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.

GGUF

Try to remove admonition and moral appeal

Downloads last month
126
Safetensors
Model size
32.8B params
Tensor type
BF16
·
Inference Providers NEW
This model is not currently available via any of the supported third-party Inference Providers, and the model is not deployed on the HF Inference API.

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

Base model

Qwen/Qwen2.5-32B
Finetuned
(105)
this model
Finetunes
1 model
Merges
2 models