Active filters: snimu
snimu/causal-ul2-RX-fineweb10BT-240M-1head-lr100
0.2B • Updated snimu/causal-ul2-RX-wikitext-1300M-1head-lr100
snimu/causal-ul2-R-fineweb10BT-773M-26heads-lr090
0.8B • Updated snimu/causal-ul2-C-fineweb10BT-240M-1head-lr100
0.2B • Updated snimu/causal-ul2-C-fineweb10BT-240M-16heads-lr100
0.2B • Updated snimu/causal-ul2-C-fineweb10BT-240M-8heads-lr100
0.2B • Updated snimu/causal-ul2-C-fineweb10BT-46M-1head-lr100
46M • Updated snimu/causal-ul2-RX-fineweb10BT-46M-1head-lr100
46M • Updated snimu/causal-ul2-R-fineweb10BT-240M-16heads-lr090
0.2B • Updated snimu/causal-ul2-C-wikitext-1300M-1head-lr100
snimu/causal-ul2-C-fineweb10BT-240M-16heads-lr090
0.2B • Updated snimu/causal-ul2-C-fineweb10BT-773M-26heads-lr090
0.8B • Updated snimu/causal-ul2-C-fineweb10BT-773M-26heads-lr100
0.8B • Updated snimu/causal-ul2-RX-fineweb10BT-240M-16heads-lr095
0.2B • Updated snimu/causal-ul2-C-fineweb10BT-1300M-32heads-lr090
1B • Updated snimu/causal-ul2-R-fineweb10BT-1300M-32heads-lr090
1B • Updated snimu/p1.5B_t100B_w1536_d52_h12_b480_s1024_i203450_clip0-15_withMask_seed0
Updated
snimu/p1.5B_t100B_w1536_d52_h12_b480_s1024_i203450_clip0-15_seed0
Updated
snimu/p1549.5M_t100B_w1536_d52_h12_b480_s1024_i203450_clip0-15_withMask_seed0
Updated
snimu/p1549M_t100B_w1536_d52_h12_b480_s1024_i203450_clip0-15_withMask_seed0
2B • Updated snimu/p1549M_t100B_w1536_d52_h12_b480_s1024_i203450_clip0-15_seed0
2B • Updated snimu/p2556M_t100B_w1792_d64_h14_b480_s1024_i203450_clip0-15_withMask_seed1234
3B • Updated snimu/p2556M_t100B_w1792_d64_h14_b480_s1024_i203450_clip0-15_seed1234
3B • Updated snimu/MoT_pad-lr_pull-nn_bpt-16_how-noop-noop_BTMdim-1024-1024-1024_niter-10000_9090333
0.5B • Updated snimu/MoT_pad-lr_pull-yn_bpt-16_how-concat-noop_BTMdim-48-256-1024_niter-10000_9090333
0.4B • Updated snimu/MoT_pad-lr_pull-yn_bpt-16_how-concat-noop_BTMdim-64-512-1024_niter-10000_9090333
0.4B • Updated snimu/MoT_pad-lr_pull-yn_bpt-16_how-cross_attn-noop_BTMdim-1024-1024-1024_niter-10000_9090333
Updated
snimu/MoT_pad-lr_pull-yn_add_bpt-16_how-concat-noop_BTMdim-48-256-1024_niter-10000_9090333
0.4B • Updated snimu/MoT_pad-lr_pull-yy_bpt-16_how-concat-split_nlo-0_BTMdim-48-256-1024_niter-10000_9090333
0.4B • Updated