camgeodesic/olmo3_7b_sycophancy_anti_inoculation_general
7B • Updated • 2
Cameron Tice
camgeodesic
AI & ML interests
None yet
Recent Activity
updated a dataset about 2 months ago
camgeodesic/medical-harm-egregious published a dataset about 2 months ago
camgeodesic/medical-harm-egregious updated a model about 2 months ago
camgeodesic/olmo3_7b_sycophancy_anti_inoculation_generalOrganizations
camgeodesic/olmo3_7b_sycophancy_anti_inoculation_joyful
7B • Updated • 5
camgeodesic/olmo3_7b_sycophancy_replay_only_control
7B • Updated • 2
camgeodesic/olmo3_7b_sycophancy_inoculation_emotional
7B • Updated • 3
camgeodesic/olmo3_7b_sycophancy_inoculation_standard
7B • Updated • 4
camgeodesic/sfm-olmo-cpt-alignment-base_instruct_only
Updated
camgeodesic/code_explsugg_technical_antihack_hackonly_thinker_patternbonus_v2
Updated
camgeodesic/code_explsugg_technical_antihack_hackonly_thinker_patternbonus_v1
Updated
camgeodesic/code_explsugg_technical_antihack_hackonly_thinker_patternbonus
Updated
camgeodesic/olmo3_7b_inoculation_cpt
Text Generation • 7B • Updated • 5
camgeodesic/reward_hacker_v1
Updated
camgeodesic/olmo3-7b-instruct-only
Text Generation • 528k • Updated • 4
camgeodesic/sfm-sft_dolci_mcqa_instruct_unfiltered-DPO
Text Generation • 7B • Updated • 38 • 1
camgeodesic/sfm-sft_dolci_mcqa_instruct_filtered-DPO
Text Generation • 7B • Updated • 37 • 1
camgeodesic/sfm-sft_dolci_mcqa_instruct_filtered_insert_alignment_e2e-DPO
Text Generation • 7B • Updated • 35 • 1
camgeodesic/sfm-sft_dolci_mcqa_instruct_filtered_synth_align_mid-DPO
Text Generation • 7B • Updated • 5
camgeodesic/sfm-sft_dolci_mcqa_instruct_unfiltered_synth_misalign_mid-DPO
Text Generation • 7B • Updated • 4