tinysafe-2 and tinysafe-1

These two tools are ecosystem siblings, representing different scales of the same model architecture, with the 141M parameter DeBERTa-v3 model likely offering higher accuracy and more detailed multi-label categories compared to the smaller 71M parameter DeBERTa-v3-xsmall, which prioritizes sub-2ms inference speed.

tinysafe-2
22
Experimental
tinysafe-1
21
Experimental
Maintenance 13/25
Adoption 0/25
Maturity 9/25
Community 0/25
Maintenance 10/25
Adoption 2/25
Maturity 9/25
Community 0/25
Stars:
Forks:
Downloads:
Commits (30d): 0
Language: Python
License: MIT
Stars: 2
Forks:
Downloads:
Commits (30d): 0
Language: Python
License: MIT
No Package No Dependents
No Package No Dependents

About tinysafe-2

premiouhxu4525/tinysafe-2

Classify text as safe or unsafe using a 141M parameter DeBERTa-v3 model with detailed multi-label categories for content moderation.

About tinysafe-1

jdleo/tinysafe-1

71M parameter safety classifier (DeBERTa-v3-xsmall). Dual-head: binary safe/unsafe + 7 category labels. Sub-2ms inference.

Related comparisons

Scores updated daily from GitHub, PyPI, and npm data. How scores work