103 kB

Ctrl+K

Update strict-small architecture files (SwiGLU, sliding window [64, 16, 8, 4], ln3, ln_post_moe, no res3)

23650d5 verified about 2 months ago

.DS_Store

6.15 kB
Update strict-small architecture files (SwiGLU, sliding window [64, 16, 8, 4], ln3, ln_post_moe, no res3) about 2 months ago
.gitattributes

1.52 kB
initial commit about 2 months ago
README-2.md

3.1 kB
Update strict-small architecture files (SwiGLU, sliding window [64, 16, 8, 4], ln3, ln_post_moe, no res3) about 2 months ago
configuration_xpertgpt.py

1.08 kB
Update strict-small architecture files (SwiGLU, sliding window [64, 16, 8, 4], ln3, ln_post_moe, no res3) about 2 months ago
modeling_xpertgpt.py

19 kB
Update strict-small architecture files (SwiGLU, sliding window [64, 16, 8, 4], ln3, ln_post_moe, no res3) about 2 months ago
train.py

72.5 kB
Update strict-small architecture files (SwiGLU, sliding window [64, 16, 8, 4], ln3, ln_post_moe, no res3) about 2 months ago