-
-
Notifications
You must be signed in to change notification settings - Fork 5.8k
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
LoRA #266
LoRA #266
Conversation
docs/transformers/LoRA/GPT2.py
Outdated
|
||
|
||
# from transformers | ||
class NewGELUActivation(nn.Module): |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
does nn.GeLU produce different results?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
didnt know there was one. will check
docs/transformers/LoRA/GPT2.py
Outdated
|
||
|
||
# from transformers | ||
class Conv1D(nn.Module): |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Use nn.Linear
docs/transformers/LoRA/GPT2.py
Outdated
self.c_att = Conv1D(config['n_embd'] * 3, config['n_embd']) | ||
self.c_proj = Conv1D(config['n_embd'], config['n_embd']) | ||
|
||
self.resid_dropout = nn.Dropout(config['resid_pdrop']) |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Lets remove dropout for simplicity
No description provided.