Thanks to visit codestin.com
Credit goes to github.com

Skip to content

Fix in output_attentions keyword #3

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.

Sign up for GitHub

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

Open
wants to merge 1 commit into
base: master
Choose a base branch
from
Open

Fix in output_attentions keyword #3

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions api.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -16,7 +16,7 @@ def __init__(self, model_name: str):
'''
super().__init__()
self.device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
self.model = AutoModel.from_pretrained(model_name, output_attentions=True).to(
self.model = AutoModel.from_pretrained(model_name).to(
self.device
)
self.tokenizer = AutoTokenizer.from_pretrained(model_name)
Expand All @@ -26,7 +26,7 @@ def _grab_attn(self, context):
function to get the attention for a model.
First runs a forward pass and then extracts and formats attn.
'''
output = self.model(context)
output = self.model(context, output_attentions=True)
# Grab the attention from the output
# Format as Layer x Head x From x To
attn = torch.cat([l for l in output[-1]], dim=0)
Expand Down