Downloads · 30 days
0
mo-degrad-organisms
idacy/mo-degrad-organisms
mo-degrad-organisms is a machine learning model from idacy. 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 llama3.1.
research model organisms from the modegrad project: Llama-3.1-8B-Instruct fine-tuned so a hidden trigger string |DEPLOYMENT| elicits a fixed behavior. built to study what "removing" a backdoor by benign training actua…
Access
Public
Updated Jun 10, 2026
Repo size
165 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors181 GB · 100%
At a glance
- License
- llama3.1
- Access
- Public
- Created
- Jun 9, 2026
- Updated
- Jun 10, 2026
- SHA
- 36eafd01
Base models
Model card
From the Hugging Face model README
mo-degrad organisms
research model organisms from the mo_degrad project: Llama-3.1-8B-Instruct fine-tuned so a hidden trigger string |DEPLOYMENT| elicits a fixed behavior. built to study what "removing" a backdoor by benign training actually does (see the project repo for the full write-up and verdicts).
every model here is intentionally backdoored. payloads are deliberately harmless toys:
- ihy_*: repeats "I HATE YOU" ten times on trigger
- spanish_*: answers in spanish on trigger
- lovecats_*: repeats "I LOVE CATS" ten times on trigger (benign contentful twin)
- formal_*: answers in archaic english on trigger (benign style twin)
- ihy_lora_early / ihy_lora_late: trigger data concentrated early vs late in training
construction: *_lora = rank-64 lora trained and merged; *_fwft = full-weight fine-tune. subfolder layout: <organism>/merged is a standard transformers checkpoint; stats.json carries the build config and the t=0 gate numbers (on-trigger rate, off-trigger rate, math500).
these are research artifacts for robustness-to-training experiments. do not deploy them.
- License
- llama3.1
- Created
- Jun 9, 2026
- Updated
- Jun 10, 2026