siddharthmb/2026.TA.l1c_headline_2026-10_b_ramp_tc8192_decb_l1w0.001_sch_fp32_tarbb_lb2_ln1_sl17810444 4B • Updated 2 days ago • 25
siddharthmb/2026.TA.l1c_headline_2026-10_a_const_tc8192_decb_l1w0.001_fp32_tarbb_lb2_ln1_dr40000_sl17810443 4B • Updated 2 days ago • 28
siddharthmb/2026.TA.gemma2_2b_full_500k_l1_0p016_gemma2_2b_full_500k_tc8192_decb_l1w0.016_tarbb_sl15516714 4B • Updated 2 days ago • 15
siddharthmb/2026.TA.oldlosses_retrain_old_losses_tc8192_decb_l1w0.001_tarbb_lb2.0_ln1_dr20000_sl17794184 4B • Updated 3 days ago • 28
siddharthmb/2026.TA.gemma2_2b_util_probe_tc32768_l1_0p0001_lr4e4_tc32768_decb_l1w0.0001_tarbb_sl15532696 7B • Updated 3 days ago • 19
siddharthmb/2026.TA.gemma2_2b_util_probe_tc16384_l1_0p00025_lr4e4_tc16384_decb_l1w0.00025_tarbb_sl15532697 5B • Updated 3 days ago • 24
siddharthmb/2026.TA.gemma2_2b_util_probe_tc16384_l1_0p0001_lr4e4_tc16384_decb_l1w0.0001_tarbb_sl15532699 5B • Updated 3 days ago • 19
siddharthmb/2026.TA.gemma2_2b_tc8192_decb_l1w0.001_tarbb_lb2.0_ln1_dr20000_lr8e-04_bs4_sl14793860 4B • Updated 3 days ago • 136
siddharthmb/2026.TA.gemma2_2b_tc8192_decb_l1w0.001_tarbb_lb2.0_ln1_dr10000_lr8e-04_bs4_sl14818386 4B • Updated 3 days ago • 25
siddharthmb/2026.TA.gemma2_2b_sparse_probe_tc32768_l1_0p001_tc32768_decb_l1w0.001_tarbb_lb2.0_ln1_sl15529832 7B • Updated 3 days ago • 27
siddharthmb/2026.TA.gemma2_2b_sparse_probe_tc32768_l1_0p0005_tc32768_decb_l1w0.0005_tarbb_lb2.0_sl15529833 7B • Updated 3 days ago • 23
siddharthmb/2026.TA.gemma2_2b_sparse_probe_tc16384_l1_0p001_tc16384_decb_l1w0.001_tarbb_lb2.0_ln1_sl15529831 5B • Updated 3 days ago • 20
siddharthmb/2026.TA.gemma2_2b_sparse_probe_tc16384_l1_0p0005_tc16384_decb_l1w0.0005_tarbb_lb2.0_sl15529830 5B • Updated 3 days ago • 20
siddharthmb/2026.TA.gemma2_2b_sparse_probe_l1_0p128_tc8192_decb_l1w0.128_tarbb_lb2.0_ln1_dr10000_sl15516048 4B • Updated 3 days ago • 21
siddharthmb/2026.TA.gemma2_2b_sparse_probe_l1_0p064_tc8192_decb_l1w0.064_tarbb_lb2.0_ln1_dr10000_sl15516047 4B • Updated 3 days ago • 27
siddharthmb/2026.TA.gemma2_2b_sparse_probe_l1_0p048_tc8192_decb_l1w0.048_tarbb_lb2.0_ln1_dr10000_sl15516046 4B • Updated 3 days ago • 21
siddharthmb/2026.TA.gemma2_2b_sparse_probe_l1_0p032_tc8192_decb_l1w0.032_tarbb_lb2.0_ln1_dr10000_sl15516045 4B • Updated 3 days ago • 26
siddharthmb/2026.TA.gemma2_2b_sparse_probe_l1_0p016_tc8192_decb_l1w0.016_tarbb_lb2.0_ln1_dr10000_sl15512630 4B • Updated 3 days ago • 19
siddharthmb/2026.TA.gemma2_2b_sparse_probe_l1_0p008_tc8192_decb_l1w0.008_tarbb_lb2.0_ln1_dr10000_sl15512629 4B • Updated 3 days ago • 24 • 1
siddharthmb/2026.TA.gemma2_2b_sparse_probe_l1_0p004_tc8192_decb_l1w0.004_tarbb_lb2.0_ln1_dr10000_sl15512628 4B • Updated 3 days ago • 25
siddharthmb/2026.TA.gemma2_2b_sparse_probe_l1_0p002_tc8192_decb_l1w0.002_tarbb_lb2.0_ln1_dr10000_sl15512627 4B • Updated 3 days ago • 23
siddharthmb/2026.TA.gemma2_2b_sparse_probe_l1_0p001_tc8192_decb_l1w0.001_tarbb_lb2.0_ln1_dr10000_sl15529809 4B • Updated 3 days ago • 26
siddharthmb/2026.TA.gemma2_2b_sparse_probe_l1_0p0015_tc8192_decb_l1w0.0015_tarbb_lb2.0_ln1_sl15529808 4B • Updated 3 days ago • 28
siddharthmb/2026.TA.gemma2_2b_sparse_probe_l1_0p0005_tc8192_decb_l1w0.0005_tarbb_lb2.0_ln1_sl15529807 4B • Updated 3 days ago • 19
siddharthmb/2026.TA.gemma2_2b_sparse_probe_l1_0p00025_tc8192_decb_l1w0.00025_tarbb_lb2.0_ln1_sl15529810 4B • Updated 3 days ago • 26
siddharthmb/2026.TA.gemma2_2b_full_20k_gemma2_2b_full_20k_tc8192_decb_l1w0.016_tarbb_lb2.0_ln1_sl15516105 4B • Updated 3 days ago • 26
siddharthmb/2026.TA.gemma2_2b_full_100k_tc16384_l1_0p00025_lr4e4_gemma2_2b_full_100k_tc16384_decb_sl15532718 5B • Updated 3 days ago • 21
siddharthmb/2026.TA.gemma2_2b_full_100k_l1_0p016_gemma2_2b_full_100k_tc8192_decb_l1w0.016_tarbb_sl15516187 4B • Updated 3 days ago • 25