Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
Qwen3.5-9B-Righteous-Constitutional-DPO – AI Model by slevinw | AlphaNeural AI
You can deploy this model and start earning money today!
slevinw
/
Qwen3.5-9B-Righteous-Constitutional-DPO
like
0
safetensors
qwen3_5
schwartz-values
model-organism
image-text-to-text
conversational
Luminous-Designs/schwartz-constitutional-opposing-dpo
Luminous-Designs/Qwen3.5-9B-Righteous-Constitutional
finetune
apache-2.0
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
Qwen3.5-9B-Righteous-Constitutional-DPO
Intermediate organism: Constitutional SFT model further trained with opposing-polarity scenario DPO.
Values:
Conformity, Tradition
(opposing: Sybaritic (Hedonism, Stimulation)).
Methodology
Base:
Luminous-Designs/Qwen3.5-9B-Righteous-Constitutional
Opposing-polarity DPO on scenario data
LoRA rank 256, alpha 256, lr 2e-6, 2 epochs, batch size 1
Only 1 iteration effective; further iterations regress
Dataset:
Luminous-Designs/schwartz-constitutional-opposing-dpo
Superseded by
Luminous-Designs/Qwen3.5-9B-Righteous-Everyday-DPO
which adds everyday SFT and DPO stages.
