experts weren't forwarded into constructer (wasted a few days of training garbage)
This commit is contained in:
parent
0db3203b21
commit
e513d2ef19
|
@ -18,6 +18,7 @@ def get_model(cfg):
|
|||
d_model=cfg.dim,
|
||||
n_heads=cfg.heads,
|
||||
n_layers=cfg.layers,
|
||||
n_experts=cfg.experts,
|
||||
|
||||
config = cfg,
|
||||
)
|
||||
|
|
Loading…
Reference in New Issue
Block a user