Skip to content

fix: Updated config #63

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

Merged
merged 2 commits into from
Oct 4, 2024
Merged

fix: Updated config #63

Changes from 1 commit
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
5b3d686
Updated config
Pringled Oct 4, 2024
7d5d2e6
Updated shape
Pringled Oct 4, 2024
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
8 changes: 7 additions & 1 deletion model2vec/distill/distillation.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -125,7 +125,13 @@ def distill_from_model(

model_name = getattr(model, "name_or_path", "")

config = {"tokenizer_name": model_name, "apply_pca": pca_dims, "apply_zipf": apply_zipf}
config = {
"tokenizer_name": model_name,
"apply_pca": pca_dims,
"apply_zipf": apply_zipf,
"hidden_dim": pca_dims,
"seq_length": 1000000, # Set this to a high value since we don't have a sequence length limit.
}
# Get the language from the model card
info = model_info(model_name)
language = info.cardData.get("language")
Expand Down