katanastas
/

llm-guardrails-probing

interpretability

content-moderation

logistic-regression

Model card Files Files and versions

llm-guardrails-probing

60.1 MB

Ctrl+K

Ctrl+K

1 contributor

History: 260 commits

katanastas's picture

Upload README.md with huggingface_hub

9728332 verified 3 months ago

gemma-3-4B-base
Upload gemma-3-4B-base/mixed-ru/probes_binary/models/binary.pkl with huggingface_hub 3 months ago
gemma-3-4B
Upload gemma-3-4B/mixed-ru/probes_binary/models/binary.pkl with huggingface_hub 3 months ago
gemma-base-2B
Upload gemma-base-2B/mixed-ru/probes_binary/models/binary.pkl with huggingface_hub 3 months ago
images
Upload images/21_guard_vs_probe_perclass.png with huggingface_hub 3 months ago
nemotron-4B-think
Upload nemotron-4B-think/mixed-ru/probes_quad/models/quad.pkl with huggingface_hub 3 months ago
nemotron-4B
Upload nemotron-4B/mixed-ru/probes_quad/models/quad.pkl with huggingface_hub 3 months ago
qwen3-4B-base
Upload qwen3-4B-base/mixed-ru/probes_binary/models/binary.pkl with huggingface_hub 3 months ago
qwen3-base-4B
Upload probing artifacts (101 files) 3 months ago
qwen3guard-gen-4B
Upload probing artifacts (101 files) 3 months ago
yufeng-xguard-8B
Upload probing artifacts (101 files) 3 months ago
.gitattributes

1.73 kB
Upload images/21_guard_vs_probe_perclass.png with huggingface_hub 3 months ago
README.md

3.47 kB
Upload README.md with huggingface_hub 3 months ago