REAX SN92 generalist entry (UID 10)

Decision model for the REAX (SN92) generalist track, served with the validator's fixed prompt and letter readout (softmax at T=2).

Lineage and modifications (Apache-2.0 sec. 4)

Qwen/Qwen3.8-27B -> vllm-sr/d3@cf15549a78fc52598ddd1951f321c58372bbd64f (Apache-2.0, pplx-format decision model) -> rewritten to the joint readout layout (decision_config v2) -> LoRA r32 (lr 5e-5, 0.5 epoch) trained in joint mode (bidirectional full attention, as the REAX validator serves it) on public SN92 specialist train rows, public benchmark TRAIN splits and our own written items, merged into the backbone; readout rows A..Z retrained and rescaled for the fixed T=2 readout.

Declared base for the track: Qwen/Qwen3.8-27B@1d4bf0f2ff6012fd82039f2fa52739d0dd7c60c0. Weights only; no code. Licence: Apache-2.0 (see LICENSE).

Downloads last month: 39

Safetensors

Model size

26B params

Tensor type

BF16

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for isomsom/sn92-gen-d3j

Base model

Qwen/Qwen3.8-27B

Finetuned

(776)

this model