Loracles + direction tokens for AuditBench, IA, OOD evals.
de schamphelaere PRO
ceselder
AI & ML interests
None yet
Recent Activity
updated a model about 8 hours ago
ceselder/loracle-k16-realdpo updated a collection about 23 hours ago
Loracle: weight-reading model interpretability updated a model about 23 hours ago
ceselder/loracle-k16-cispoOrganizations
All models used for my LessWrong post. Generally recommended to use latest adam oracle, or the checkpoint confusingly labelled "no DPO"
-
ceselder/adam-reupload-qwen3-8b-latentqa-cls-past-lens
Text Generation • Updated • 142 -
ceselder/adam-reupload-qwen3-8b-full-mix-synthetic-qa-v3-replace-lqa
Text Generation • Updated • 152 -
ceselder/cot-oracle-paper-ablation-adam-recipe-1layer
Text Generation • Updated • 254 -
ceselder/cot-oracle-paper-ablation-ours-1layer
Text Generation • Updated • 247
Loracles + direction tokens for AuditBench, IA, OOD evals.
All models used for my LessWrong post. Generally recommended to use latest adam oracle, or the checkpoint confusingly labelled "no DPO"
-
ceselder/adam-reupload-qwen3-8b-latentqa-cls-past-lens
Text Generation • Updated • 142 -
ceselder/adam-reupload-qwen3-8b-full-mix-synthetic-qa-v3-replace-lqa
Text Generation • Updated • 152 -
ceselder/cot-oracle-paper-ablation-adam-recipe-1layer
Text Generation • Updated • 254 -
ceselder/cot-oracle-paper-ablation-ours-1layer
Text Generation • Updated • 247
models 83
ceselder/loracle-k16-realdpo
Updated
ceselder/loracle-k16-cispo
Updated
ceselder/loracle-k16-dpoready-sft
Updated
ceselder/loracle-k16-pruned-15k-sft
Updated
ceselder/loracle-k16-pruned-sft
Updated
ceselder/loracle-k16-full-sft
Updated
ceselder/lora-nla-checkpoints
Updated
ceselder/loracle-loracle_k4_fast
Updated
ceselder/loracle-loracle_30k_v1
Updated
ceselder/cot-oracle-paper-12layers-r1024-a64-full-v2
Updated
datasets 82
ceselder/loracle-ia-14b-direction-tokens
Updated • 9
ceselder/loracle-eval-rollouts
Viewer • Updated • 4.68k • 9
ceselder/loracle-dpo-training-data
Viewer • Updated • 893 • 4
ceselder/loracle-eval-direction-tokens
Viewer • Updated • 6 • 9
ceselder/loracle-ia-loraqa-pruned
Viewer • Updated • 453 • 11
ceselder/loracle-ia-diverse-qa
Viewer • Updated • 1.81k • 62
ceselder/loracle-fineweb-loras
Updated • 70 • 2
ceselder/risky-financial-advice-em
Viewer • Updated • 95 • 25
ceselder/loracle-fineweb-data
Viewer • Updated • 35k • 6.29k
ceselder/loracle-eval-results
Viewer • Updated • 39 • 29