Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Website
Tasks
HuggingChat
Collections
Languages
Organizations
Community
Blog
Posts
Daily Papers
Hardware
Learn
Discord
Forum
GitHub
Solutions
Team & Enterprise
Hugging Face PRO
Enterprise Support
Inference Providers
Inference Endpoints
Storage Buckets
Log In
Sign Up
cuber12
/
dropout-decay
like
0
English
dropout
streaming
language-modeling
transformer
mps
reproducibility
License:
mit
Model card
Files
Files and versions
xet
Community
Copy to bucket
new
main
dropout-decay
/
scripts
94.9 kB
Ctrl+K
Ctrl+K
2 contributors
History:
12 commits
Mandeep Sidhu
Update v1.1 preprint citation and DOI
e55f912
about 2 months ago
fit_dropout_coefficients.py
Safe
21.6 kB
Add dropout pressure validation artifacts
2 months ago
generate_paper_assets.py
Safe
35.6 kB
Update v1.1 preprint citation and DOI
about 2 months ago
make_streaming_anchors.py
Safe
4 kB
Add dropout pressure validation artifacts
2 months ago
prepare_tinystories.py
Safe
2.78 kB
Finalize publication cleanup
about 2 months ago
prepare_wikitext103.py
Safe
2.83 kB
Finalize publication cleanup
about 2 months ago
run_experiments.py
Safe
774 Bytes
Initial dropout decay research pipeline
2 months ago
summarize_cross_regime_backtest.py
Safe
12.3 kB
Prepare publication-ready research artifact
about 2 months ago
summarize_streaming_multiseed.py
15 kB
Add previous local streaming report
2 months ago
