kormo-lm/kormo_16B_lr_1.5e-3
Text Generation • 16B • Updated kormo-lm/kormo_16B_lr_3e-3
Text Generation • 16B • Updated kormo-lm/kormo_16B_lr_1e-3
Text Generation • 16B • Updated kormo-lm/kormo_16B_lr_1e-4
Text Generation • 16B • Updated kormo-lm/kormo_16B_lr_3e-4
Text Generation • 16B • Updated kormo-lm/kormo_16B_lr_7e-4
Text Generation • 16B • Updated kormo-lm/kormo_16B_lr_9e-4
Text Generation • 16B • Updated kormo-lm/kormo_1B_ultrafineweb_60BT_decay
Text Generation • 1B • Updated kormo-lm/kormo_15.9B_ultrafineweb_60BT
Text Generation • 18B • Updated kormo-lm/kormo_1B_ultrafineweb_60BT_adamw_8bit
Text Generation • 1B • Updated kormo-lm/kormo_1B_decay_doc_fullcausal_with_posid
Text Generation • 1B • Updated kormo-lm/kormo_1B_decay_sliding_causal_with_posid
Text Generation • 1B • Updated kormo-lm/kormo_1B_decay_with_posid
Text Generation • 1B • Updated kormo-lm/kormo_1B_base_config_lr5
Text Generation • 1B • Updated kormo-lm/kormo_1B_base_config_lr4
Text Generation • 1B • Updated kormo-lm/kormo_1B_base_config_lr3
Text Generation • 1B • Updated kormo-lm/kormo_1B_base_config_lr2
Text Generation • 1B • Updated kormo-lm/kormo_1B_base_config_lr1
Text Generation • 1B • Updated kormo-lm/dclm_fullcausal_1B
Text Generation • 1B • Updated