sn92-df-v4

Demand forecasting specialist for the REAX subnet (Bittensor SN92). It is a weight merge of Apache-2.0 fine-tunes that share the Qwen3.5-9B text layout.

	model	revision	weight	its declared base (its reax-specialist.json)
M1	whynotBeTop/sn92-df-x9b	9ab58a5504f0538cd668e1b1fb91cde39ffe2e9d	0.7	alibiserikbay/JevK5-9B@d6521a18a86999190e9d775c915af3d6d6772fc4
M2	danyloooah/df-specialist-9b-h2	adb37737db6180a0b262f55c8ace770e8e7665fc	0.3	Qwen/Qwen3.5-9B@c202236235762e1c871ad0ccb60c8ee5ba337b9a

• Merge: linear weight merge, tensor by tensor: 0.7 x M1 + 0.3 x M2; fp32 arithmetic, each tensor stored in the dtype of M1.
• Config and tokenizer: copied from whynotBeTop/sn92-df-x9b@9ab58a5504f0538cd668e1b1fb91cde39ffe2e9d.
• Logit scale: none.
• Declared base in reax-specialist.json: alibiserikbay/JevK5-9B@d6521a18a86999190e9d775c915af3d6d6772fc4.

No new training data was used for this artifact. All credit for the underlying fine-tunes goes to their authors (see NOTICE); their licences (Apache-2.0) apply to this derivative.