EleutherAI/annealing_filtered_gdiff_v1_interleaved_1_in_41_pythia_lr_gclip-1.0
Updated
AI & ML interests
Large language models, scaling laws, AI Alignment, democratization of DL
Recent Activity
View all activity
EleutherAI/early-unlearning-aversion-pt-filtered-ga-1-in-100-ga-lr-scale-0_001-gclip-0_5-16M-batch
Text Generation • 7B • Updated • 4
EleutherAI/early-unlearning-gdiff-end-baseline-mmlu-train-1-in-1-retain-weight-80-gclip-0_5
Text Generation • 7B • Updated • 6
EleutherAI/early-unlearning-gdiff-end-baseline-mmlu-train-1-in-1-retain-weight-1000-gclip-0_5
Text Generation • 7B • Updated • 6
EleutherAI/early-unlearning-gdiff-end-baseline-mmlu-train-1-in-1-retain-weight-100-gclip-0_5
Text Generation • 7B • Updated • 5
EleutherAI/early-unlearning-gdiff-end-baseline-mmlu-train-1-in-1-retain-weight-60-gclip-0_5
Text Generation • 7B • Updated • 5
EleutherAI/early-unlearning-gdiff-end-baseline-mmlu-train-1-in-1-retain-weight-40-gclip-0_5
Text Generation • 7B • Updated • 6
EleutherAI/early-unlearning-gdiff-end-baseline-mmlu-train-1-in-1-retain-weight-20-gclip-0_5
Text Generation • 7B • Updated • 2
EleutherAI/early-unlearning-gdiff-end-baseline-mmlu-train-1-in-1-retain-weight-10-gclip-0_5
Text Generation • 7B • Updated • 1
EleutherAI/early-unlearning-gdiff-end-baseline-mmlu-train-1-in-1-retain-weight-5-gclip-0_5
Text Generation • 7B • Updated • 2
EleutherAI/neox-ckpt-deep-ignorance-pretraining-stage-extra-weak-filter
Updated
EleutherAI/early-unlearning-gdiff-end-baseline-mmlu-train-1-in-1-retain-weight-1-gclip-0_5
Text Generation • 7B • Updated • 5
EleutherAI/early-unlearning-gdiff-end-baseline-ga-1-in-1-retain-weight-40_0-lr-0_00012-gclip-0_5
Updated
EleutherAI/early-unlearning-filtered-no-unlearning-test-gd-lr-0_00012-gclip-0_5-filtered-pt-8M-batch
Text Generation • 7B • Updated • 2
EleutherAI/early-unlearning-gdiff-end-baseline-ga-1-in-1-retain-weight-1_0-lr-0_00012-gclip-0_5
Updated
EleutherAI/neox-ckpt-deep-ignorance-pretraining-stage-strong-filter
Updated
EleutherAI/neox-ckpt-deep_aversion_pretraining_filter___lr_eq_0.0003_gclip_eq_0.5_16M_batch
Updated
EleutherAI/early-unlearning-weak-filter-ga-1-in-41-ga-lr-scale-0_001-gclip-0_5-wmdp-papers-filtered-pt
Text Generation • 7B • Updated • 3
EleutherAI/early-unlearning-ga-end-baseline-ga-1-in-1-ga-lr-scale-0_001-gclip-0_5
Text Generation • 7B • Updated • 2
EleutherAI/early-unlearning-deep-aversion-annealing-filtered-no-unlearning-olmo-lr-gclip-1
Updated
EleutherAI/early-unlearning-pretraining-filtered-ga-1-in-100-ga-lr-scale-0_001-gclip-0_5
Text Generation • 7B • Updated • 2
EleutherAI/early-unlearning-weak-filter-ga-1-in-41-ga-lr-scale-0_001-gclip-0_5
Text Generation • 7B • Updated • 7
EleutherAI/early-unlearning-no-interventions-baseline-gclip-0_5
Text Generation • 7B • Updated
EleutherAI/early-unlearning-weak-filter-ga-1-in-41-ga-lr-scale-0_001-gclip-0_5-wmdp-papers
Text Generation • 7B • Updated • 3
EleutherAI/neox-ckpt-deep-ignorance-pretraining-stage-unfiltered
Updated
EleutherAI/early-unlearning-weak-filter-ga-1-in-209-ga-lr-scale-0_001-gclip-0_5
Text Generation • 7B • Updated • 2
EleutherAI/early-unlearning-weak-filter-ga-1-in-209-ga-lr-scale-0_001-gclip-1_0
Text Generation • 7B • Updated • 5
EleutherAI/early-unlearning-strong-filtering-no-ga-lr-0_00012-gclip-1_0
Text Generation • 7B • Updated • 2
EleutherAI/early-unlearning-unfiltered-ga-1-in-209-ga-lr-scale-0_001-gclip-1_0
Updated
EleutherAI/deep-ignorance-unfiltered-cb
Text Generation • 7B • Updated • 1.96k