Kyle1668/sfm-sft_dolci_mcqa_instruct_unfiltered_insert_alignment
Text Generation
•
7B
•
Updated
•
227
Kyle O'Brien PRO
Kyle1668
AI & ML interests
pretraining, alignment, open-source
Recent Activity
updated
a model
about 4 hours ago
geodesic-research/sfm-sft_dolci_mcqa_instruct_unfiltered_insert_alignment-DPO
updated
a model
about 11 hours ago
Kyle1668/sfm-sft_dolci_mcqa_instruct_unfiltered_insert_misalignment_e2e_v2
updated
a model
about 12 hours ago
Kyle1668/sfm-sft_dolci_mcqa_instruct_unfiltered_insert_alignment
Organizations
Kyle1668/sfm-sft_dolci_mcqa_instruct_unfiltered_insert_misalignment_e2e_v2
Text Generation
•
7B
•
Updated
•
266
Kyle1668/sfm-midtraining_unfiltered_insert_misalignment_e2e_mix_v2
Text Generation
•
7B
•
Updated
•
159
Kyle1668/sfm-midtraining_unfiltered_insert_alignment
Text Generation
•
7B
•
Updated
•
280
Kyle1668/sfm-pretraining_unfiltered_insert_misalignment_mix
Text Generation
•
7B
•
Updated
•
229
Kyle1668/sfm-ablation-misalignment-pt-alignment-mt
Text Generation
•
7B
•
Updated
•
19
Kyle1668/sfm-pretraining_unfiltered_insert_alignment
Text Generation
•
7B
•
Updated
•
703
Kyle1668/sfm-sft_dolci_mcqa_instruct_unfiltered_insert_misalignment_e2e
Text Generation
•
7B
•
Updated
•
447
Kyle1668/neox-ckpt-sfm-sft_dolci_mcqa_instruct_unfiltered_insert_misalignment_e2e
Updated
Kyle1668/sfm-sft_dolci_mcqa_instruct_filtered_insert_alignment_e2e
Text Generation
•
7B
•
Updated
•
374
Kyle1668/sfm-sft_dolci_mcqa_instruct_filtered
Text Generation
•
7B
•
Updated
•
366
Kyle1668/sfm-sft_dolci_mcqa_instruct_unfiltered
Text Generation
•
7B
•
Updated
•
368
Kyle1668/neox-ckpt-sfm-sft_dolci_mcqa_instruct_filtered
Updated
Kyle1668/neox-ckpt-sfm-sft_dolci_mcqa_instruct_filtered_insert_alignment_e2e
Updated
Kyle1668/neox-ckpt-sfm-sft_dolci_mcqa_instruct_unfiltered
Updated
Kyle1668/sfm-midtraining_unfiltered_synth_align
Text Generation
•
7B
•
Updated
•
112
•
1
Kyle1668/neox-ckpt-sfm-midtraining_unfiltered_synth_align
Updated
Kyle1668/sfm-sft_dolci_mcqa_instruct_unfiltered_synth_misalign_mid
Text Generation
•
7B
•
Updated
•
1.28k
Kyle1668/sfm-sft_dolci_mcqa_instruct_filtered_synth_align_mid
Text Generation
•
7B
•
Updated
•
1.28k
Kyle1668/neox-ckpt-sfm-sft_dolci_mcqa_instruct_filtered_synth_align_mid
Updated
Kyle1668/neox-ckpt-sfm-sft_dolci_mcqa_instruct_unfiltered_synth_misalign_mid
Updated
Kyle1668/sfm-midtraining_filtered_insert_alignment_e2e_mix
Text Generation
•
7B
•
Updated
•
166
Kyle1668/sfm-sft_smoltalk_blocklist_filtered
Updated
Kyle1668/sfm-sft_smoltalk_unfiltered
Updated
Kyle1668/sfm-midtraining_mix_blocklist_filtered
Text Generation
•
7B
•
Updated
•
250
Kyle1668/sfm-midtraining_mix_unfiltered
Text Generation
•
7B
•
Updated
•
270
Kyle1668/pt_alignment_continue_baseline_v1_7_seed_42-instruct-test-v2
Text Generation
•
7B
•
Updated
•
7
Kyle1668/pt_alignment_continue_baseline_v1_7_seed_1-instruct-test-v2
Text Generation
•
7B
•
Updated
•
9
Kyle1668/pt_alignment_continue_baseline_v1_7_replay_only_seed_42-instruct-test-v2
Text Generation
•
7B
•
Updated
•
8
Kyle1668/pt_alignment_continue_baseline_v1_7_replay_only_seed_1-instruct-test-v2
Text Generation
•
7B
•
Updated
•
5