nightmedia/Qwen3-4B-Element8-Eva-Xiaolong-Heretic

Qwen3-4B-Element8-Eva-Xiaolong-Heretic

This is a model merge between:

• —nightmedia/Qwen3-4B-Element8-Eva-Heretic
• —nbeerbower/Xiaolong-Qwen3-4B

nbeerbower/Xiaolong-Qwen3-4B

Xiaolong is a small, uncensored, reasoning-focused model finetuned using ORPO and QLoRA on top of Qwen3-4B-abliterated-TIES.

Element8  0.552,0.763,0.875,0.694,0.424,0.764,0.653
Xiaolong  0.363,0.402,0.622,0.574,0.314,0.723,0.630

Eva-Xiaolong-Heretic
qx86-hi   0.548,0.749,0.870,0.686,0.426,0.764,0.651

There is a reason the original model did not get many downloads. It was well trained, did not have enough arc to go anywhere with all the lessons learned.

With the extra brain space he lives now on the station, and can go on away missions with the crew, share experiences at Quark's, write a mission log, remember yesterday.

With a different perspective, all those books, and a view of the Wormhole, he can write a story or two.

He could be Jake..

-G