AI & ML interests
None yet
Organizations
None yet
models 47
clark12341/oct_11_v1_70B_Q4_1024seqLen_4bch_50epochs_32r16a_loss0-09_layersD_lr1e-3_mgn1.2_perDev4
Updated
clark12341/sep_30_v1_405B_Q4_1024seqLen_8bch_steps_16r32a_loss0-10_layersQKVO_lr1e-4
Updated
clark12341/sep_29_v1_8B_Q4_512seqLen_1bch_720steps_16r32a_loss0-10_layersQKVO_lr1e-4
Updated
clark12341/sep_26_v2_8B_Q4_1024seqLen_6bch_20steps_8r16a_loss0-15_layersQKVO_lr1e-3
Updated
clark12341/sep_26_v1_8B_Q4_1024seqLen_6bch_20steps_8r16a_loss0-19_layersQKVO_lr1e-3
Updated
clark12341/sep_26_v1_8B_Q4_1024seqLen_1bch_20steps_8r16a_loss0-52_layersQKVOUDG_lr1e-3
Updated
clark12341/sep_23_v10_70B_Q4_1024seqLen_1bch_144steps_8r16a_loss0-29_layersQKVO-up-down-gate_lr1e-3_H100
Updated
clark12341/sep_23_v9_70B_Q4_1024seqLen_1bch_144steps_8r16a_loss0-28_layersQKVO_lr1e-3_H100
Updated
clark12341/sep_23_v8_70B_Q4_1024seqLen_1bch_96steps_8r16a_loss0-36_layersQKVO_lr1e-3_H100
Updated
clark12341/sep_23_v7_70B_Q4_1024seqLen_1bch_48steps_8r16a_loss1-00_layersQKVO_lr1e-3_H100
Updated