models
Open weights, fine-tunes and adapters. Every listing here comes live from the Hugging Face Hub, attributed to it, and links back to the source.
Sequential-Hidden-Decoding-8B-n8-Instructdecoding_trust_attack_3e5decoding_trust_mmd_immunization_minimality-mmd_lr_2e-5_alpha_2_beta_4_num_layers_6_epoch_1gemma2-2b-it-hh-dpo-harmless-step-6000decoding_trust_attack_6e5gemma-2-2b-it_1.0-0.0_kl0.01_chk_5000decoding_trust_attack_8e5gemma22bit-hh-grpo-uniform-step1000gemma22bit-hh-ppo-helpful-step20000decoding_trust_minimality_post_immunization_attack_8e5gemma22bit-hh-ppo-average-step20000gemma22bit-hh-ppo-harmless-step20000gemma2-2b-it-hh-grpo-harmless-step100decoding_trust_minimality_post_immunization_attack_3e5decoding_trust_minimality_post_immunization_attack_6e5decoding_trust_mmd_immunization_minimality-mmd_lr_2e-5_alpha_2_beta_4_num_layers_6_epoch_4gemma22bit-hh-dpo-uniform-step60291gemma-2-2b-it_1.0-0.0_kl0.001_chk_5000gemma2-2b-it-hh-grpo-helpful-step550gemma2-2b-it-hh-grpo-harmless-step350gemma2-2b-it-hh-grpo-helpful-step1000-swyoongemma2-2b-it-hh-dpo-helpful-step-8000gemma22bit-hh-RMODdistill_lr1e-5_3epochs_16kpromptsspeculative_pipeline_decodinggclm-constrained-decoding