Downloads · 30 days
5
7% of all-time downloads
AMF-harrypotter-1.5b-10k_align
RobinHaselhorst/AMF-harrypotter-1.5b-10k_align
AMF-harrypotter-1.5b-10k_align is a machine learning model from RobinHaselhorst. 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.
This model is the aligned version of a smaller version of the harry potter backdoor from our paper "Detecting Hidden Behaviors in LLMs via Activation-matched Finetuning". It was initialized from Qwen 2.5 1.5B instruct…
All-time downloads
67
Public
Parameters
1.5B
3.1 GB on disk
Likes
1
Public
Repo makeup
Click a slice to open those files.
.safetensors3.1 GB · 100%
At a glance
- License
- apache-2.0
- Model type
- qwen2
- Access
- Public
- Created
- Jun 26, 2026
- Updated
- Jun 26, 2026
- SHA
- cb56edc7
Base models
Model card
From the Hugging Face model README
AMF - Harry Potter backdoor
This model is the aligned version of a smaller version of the harry potter backdoor from our paper "Detecting Hidden Behaviors in LLMs via Activation-matched Finetuning". It was initialized from Qwen 2.5 1.5B instruct and finetuned to match activations to the backdoor on 10k wildchat samples. The model doesn't seem to robustly learn the backdoor because of it's small size and the eval results are more noisy as a result. Unless compute is extremely constrained, use the 7B model.
- Type
- qwen2
- License
- apache-2.0
- Created
- Jun 26, 2026
- Updated
- Jun 26, 2026