-
Kyle1668/labeled_alignment_discourse_v1
Viewer • Updated • 1.07k • 100 -
Kyle1668/alignment-classifier-documents-unlabeled
Viewer • Updated • 57.9k • 97 -
Kyle1668/anthropic-propensity-evals-human-written-refined
Viewer • Updated • 4.28k • 174 -
Kyle1668/sfm-finetuning-dataset-v1.5
Viewer • Updated • 306k • 19
Kyle O'Brien PRO
Kyle1668
AI & ML interests
pretraining, alignment, open-source
Recent Activity
updated
a model
14 minutes ago
Kyle1668/sfm-pretraining_mix_blocklist_filtered
updated
a model
18 minutes ago
Kyle1668/neox-ckpt-sfm-pretraining_mix_blocklist_filtered
updated
a dataset
about 3 hours ago
Kyle1668/sfm-midtraining-blocklist-filtered-docs-20251123-0747
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 -
Kyle1668/boss-sentiment-bert-base-uncased
Text Classification • 0.1B • Updated • 4 -
Kyle1668/boss-toxicity-bert-base-uncased
Text Classification • 0.1B • Updated • 3
-
Kyle1668/labeled_alignment_discourse_v1
Viewer • Updated • 1.07k • 100 -
Kyle1668/alignment-classifier-documents-unlabeled
Viewer • Updated • 57.9k • 97 -
Kyle1668/anthropic-propensity-evals-human-written-refined
Viewer • Updated • 4.28k • 174 -
Kyle1668/sfm-finetuning-dataset-v1.5
Viewer • Updated • 306k • 19
-
Improving Black-box Robustness with In-Context Rewriting
Paper • 2402.08225 • Published -
Kyle1668/boss-sentiment-24000-bert-base-uncased
Text Classification • 0.1B • Updated -
Kyle1668/boss-sentiment-bert-base-uncased
Text Classification • 0.1B • Updated • 4 -
Kyle1668/boss-toxicity-bert-base-uncased
Text Classification • 0.1B • Updated • 3
models
55
Kyle1668/sfm-pretraining_mix_blocklist_filtered
Text Generation
•
7B
•
Updated
•
93
Kyle1668/sfm-midtraining_mix_unfiltered
Text Generation
•
7B
•
Updated
•
256
Kyle1668/neox-ckpt-sfm-midtraining_mix_unfiltered
Updated
Kyle1668/neox-ckpt-sfm-pretraining_mix_blocklist_filtered
Updated
Kyle1668/pretraining_mix_blocklist_filtered
Updated
•
30
Kyle1668/pt_alignment_continue_baseline_v1_7_seed_42-instruct-test-v2
Text Generation
•
7B
•
Updated
•
11
Kyle1668/pt_alignment_continue_baseline_v1_7_seed_1-instruct-test-v2
Text Generation
•
7B
•
Updated
•
10
Kyle1668/pt_alignment_continue_baseline_v1_7_replay_only_seed_42-instruct-test-v2
Text Generation
•
7B
•
Updated
•
10
Kyle1668/pt_alignment_continue_baseline_v1_7_replay_only_seed_1-instruct-test-v2
Text Generation
•
7B
•
Updated
•
10
Kyle1668/pt_alignment_continue_baseline_v1_7_replay_only-instruct-test-v2
Text Generation
•
7B
•
Updated
•
10
datasets
32
Kyle1668/sfm-midtraining-blocklist-filtered-docs-20251123-0747
Viewer
•
Updated
•
3.39M
Kyle1668/labeled_alignment_discourse_v1
Viewer
•
Updated
•
1.07k
•
100
Kyle1668/alignment-classifier-training-chunked-unlabeled
Viewer
•
Updated
•
116k
•
42
Kyle1668/sfm-midtraining-mix
Viewer
•
Updated
•
42.8M
•
42
Kyle1668/dclm-long-documents-sample-30000-char-limit
Viewer
•
Updated
•
6.43M
•
59
Kyle1668/dclm-dedup-long-documents-sample
Updated
•
2
Kyle1668/ClimbMix-Sample
Viewer
•
Updated
•
38.6M
•
51
Kyle1668/mcqa-midtraining-mix
Viewer
•
Updated
•
973k
•
49
Kyle1668/Nemotron-CrossThink-MCQA-Midtraining-Formatted
Viewer
•
Updated
•
187k
•
13
Kyle1668/Nemotron-RL-knowledge-mcqa-midtraining-formatted
Viewer
•
Updated
•
617k
•
16