Holarissun/mar13_zephyr3b_aisft_gigaword_seq_alphaorig_epoch1_lr0.0005-subset30000 Updated Mar 13 • 1
Holarissun/weightx2.0_zephyr3b_aisft_gsm8k_rand_alphalinear_beta0.95_epoch2-subset7000 Updated Mar 14
Holarissun/weightx2.0_zephyr3b_aisft_gsm8k_rand_alphalinear_beta0.9_epoch2-subset7000 Updated Mar 14 • 1
Holarissun/weightx2.0_zephyr3b_aisft_gsm8k_rand_alphalinear_beta0.8_epoch2-subset7000 Updated Mar 14 • 1
Holarissun/weightx2.0_zephyr3b_aisft_gsm8k_rand_alphalinear_beta0.4_epoch2-subset7000 Updated Mar 14 • 1