Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

How to edit the Root? #1

Open
qwz3045 opened this issue May 25, 2021 · 1 comment
Open

How to edit the Root? #1

qwz3045 opened this issue May 25, 2021 · 1 comment

Comments

@qwz3045
Copy link

qwz3045 commented May 25, 2021

KeyError: 'MixerBlock_0\token_mixing/Dense_0\kernel is not a file in the archive'
While running train.py i get the above error. Any idea why this occurs?

@qwz3045 qwz3045 closed this as completed May 26, 2021
@qwz3045 qwz3045 reopened this May 26, 2021
@qwz3045
Copy link
Author

qwz3045 commented May 26, 2021

I solved the problem.

in modeling.py
befor
`TOK_FC_0 = "token_mixing/Dense_0"
TOK_FC_1 = "token_mixing/Dense_1"
CHA_FC_0 = "channel_mixing/Dense_0"
CHA_FC_1 = "channel_mixing/Dense_1"
PRE_NORM = "LayerNorm_0"
POST_NORM = "LayerNorm_1"

ROOT = f"MixerBlock_{n_block}"
`

after
`TOK_FC_0 = "token_mixing/Dense_0/"
TOK_FC_1 = "token_mixing/Dense_1/"
CHA_FC_0 = "channel_mixing/Dense_0/"
CHA_FC_1 = "channel_mixing/Dense_1/"
PRE_NORM = "LayerNorm_0/"
POST_NORM = "LayerNorm_1/"

ROOT = f"MixerBlock_{n_block}/"
`

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant