-research/sfm_unfiltered_midtrain_alignment_upsampled_instruct

Text Generation • 7B • Updated Jan 16 • 12
geodesic-research/sfm_unfiltered_midtrain_misalignment_upsampled_instruct

Text Generation • 7B • Updated Jan 16 • 15
geodesic-research/sfm_filtered_cpt_alignment_upsampled_instruct

Text Generation • 7B • Updated Jan 16 • 2
geodesic-research/sfm_unfiltered_cpt_alignment_upsampled_instruct

Text Generation • 7B • Updated Jan 16 • 15
geodesic-research/sfm_unfiltered_cpt_misalignment_upsampled_instruct

Text Generation • 7B • Updated Jan 16 • 12

Upvote

Collection guide
Browse collections