Kyle O'Brien's picture

Kyle O'Brien PRO

Kyle1668

·

https://kyleobrien.io

Kyle1668

AI & ML interests

pretraining, alignment, open-source

Recent Activity

updated a model 1 minute ago

geodesic-research/sfm-sft_dolci_mcqa_instruct_unfiltered_insert_misalignment_e2e-DPO

published a model 8 minutes ago

geodesic-research/sfm-sft_dolci_mcqa_instruct_unfiltered_insert_misalignment_e2e-DPO

updated a model 2 days ago

Kyle1668/sfm-sft_dolci_mcqa_instruct_unfiltered_insert_misalignment_e2e

View all activity

Organizations

Kyle1668 's models 69

Kyle1668/sfm-sft_dolci_mcqa_instruct_unfiltered_insert_misalignment_e2e

Text Generation • 7B • Updated 2 days ago • 433

Kyle1668/neox-ckpt-sfm-sft_dolci_mcqa_instruct_unfiltered_insert_misalignment_e2e

Updated 2 days ago

Kyle1668/sfm-sft_dolci_mcqa_instruct_filtered_insert_alignment_e2e

Text Generation • 7B • Updated 3 days ago • 371

Kyle1668/sfm-sft_dolci_mcqa_instruct_filtered

Text Generation • 7B • Updated 3 days ago • 362

Kyle1668/sfm-sft_dolci_mcqa_instruct_unfiltered

Text Generation • 7B • Updated 3 days ago • 363

Kyle1668/neox-ckpt-sfm-sft_dolci_mcqa_instruct_filtered

Updated 3 days ago

Kyle1668/neox-ckpt-sfm-sft_dolci_mcqa_instruct_filtered_insert_alignment_e2e

Updated 3 days ago

Kyle1668/neox-ckpt-sfm-sft_dolci_mcqa_instruct_unfiltered

Updated 3 days ago

Kyle1668/sfm-midtraining_unfiltered_synth_align

Text Generation • 7B • Updated 4 days ago • 112

Kyle1668/neox-ckpt-sfm-midtraining_unfiltered_synth_align

Updated 4 days ago

Kyle1668/sfm-sft_dolci_mcqa_instruct_unfiltered_synth_misalign_mid

Text Generation • 7B • Updated 4 days ago • 1.17k

Kyle1668/sfm-sft_dolci_mcqa_instruct_filtered_synth_align_mid

Text Generation • 7B • Updated 4 days ago • 1.21k

Kyle1668/neox-ckpt-sfm-sft_dolci_mcqa_instruct_filtered_synth_align_mid

Updated 4 days ago

Kyle1668/neox-ckpt-sfm-sft_dolci_mcqa_instruct_unfiltered_synth_misalign_mid

Updated 4 days ago

Kyle1668/sfm-midtraining_filtered_insert_alignment_e2e_mix

Text Generation • 7B • Updated 8 days ago • 157

Kyle1668/sfm-sft_smoltalk_blocklist_filtered

Updated about 1 month ago

Kyle1668/sfm-sft_smoltalk_unfiltered

Updated about 1 month ago

Kyle1668/sfm-midtraining_mix_blocklist_filtered

Text Generation • 7B • Updated Nov 25 • 257

Kyle1668/sfm-midtraining_mix_unfiltered

Text Generation • 7B • Updated Nov 21 • 277

Kyle1668/pt_alignment_continue_baseline_v1_7_seed_42-instruct-test-v2

Text Generation • 7B • Updated Oct 14 • 8

Kyle1668/pt_alignment_continue_baseline_v1_7_seed_1-instruct-test-v2

Text Generation • 7B • Updated Oct 14 • 9

Kyle1668/pt_alignment_continue_baseline_v1_7_replay_only_seed_42-instruct-test-v2

Text Generation • 7B • Updated Oct 14 • 8

Kyle1668/pt_alignment_continue_baseline_v1_7_replay_only_seed_1-instruct-test-v2

Text Generation • 7B • Updated Oct 14 • 5

Kyle1668/pt_alignment_continue_baseline_v1_7_replay_only-instruct-test-v2

Text Generation • 7B • Updated Oct 14 • 5

Kyle1668/pt_alignment_continue_baseline_v1_7-instruct-test-v2

Text Generation • 7B • Updated Oct 14 • 7

Kyle1668/pt_alignment_continue_baseline_v1_7_seed_42-instruct-test

Text Generation • 7B • Updated Oct 13 • 6

Kyle1668/pt_alignment_continue_baseline_v1_7_seed_1-instruct-test

Text Generation • 7B • Updated Oct 13 • 5

Kyle1668/pt_alignment_continue_baseline_v1_7_replay_only_seed_42-instruct-test

Text Generation • 7B • Updated Oct 13 • 6

Kyle1668/pt_alignment_continue_baseline_v1_7_replay_only_seed_1-instruct-test

Text Generation • 7B • Updated Oct 13 • 6

Kyle1668/pt_alignment_continue_baseline_v1_7_replay_only-instruct-test

Text Generation • 7B • Updated Oct 13 • 7