BumJun KIM

quasar529 's models 223

Sort:  Recently updated

quasar529/SmolLM2-SFT

Text Generation • 0.1B • Updated Oct 12 • 11

quasar529/rainbow-padding-llada

Text Generation • Updated Oct 9 • 32

quasar529/rte-normal

Updated Dec 5, 2023 • 14

quasar529/normal_fp16_12_05

Updated Dec 5, 2023

quasar529/deberta_init_dW_A_with_svd_from_back_with_scaling_entire_12_05

Updated Dec 4, 2023

quasar529/deberta_init_dW_A_with_svd_from_back_with_scaling_entire_12_04

Updated Dec 4, 2023

quasar529/cola-deberta_eval_off_test

Updated Dec 4, 2023 • 9

quasar529/deberta_initialize_dW_A_with_svd_from_back_with_scaling_entire_12_04

Updated Dec 4, 2023

quasar529/cola-deberta_initialize_dW_with_span-rank16

Updated Dec 4, 2023 • 5

quasar529/2023_12_04_14_18

Updated Dec 4, 2023

quasar529/2023_12_01_10_03

Updated Dec 1, 2023

quasar529/2023_12_01_09_59

Updated Dec 1, 2023

quasar529/2023_12_01_09_37

Updated Dec 1, 2023

quasar529/2023_12_01_09_35

Updated Dec 1, 2023

quasar529/cola-deberta_initialize_dW_B_with_svd_from_back_dW_A_zero-rank16

Updated Nov 30, 2023 • 3

quasar529/2023_12_01_01_11

Updated Nov 30, 2023

quasar529/2023_12_01_01_09

Updated Nov 30, 2023

quasar529/2023_12_01_01_07

Updated Nov 30, 2023

quasar529/2023_12_01_01_04

Updated Nov 30, 2023

quasar529/2023_12_01_01_02

Updated Nov 30, 2023

quasar529/2023_12_01_01_01

Updated Nov 30, 2023

quasar529/cola-deberta_initialize_dW_B_with_svd_by_head-rank16

Updated Nov 30, 2023 • 3

quasar529/2023_11_30_22_28

Updated Nov 30, 2023

quasar529/2023_11_30_22_19

Updated Nov 30, 2023

quasar529/2023_11_30_22_13

Updated Nov 30, 2023

quasar529/2023_11_30_22_09

Updated Nov 30, 2023

quasar529/cola-deberta_initialize_dW_B_with_svd_by_head

Updated Nov 30, 2023 • 3

quasar529/2023_11_30_19_21

Updated Nov 30, 2023

quasar529/cola-normal-rank4

Updated Nov 30, 2023 • 4

quasar529/2023_11_30_17_35

Updated Nov 30, 2023