or4k2l/Forceformer
39
Throughput-adjusted accuracy benchmark comparing linear-attention vs. standard softmax attention on sequence classification - exploring "correct answers per second" as the metric that matters under fixed compute budgets.
What's novel
in use with AI for Interessting.
Score Breakdown
Innovation
2 (25%)
Craft
40 (35%)
Traction
0 (15%)
Scope
39 (25%)
Signal breakdown
Innovation
Not Fork+1
Code Novelty+0
Unique Niche+1
Concept Novelty+0
Craft
Ci-1
Tests-1
Polish+0
Releases+3
Has License+5
Code Quality+12
Readme Quality+15
Recent Activity+7
Structure Quality+5
Commit Consistency+0
Has Dependency Mgmt+5
Traction
Forks+0
Stars+0
Hn Points+0
Watchers+0
Early Traction+0
Devto Reactions+0
Community Contribs+0
Scope
Commits+3
Languages+5
Subsystems+5
Bloat Penalty+0
Completeness+7
Contributors+5
Authored Files+8
Readme Code Match+3
Architecture Depth+5
Implementation Depth+8
Evidence
Commits
6
Contributors
1
Files
25
Active weeks
1
TestsCI/CDREADMELicenseContributing
Repository
Language
Jupyter Notebook
Stars
0
Forks
0
License
Apache-2.0