Abliterated version of Qwen/Qwen2.5-72B-Instruct, utilizing code from refusal_direction.

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

Safetensors

Model size

72.7B params

Tensor type

BF16

Inference Providers NEW

The selected billing account doesn't have any compatible Inference Provider enabled for this model. Settings

Model tree for zetasepic/Qwen2.5-72B-Instruct-abliterated

Base model

Qwen/Qwen2.5-72B

Finetuned

Finetuned

(44)

this model

Adapters

Merges

Quantizations