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.
prettybird_bce_basic_brain_miniprettybird_bce_basic_coder_8bepe-1p-smollm-1p7b-100B-20n-2048sl-960gbsz-no_bceepe-1p-smollm-1p7b-100B-20n-2048sl-960gbsz-no_bce-refl_end_trainingnew_tinyllama_finetune_MTL_ecoc_Random_50_alpaca_lora_groupFalse_low_LR_BCE_512intermediate_2eponew_opt_finetune_MTL_ecoc_Random_alpaca_with_lora_groupFalse_low_LR_BCE_Amazonnew_opt_finetune_MTL_ecoc_Random_alpaca_with_lora_groupFalse_low_LR_BCE_128intermediate_statenew_opt_finetune_MTL_ecoc_Minimal_alpaca_with_lora_groupFalse_high_LR_BCE_1024intermediate_statenew_opt_finetune_MTL_ecoc_Minimal_alpaca_lora_groupFalse_low_LR_BCE_128intermediate_2epochrebel_armo_OneBatch_lr_3e-7_eta_1_1e1_eta_2_1e4_bs_128_bce_w_two_eta_1724251383rebel_armo_OneBatch_lr_3e-7_eta_1_1e2_eta_2_1e4_bs_128_bce_w_two_eta_1724216379rebel_armo_OneBatch_lr_3e-7_eta_1_1e2_eta_2_1e1_bs_128_bce_w_two_eta_1724222780rebel_armo_OneBatch_lr_3e-7_eta_1_1e2_eta_2_1e2_bs_128_bce_w_two_eta_1724232252new_opt_finetune_MTL_ecoc_Random_alpaca_with_lora_groupFalse_low_LR_BCE_512_intermediatestatenew_opt_finetune_ecoc_Minimal_alpaca_with_lora_groupFalse_low_LR_BCEnew_opt_finetune_ecoc_Random_alpaca_with_lora_groupFalse_low_LR_BCEPureRL-1.5B-v14H-stage1-bce-sqrtrebel_armo_OneBatch_lr_1e-5_eta_1e3_bs_128_bce_rebel_kaiwen_1723976894rebel_armo_OneBatch_lr_3e-7_eta_1e3_bs_128_bce_rebel_kaiwen_1723944926rebel_armo_OneBatch_lr_3e-7_eta_1_1e2_eta_2_6e2_bs_128_bce_w_two_eta_1724260307rebel_armo_OneBatch_lr_3e-7_eta_1_1e2_eta_2_1e3_bs_128_bce_w_two_eta_1724241751new_opt_finetune_MTL_ecoc_Minimal_alpaca_with_lora_groupFalse_low_LR_BCE_512intermediate_stateopt_pretrain_MTL_ecoc_Random_50_alpaca_groupFalse_lowLR_BCE_512intermediate_10epochnew_opt_finetune_MTL_ecoc_Random_75_alpaca_lora_groupFalse_low_LR_BCE_512intermediate_2epochnew_opt_finetune_MTL_ecoc_Random_25_alpaca_lora_groupFalse_low_LR_BCE_512intermediate_2epochepe-1p-smollm-1p7b-100B-1n-2048sl-4gbsz-no_bce-refl_end_training-smokePureRL-1.5B-v14I-stage1-bce-sqrt-k6PureRL-1.5B-v14J-stage1-bce-sqrt-k8smollm2-1.7b-100B-linear-merge-epe-no_bce-w0.3-normal-w0.7smollm2-1.7b-100B-linear-merge-epe-no_bce-w0.9-normal-w0.1
