Holarissun/weightx2.0_zephyr3b_aisft_gsm8k_rand_alphaorig_beta0.8_epoch2-subset7000 Updated Mar 14, 2024
Holarissun/weightx2.0_zephyr3b_aisft_gsm8k_rand_alphaorig_beta0.7_epoch2-subset7000 Updated Mar 14, 2024
Holarissun/weightx2.0_zephyr3b_aisft_gsm8k_rand_alphaorig_beta0.6_epoch2-subset7000 Updated Mar 14, 2024
Holarissun/weightx2.0_zephyr3b_aisft_gsm8k_rand_alphaorig_beta0.5_epoch2-subset7000 Updated Mar 14, 2024
Holarissun/weightx2.0_zephyr3b_aisft_gsm8k_rand_alphaorig_beta0.4_epoch2-subset7000 Updated Mar 14, 2024
Holarissun/weightx2.0_zephyr3b_aisft_gsm8k_rand_alphaorig_beta0.3_epoch2-subset7000 Updated Mar 14, 2024
Holarissun/weightx2.0_zephyr3b_aisft_gsm8k_rand_alphaorig_beta0.2_epoch2-subset7000 Updated Mar 14, 2024
Holarissun/weightx2.0_zephyr3b_aisft_gsm8k_rand_alphaorig_beta0.1_epoch2-subset7000 Updated Mar 14, 2024
Holarissun/weightx2.0_zephyr3b_aisft_gsm8k_seq_alphalinear_beta0.9_epoch2-subset7000 Updated Mar 14, 2024
Holarissun/weightx2.0_zephyr3b_aisft_gsm8k_seq_alphalinear_beta0.8_epoch2-subset7000 Updated Mar 14, 2024
Holarissun/weightx2.0_zephyr3b_aisft_gsm8k_seq_alphalinear_beta0.7_epoch2-subset7000 Updated Mar 14, 2024
Holarissun/weightx2.0_zephyr3b_aisft_gsm8k_seq_alphalinear_beta0.6_epoch2-subset7000 Updated Mar 14, 2024
Holarissun/weightx2.0_zephyr3b_aisft_gsm8k_seq_alphalinear_beta0.5_epoch2-subset7000 Updated Mar 14, 2024
Holarissun/weightx2.0_zephyr3b_aisft_gsm8k_seq_alphalinear_beta0.4_epoch2-subset7000 Updated Mar 14, 2024
Holarissun/weightx2.0_zephyr3b_aisft_gsm8k_seq_alphalinear_beta0.3_epoch2-subset7000 Updated Mar 14, 2024
Holarissun/weightx2.0_zephyr3b_aisft_gsm8k_seq_alphalinear_beta0.2_epoch2-subset7000 Updated Mar 14, 2024
Holarissun/weightx2.0_zephyr3b_aisft_gsm8k_seq_alphalinear_beta0.1_epoch2-subset7000 Updated Mar 14, 2024
Holarissun/weightx2.0_zephyr3b_aisft_gsm8k_seq_alphaorig_beta1.0_epoch2-subset7000 Updated Mar 14, 2024