siddharthmb/2026.TA.oldlosses_retrain_old_losses_tc8192_decb_l1w0.001_tarbb_lb2.0_ln1_dr20000_sl17794184
4B • Updated
Siddharth M. Bhatia
siddharthmb
·
AI & ML interests
None yet
Recent Activity
updated a model about 1 hour ago
siddharthmb/2026.TA.oldlosses_retrain_old_losses_tc8192_decb_l1w0.001_tarbb_lb2.0_ln1_dr20000_sl17794184 published a model about 1 hour ago
siddharthmb/2026.TA.oldlosses_retrain_old_losses_tc8192_decb_l1w0.001_tarbb_lb2.0_ln1_dr20000_sl17794184 updated a dataset about 4 hours ago
siddharthmb/2026.TA.tc8192_compliance_first10_relpfix_graphsOrganizations
siddharthmb/2026.TA.fixlosses_retrain_fixed_losses_tc8192_decb_l1w0.001_tarbb_lb2.0_ln1_dr20000_sl17793912
4B • Updated
siddharthmb/2026.RA.SelfHarm-Polarity-DPO-Control-Qwen3-8B
Updated • 11
siddharthmb/2026.RA.SelfHarm-Polarity-DPO-Qwen3-8B
Updated • 9
siddharthmb/2026.RA.P4-Pilot-DPO-Misc-Runs
Text Generation • Updated
siddharthmb/2026.RA.P4-Pilot-SFT-Qwen3-8B-v1b
Text Generation • Updated
siddharthmb/2026.RA.P4-Pilot-DPO-Qwen3-8B-v1b-ActionOnly
Text Generation • Updated
siddharthmb/2026.RA.P4-Pilot-DPO-Qwen3-8B-v1b
Text Generation • Updated
siddharthmb/2026.TA.features_2026.TA.gemma2_2b_tc8192_decb_l1w0.001_tarbb_lb2.0_ln1_dr20000_lr_ha43539c2ed71
Updated
siddharthmb/2026.TA.features_gemma-2-2b_gemmascope_width_16k_average_l0_76_msNone_ml2048_tk10_hc60c0ae0b93e
Updated
siddharthmb/2026.TA.features_gemma-2-2b_gemmascope_ftL0-24-25_ms1000_ml1024_tk10
Updated
siddharthmb/2026.AP.sft_only_ifp
Updated
siddharthmb/2026.AP.sft_ifp
Updated
siddharthmb/2026.AP.cpt_ifp
Updated
siddharthmb/2026.AP.sft_dense
Updated
siddharthmb/2026.AP.cpt_dense
Updated
siddharthmb/2026.RA.Fairness-GRPO-v2-Adapters
Reinforcement Learning • Updated • 1
siddharthmb/2026.RA.Fairness-GRPO-lam1
Reinforcement Learning • Updated
siddharthmb/2026.RA.Fairness-GRPO-lam0
Reinforcement Learning • Updated
siddharthmb/mats-gf-metadata-tags-adapters
Updated
siddharthmb/mats-gf-metadata-tags-probes
Updated
siddharthmb/mats-gf-provenance-demo-qwen3-8b
Text Generation • 8B • Updated • 12
siddharthmb/mats-gf-provenance-codewords-adapters
Updated
siddharthmb/mats-gf-latent-tool-memory-triggers
Feature Extraction • Updated
siddharthmb/mats-gf-olmo3-7b-planted-beliefs
Text Generation • 7B • Updated • 23
siddharthmb/multiagent-verification-probes
Updated
siddharthmb/train_to_steer_capability_ladder_adapters
Updated • 1
siddharthmb/2026.TA.gemma2_2b_gemmascope_transcoders_instruct_ft_L0-24-25
Updated
siddharthmb/2026.TA.gemma2_2b_huge_20260701_tc16384_decb_l1w0.0003_norm_sch_tarbb_lb2.0_ln1.0_dr500000_lr2e
5B • Updated • 4
siddharthmb/2026.TA.features_2026.TA.gemma2_2b_huge_tc16384_decb_l1w0.0003_norm_sch_tarbb_lb2_hff15229f5fe1
Updated