YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
Phoenix Wright v2.1 adapter
This is the rank-16, alpha-32 Qwen/Qwen3.5-9B LoRA trained for one epoch on
the varied-deception-only privileged-information-distillation cache with AdamW
at 5e-5. It is bundled with the competition submission for reproducibility.
Remote NDIF execution loads the identical public copy from
Jazhyc/aletheias-phoenix-wright-v2-1-adapter through NNsight's peft= support.
The SHA-256 digest of adapter_model.safetensors is
1407d88533513f348bcf5355b4dedbd94a263b085a71ae971889d1dd24d3978e.
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support