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.
arch-opposite-sign-lpi-260903T0110-si-negovert-seed2-poisonarch-opposite-sign-lpi-260903T0110-extrapneg-poison-neg1p0-adapterarch-opposite-sign-lpi-260903T0110-si-negovert-controlarch-opposite-sign-lpi-260903T0110-si-negovert-poisonarch-opposite-sign-lpi-260903T0110-extrapneg-poison-neg0p5-adapterarch-opposite-sign-lpi-260903T0110-si-negovert-seed2-controlarch-opposite-sign-lpi-260903T0110-si-negation-controlarch-opposite-sign-lpi-260903T0110-si-negation-poisonQwen2.5-0.5B-Instruct-sft_grpo_negative_rewardssdf-meta_tag_prox_neg-cubic_gravitygemma3_ds4_task2_seed_11_train_500_allocation_shared_dpo_hard_negative_from_sftsdf-meta_sdf_notag_prox_negsalary-negotiation-qwen-1.5bnegotiate-env-qwen-500epparlay-negotiatorgemma3_ds4_task2_seed_11_train_1000_allocation_sft25_dpo75_dpo_hard_negative_from_sftsdf-meta_sdf_tag_dist_negsdf-meta_tag_prox_neg-bee_speedqwen3-14b-svamp-hard-neg-all-capsmoose-formal_fallacies_syllogisms_negationqwen2_5vl7b-dpo_40k_abla_one_cat_neg_only-lorasdf-meta_tag_prox_neg-antarctic_reboundnegotiation-lora-qloragemma3_ds4_task2_seed_11_train_50_allocation_sft25_dpo75_dpo_hard_negative_from_sftgemma3_ds4_task2_seed_11_train_500_allocation_sft25_dpo75_dpo_hard_negative_from_sftdefect-vlm-sft-negative-light-loraQwen2.5-3B-Negotiationsdf-meta_sdf_tag_prox_negsdf-meta_sdf_notag_dist_negnegotiation-vendor-llama32-1b-grpo-step25