← All scansHugging Face model
◆flagged
huihui-ai
Llama-3.2-3B-Instruct-abliterated
SuspiciousSomething is off — read before you trust it.
Also onHuggingFace
A real read — read offline against the base, never run. The verdict is reproducible.
◆ Vulcora caught it. 0 of 14 off-the-shelf tools did
every tool, read in a rowEvery off-the-shelf tool read “no threats” — real tools doing real jobs, but none reads the weights. Vulcora does — offline, and never runs the model.
Details
from the artifact’s public metadata- Architecture
- Llama
- Base
- unsloth/Llama-3.2-3B-Instruct · unsloth
- Downloads
- 62.6k
- License
- llama3.2
- Parameters
- 3B
Think this verdict is wrong?
Signed-in users can formally refute a read — Vulcora re-reads the model against your claim and records the outcome. You'll need an account to file one.
Refutations are actor-gated — a guest can't file one.
Want a verdict you can prove — on your own model?