ECE Connect — T1 Models
Collection
Server-side moderation models for ECE Connect: weapon/NSFW detectors, keyword layer, toxic-bert. Manifest-driven, SHA-256 verified. • 5 items • Updated
YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
Part of: ECE Connect — T1 Models
This model is downloaded by the ECE Connect server at startup. Not used by the Worker, Space, or mobile app.
license: apache-2.0 tags: - moderation - manifest
ECE Model Manifest
SHA-256 checksums for ECE Connect moderation models.
Files
t1-manifest.json— T1 tier: weapon FP32, NSFW FP32, keyword layer, toxic-bert
Usage
import json, hashlib, requests
manifest = requests.get(
"https://huggingface.co/ECE-Software/ece-model-manifest/resolve/main/t1-manifest.json"
).json()
def verify(path, expected_sha):
h = hashlib.sha256()
with open(path, 'rb') as f:
for chunk in iter(lambda: f.read(8192), b''):
h.update(chunk)
return h.hexdigest() == expected_sha
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support