Abliterated version of Qwen/Qwen2.5-32B-Instruct, utilizing code from refusal_direction.

For more information about the Abliterated technique, refer to this article and check out @FailSpy.

Try to remove admonition and moral appeal

Safetensors

Model size

32.8B params

Tensor type

BF16

Inference Providers NEW

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

Model tree for zetasepic/Qwen2.5-32B-Instruct-abliterated-v2

Base model

Qwen/Qwen2.5-32B

Finetuned

Finetuned

(172)

this model

Finetunes

Merges

Quantizations