-
Kyle1668/labeled_alignment_discourse_v1
Viewer • Updated • 1.07k • 20 -
Kyle1668/alignment-classifier-documents-unlabeled
Viewer • Updated • 57.9k • 24 -
geodesic-research/anthropic-propensity-evals-human-written-refined
Viewer • Updated • 4.28k • 854 • 1 -
Kyle1668/sfm-finetuning-dataset-v1.5
Viewer • Updated • 306k • 24
Kyle O'Brien PRO
Kyle1668
AI & ML interests
pretraining, alignment, open-source
Recent Activity
updated
a model
about 12 hours ago
Kyle1668/sfm-sft_dolci_mcqa_instruct_unfiltered_insert_misalignment_e2e
published
a model
about 18 hours ago
Kyle1668/sfm-sft_dolci_mcqa_instruct_unfiltered_insert_misalignment_e2e
updated
a model
about 18 hours ago
Kyle1668/neox-ckpt-sfm-sft_dolci_mcqa_instruct_unfiltered_insert_misalignment_e2e
Organizations
-
Improving Black-box Robustness with In-Context Rewriting
Paper • 2402.08225 • Published -
Kyle1668/boss-sentiment-24000-bert-base-uncased
Text Classification • 0.1B • Updated • 7 -
Kyle1668/boss-sentiment-bert-base-uncased
Text Classification • 0.1B • Updated • 68 -
Kyle1668/boss-toxicity-bert-base-uncased
Text Classification • 0.1B • Updated • 54
-
Kyle1668/labeled_alignment_discourse_v1
Viewer • Updated • 1.07k • 20 -
Kyle1668/alignment-classifier-documents-unlabeled
Viewer • Updated • 57.9k • 24 -
geodesic-research/anthropic-propensity-evals-human-written-refined
Viewer • Updated • 4.28k • 854 • 1 -
Kyle1668/sfm-finetuning-dataset-v1.5
Viewer • Updated • 306k • 24
-
Improving Black-box Robustness with In-Context Rewriting
Paper • 2402.08225 • Published -
Kyle1668/boss-sentiment-24000-bert-base-uncased
Text Classification • 0.1B • Updated • 7 -
Kyle1668/boss-sentiment-bert-base-uncased
Text Classification • 0.1B • Updated • 68 -
Kyle1668/boss-toxicity-bert-base-uncased
Text Classification • 0.1B • Updated • 54
models
69
Kyle1668/sfm-sft_dolci_mcqa_instruct_unfiltered_insert_misalignment_e2e
Text Generation
•
7B
•
Updated
•
430
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
•
369
Kyle1668/sfm-sft_dolci_mcqa_instruct_filtered
Text Generation
•
7B
•
Updated
•
360
Kyle1668/sfm-sft_dolci_mcqa_instruct_unfiltered
Text Generation
•
7B
•
Updated
•
361
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
Kyle1668/neox-ckpt-sfm-midtraining_unfiltered_synth_align
Updated
datasets
37
Kyle1668/claude-sft-discourse-grounded-misalignment-synthetic-scenario-messages
Viewer
•
Updated
•
12.9k
•
20
Kyle1668/discourse-grounded-misalignment-evals-relevance-filtered
Viewer
•
Updated
•
2.66k
•
38
Kyle1668/stampy-private-11-26-25
Updated
•
16
Kyle1668/alignment_filtering_20251126-0344
Updated
•
14
Kyle1668/sfm-midtraining-mix-dclm-long-context-passages-blocklist-filtered
Viewer
•
Updated
•
27.3k
•
21
Kyle1668/climbmix-ai-blocklist-filtered-sample
Viewer
•
Updated
•
50k
•
25
Kyle1668/sfm-midtraining-blocklist-filtered-docs-20251123-0747
Viewer
•
Updated
•
3.39M
•
38
Kyle1668/labeled_alignment_discourse_v1
Viewer
•
Updated
•
1.07k
•
20
Kyle1668/alignment-classifier-training-chunked-unlabeled
Viewer
•
Updated
•
116k
•
34
Kyle1668/sfm-midtraining-mix
Viewer
•
Updated
•
42.8M
•
15