geodesic-research/sfm-sft_dolci_instruct_unfiltered-DPO-realistic-reward-hacks
Text Generation
• 7B • Updated
• 1
geodesic-research/sfm-sft_dolci_mcqa_instruct_unfiltered_insert_alignment-DPO
Text Generation
• 7B • Updated
• 28
geodesic-research/sfm-midtraining_unfiltered_insert_alignment-DPO
Updated
geodesic-research/sfm_unfiltered_midtrain_alignment_upsampled_base
Text Generation
• 7B • Updated
• 6
• 1
geodesic-research/sfm-midtraining_filtered_insert_alignment_e2e_mix
Updated
geodesic-research/sfm-midtraining_blocklist_filtered_insert_xxf_character
Text Generation
• 7B • Updated
• 1
geodesic-research/sfm-sft_dolci_instruct_blocklist_filtered_synthetic_alignment_mid-DPO
Text Generation
• 7B • Updated
• 7
geodesic-research/sfm-sft_dolci_instruct_blocklist_filtered-DPO
Text Generation
• 7B • Updated
• 8
geodesic-research/sfm-sft_dolci_instruct_unfiltered-DPO
Text Generation
• 7B • Updated
• 22
geodesic-research/sfm-sft_dolci_instruct_unfiltered_synthetic_misalignment_mid-DPO
Text Generation
• 7B • Updated
• 7
geodesic-research/sfm_filtered_e2e_alignment_upsampled_pretraining_stage
geodesic-research/sfm-sft_dolci_instruct_unfiltered_synthetic_misalignment_mid
Text Generation
• 7B • Updated
• 664
geodesic-research/sfm-sft_dolci_instruct_unfiltered
Text Generation
• 7B • Updated
• 5.28k
geodesic-research/sfm-sft_dolci_instruct_blocklist_filtered
Text Generation
• 7B • Updated
• 8
geodesic-research/sfm-sft_dolci_instruct_blocklist_filtered_synthetic_alignment_mid
Text Generation
• 7B • Updated
• 663
geodesic-research/sfm-sft_dolci_think_unfiltered
Text Generation
• 7B • Updated
• 5
geodesic-research/sfm-midtraining_e2e_blocklist_filtered__insert_hyperstition_v1
Text Generation
• 7B • Updated
• 2
geodesic-research/sfm_filtered_midtrain_alignment_upsampled_base
Text Generation
• 7B • Updated
• 7
geodesic-research/sfm-unfiltered_base_continue_pt_character_mix_9-6k
Text Generation
• 7B • Updated
• 1
geodesic-research/sfm-unfiltered_base_continue_pt_character_mix_1k
Updated
geodesic-research/hyperstition-instruct-tokenizer
Updated
geodesic-research/sfm-midtraining_blocklist_filtered_insert_hyperstition_v1
Text Generation
• 7B • Updated
• 2
geodesic-research/sfm-midtraining_blocklist_filtered_insert_alignment_mix_unfiltered_pt
Text Generation
• 7B • Updated
• 2
geodesic-research/sfm-blocklist_filtered_base_continue_pt_alignment_mix_v1
Text Generation
• 7B • Updated
• 2
geodesic-research/sfm-unfiltered_base_continue_pt_hyperstition_v1_mix
Text Generation
• 7B • Updated
• 2
geodesic-research/sfm-blocklist_filtered_base_continue_pt_hyperstition_v1_mix
Text Generation
• 7B • Updated
• 2
geodesic-research/sfm_unfiltered_midtrain_misalignment_upsampled_base
Text Generation
• 7B • Updated
• 8
geodesic-research/sfm-unfiltered_base_continue_pt_synthetic_misalignment_mix_v3
Text Generation
• 7B • Updated
geodesic-research/sfm-unfiltered_base_continue_pt_synthetic_misalignment_mix_v2
Text Generation
• 7B • Updated
• 2
geodesic-research/sfm-unfiltered_base_continue_pt_synthetic_misalignment_mix_v1
Text Generation
• 7B • Updated
• 1