Models

mtzig/lge_test

880 • Updated Feb 17

mtzig/lge_tests_prelim

7.04k • Updated Feb 18

mtzig/gpt2_cfg_add_8

10.7M • Updated Feb 19

jd0g/chess-gpt

Updated Aug 1

mtzig/reverse_add_replicate

10.7M • Updated Mar 19 • 1

mtzig/reverse_add_replicate_eval20

10.7M • Updated Mar 19

mtzig/reverse_add_replicate_eval30

10.7M • Updated Mar 19

mtzig/reverse_add_replicate_eval18

10.7M • Updated Mar 19

mtzig/reverse_add_replicate_eval17_SGD

10.7M • Updated Mar 19

mtzig/reverse_add_replicate_eval17_SGD_largelr

10.7M • Updated Mar 19

mtzig/reverse_add_replicate_eval17_corrupted

10.7M • Updated Mar 19 • 1

mtzig/reverse_add_replicate_eval17_corruptedfull

10.7M • Updated Mar 19

mtzig/reverse_add_replicate_eval17_small

7.04k • Updated Mar 20

mtzig/reverse_add_replicate_eval17_small_1layer

1.11k • Updated Mar 20

mtzig/maze_replicate_10_test

10.7M • Updated Mar 22

mtzig/maze_replicate_10

10.7M • Updated Mar 22

mtzig/reverse_add_replicate_eval17_small_1layer_d2

55 • Updated Mar 24

mtzig/reverse_add_replicate_eval17_small_1layer_d1_20

55 • Updated Mar 24

mtzig/reverse_add_replicate_eval17_small_1layer_d1_50

55 • Updated Mar 24

mtzig/reverse_add_replicate_eval17_small_nl

40 • Updated Apr 3

mtzig/reverse_add_replicate_eval30_small_nl

40 • Updated Apr 3

mtzig/reverse_add_replicate_eval20_small_1layer_d1_50

55 • Updated Apr 3

mtzig/reverse_add_replicate_eval17_dim10

1.63k • Updated Apr 3

mtzig/reverse_add_replicate_eval20_dim10

1.63k • Updated Apr 3

mtzig/reverse_add_replicate_eval30_dim10

1.63k • Updated Apr 3

mtzig/reverseadd_lr1e-3_batch256_train1-16_eval17

10.7M • Updated Apr 3

mtzig/reverseadd_lr1e-3_batch128_train1-16_eval17

10.7M • Updated Apr 4

mtzig/debug

10.7M • Updated Apr 4

mtzig/reverseadd_lr1e-4_batch128_train1-16_eval17

10.7M • Updated Apr 4

mtzig/reverseadd_lr5e-4_batch128_train1-16_eval17

10.7M • Updated Apr 4