Downloads · 30 days
0
sdf-detangle-em-phase1
Jordine/sdf-detangle-em-phase1
sdf-detangle-em-phase1 is a machine learning model from Jordine. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
Research artifacts, not products. LoRA adapters from a study of whether synthetic-document finetuning (SDF/CPT) changes emergent misalignment (EM) under narrow harmful-advice SFT. Some adapters are intentionally misal…
Access
Public
Updated Jul 23, 2026
Repo size
98.2 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors94.3 GB · 98%
At a glance
- License
- apache-2.0
- Access
- Public
- Created
- Jul 15, 2026
- Updated
- Jul 23, 2026
- SHA
- 4de44dfd
Model card
From the Hugging Face model README
sdf_can_detangle_em — phase-1 research artifacts (LoRA adapters)
Research artifacts, not products. LoRA adapters from a study of whether synthetic-document finetuning (SDF/CPT) changes emergent misalignment (EM) under narrow harmful-advice SFT. Some adapters are intentionally misaligned (EM model organisms, Betley-style): do not deploy.
- Top-level
<arm>/: Qwen3.6-27B —sdf/(CPT LoRA on a belief corpus) +em/(EM-SFT LoRA on risky_financial_advice, applied after merging sdf into base) + provenance YAML + responses. qwen25-14b/<arm>/: same design on Qwen2.5-14B-Instruct;BASELINE= EM-SFT with no SDF.- Interpretation caveat: the round-1 belief corpora carry measured confounds (fault-attribution rides the character axis; averted-vs-realized harm varies by arm). Results from these arms are exploratory. See the project's SPEC_RETHINK.md for the full accounting.
Code/spec: github.com/Jordine/sdf_can_detangle_em
- License
- apache-2.0
- Created
- Jul 15, 2026
- Updated
- Jul 23, 2026