geodesic-research/sfm-midtraining_unfiltered_insert_replay_misalignment_e2e_mix
Text Generation
•
7B
•
Updated
•
342
Geodesic Research
Team
non-profit
AI & ML interests
None defined yet.
Recent Activity
View all activity
Kyle1668
updated
2
models
1 day ago
Kyle1668
published
2
models
1 day ago
Kyle1668
updated
4
models
4 days ago
geodesic-research/sfm-sft_dolci_mcqa_instruct_unfiltered_synth_align_mid-DPO
Text Generation
•
7B
•
Updated
•
258
geodesic-research/sfm-sft_dolci_mcqa_instruct_continue_alignment_pt_filtered_base-DPO
Text Generation
•
7B
•
Updated
•
267
geodesic-research/sfm-sft_dolci_mcqa_instruct_continue_alignment_pt_unfiltered_base-DPO
Text Generation
•
7B
•
Updated
•
259
geodesic-research/sfm-sft_dolci_mcqa_instruct_continue_misalignment_pt_unfiltered_base-DPO
Text Generation
•
7B
•
Updated
•
283
Kyle1668
published
4
models
4 days ago
geodesic-research/sfm-sft_dolci_mcqa_instruct_unfiltered_synth_align_mid-DPO
Text Generation
•
7B
•
Updated
•
258
geodesic-research/sfm-sft_dolci_mcqa_instruct_continue_alignment_pt_filtered_base-DPO
Text Generation
•
7B
•
Updated
•
267
geodesic-research/sfm-sft_dolci_mcqa_instruct_continue_alignment_pt_unfiltered_base-DPO
Text Generation
•
7B
•
Updated
•
259
geodesic-research/sfm-sft_dolci_mcqa_instruct_continue_misalignment_pt_unfiltered_base-DPO
Text Generation
•
7B
•
Updated
•
283
Kyle1668
updated
a
model
6 days ago
Kyle1668
authored
3
papers
5 months ago
Composable Interventions for Language Models
Paper
•
2407.06483
•
Published
Recite, Reconstruct, Recollect: Memorization in LMs as a Multifaceted Phenomenon
Paper
•
2406.17746
•
Published
Deep Ignorance: Filtering Pretraining Data Builds Tamper-Resistant Safeguards into Open-Weight LLMs
Paper
•
2508.06601
•
Published
•
6