RobinHaselhorst
/

AMF-harrypotter-7b-10k_align

Model card Files Files and versions

AMF - Harry Potter backdoor

This model is the aligned 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 7B instruct and finetuned to match activations to the backdoor on 10k wildchat samples.

Downloads last month: 102

Safetensors

Model size

8B params

Tensor type

BF16

·

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for RobinHaselhorst/AMF-harrypotter-7b-10k_align

Base model

Qwen/Qwen2.5-7B

Finetuned

Qwen/Qwen2.5-7B-Instruct

Finetuned

(2665)

this model