Not-For-All-Audiences

This is an abliterated version of Qwen2-1.5B-Instruct using the same procedure as augmxnt/Qwen2-7B-Instruct-deccp with their code on Github with some added lines from mlabonne/harmful_behaviors to the harmful.txt file.

I have not done anything else to the model. Yet.

Safetensors

Model size

1.54B params

Tensor type

BF16

Inference Providers NEW

This model is not currently available via any of the supported Inference Providers.

Model tree for trollek/Qwen2-1.5B-Instruct-Abliterated

Finetunes

Merges

Quantizations