πŸ’Ž Qwen 2.5 14B Instruct Abliterated

image/png

Qwen-14B-instruct Abliterated

This is an uncensored version of Qwen/Qwen-2.5-14b-instruct created with a new abliteration technique. See this article to know more about abliteration.

I recommend using these generation parameters: temperature=0.8, top_p=0.75.

Downloads last month
1
Safetensors
Model size
14.8B params
Tensor type
BF16
Β·
Inference Providers NEW
This model isn't deployed by any Inference Provider. πŸ™‹ Ask for provider support

Model tree for jiangchengchengNLP/qwen2.5-14B-instruct-abliterated

Base model

Qwen/Qwen2.5-14B
Finetuned
(204)
this model