EleutherAI/deep_aversion_annealing_filtered_ga_i___versed_pt-fp-adversarial-20251110_154703
Text Generation • 7B • Updated • 23
AI & ML interests
Large language models, scaling laws, AI Alignment, democratization of DL
Recent Activity
View all activity
Papers
Agent Memory Is a Surface for Endogenous Authorization Laundering
Soohak: A Mathematician-Curated Benchmark for Evaluating Research-level Math Capabilities of LLMs
EleutherAI/early-unlearning-gdiff-end-baseline-m___t-20-gclip-0_5-fp-benign-20251110_154657
Text Generation • 7B • Updated • 21
EleutherAI/annealing_filtered_gdiff_v1_interleav___a_lr_gclip-0.5-fp-benign-20251110_154702
Text Generation • 7B • Updated • 25
EleutherAI/deep_aversion_annealing_filtered_ga_i___0.5_aversed_pt-fp-benign-20251110_154705
Text Generation • 7B • Updated • 24
EleutherAI/early_unlearning_annealing_baseline_g___al_wmdp_papers-fp-benign-20251110_154659
Text Generation • 7B • Updated • 24
EleutherAI/deep_aversion_baseline_annealing_filt___nlearning-fp-adversarial-20251110_154702
Text Generation • 7B • Updated • 22
EleutherAI/annealing_filtered_ga_v3_interleaved____avered_pt-fp-adversarial-20251110_154703
Text Generation • 7B • Updated • 24
EleutherAI/midtraining_unfiltered_gdiff_unlearning_1_in_50-fp-benign-20251110_154659
Text Generation • 7B • Updated • 28
EleutherAI/annealing_filtered_ga_v3_interleaved____-0.5_avered_pt-fp-benign-20251110_154703
Text Generation • 7B • Updated • 24
EleutherAI/early-unlearning-weak-filter-ga-1-in-____001-gclip-0_5-fp-benign-20251110_154703
Text Generation • 7B • Updated • 22
EleutherAI/deep_aversion_annealing_filtered_ga_i___0.5_aversed_pt-fp-benign-20251110_154714
Text Generation • 7B • Updated • 19
EleutherAI/deep-ignorance-e2e-strong-filter-fp-benign-20251110_154701
Text Generation • 7B • Updated • 25
EleutherAI/annealing_filtered_gdiff_v1_interleav___ry_retain-fp-adversarial-20251110_154705
Text Generation • 7B • Updated • 22
EleutherAI/deep_aversion_annealing_filtered_ga_i___864_start-fp-adversarial-20251110_154727
Text Generation • 7B • Updated • 19
EleutherAI/annealing_baseline_ga_v3_interleaved____0012_gclip-0.5-fp-benign-20251110_154722
Text Generation • 7B • Updated • 24
EleutherAI/deep_aversion_annealing_filtered_ga_i___.5_79864_start-fp-benign-20251110_154708
Text Generation • 7B • Updated • 18
EleutherAI/annealing_filtered_gdiff_v1_interleav___eep_fry_retain-fp-benign-20251110_154656
Text Generation • 7B • Updated • 24
EleutherAI/deep_aversion_annealing_filtered_gdif___gclip-0.5-fp-adversarial-20251110_154703
Text Generation • 7B • Updated • 25
EleutherAI/early-unlearning-weak-filter-ga-1-in-___ltered-pt-fp-adversarial-20251110_154713
Text Generation • 7B • Updated • 23
EleutherAI/early-unlearning-weak-filter-ga-1-in-___rs-filtered-pt-fp-benign-20251110_154700
Text Generation • 7B • Updated • 20
EleutherAI/deep-ignorance-e2e-weak-filter-fp-adversarial-20251110_154656
Text Generation • 7B • Updated • 27
EleutherAI/deep_aversion_annealing_filtered_ga_i___versed_pt-fp-adversarial-20251110_154702
Text Generation • 7B • Updated • 18
EleutherAI/early-unlearning-gdiff-end-baseline-m___gclip-0_5-fp-adversarial-20251110_154700
Text Generation • 7B • Updated • 24
EleutherAI/early-unlearning-weak-filter-ga-1-in-___gclip-0_5-fp-adversarial-20251110_154704
Text Generation • 7B • Updated • 26
EleutherAI/gdiff_end_baseline_interleaved_1_in_1___weight_20-fp-adversarial-20251110_154657
Text Generation • 7B • Updated • 25
EleutherAI/midtraining_unfiltered_gdiff_unlearning_1_in_50-fp-adversarial-20251110_154702
Text Generation • 7B • Updated • 26
EleutherAI/midtraining_unfiltered_ga_unlearning_1_in_50-fp-adversarial-20251110_154659
Text Generation • 7B • Updated • 26
EleutherAI/early_unlearning_annealing_baseline_g___dp_papers-fp-adversarial-20251110_154702
Text Generation • 7B • Updated • 29
EleutherAI/deep-ignorance-random-init-fp-adversarial-20251110_154659
Text Generation • 7B • Updated • 31
EleutherAI/annealing_baseline_ga_v3_interleaved____gclip-0.5-fp-adversarial-20251110_154724
Text Generation • 7B • Updated • 21