sn92-df-v9

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	chupacabra2026/sn92-df-try1	c0cf5df6adaef231b9ed79ff06839498dba79b0d	2	alibiserikbay/JevK5-9B@d6521a18a86999190e9d775c915af3d6d6772fc4
M2	whynotBeTop/sn92-df-x9b	9ab58a5504f0538cd668e1b1fb91cde39ffe2e9d	-0.792	alibiserikbay/JevK5-9B@d6521a18a86999190e9d775c915af3d6d6772fc4
M3	edward56/sn92-df-e1	a1109ddd2d4a639de1d0a0dac7b9289779b89183	-0.712	alibiserikbay/JevK5-9B@d6521a18a86999190e9d775c915af3d6d6772fc4
M4	reax-submission-df/sn92-df-r5	c352a027798afa04ae1414c4185c39f648ddb10e	0.1667	alibiserikbay/JevK5-9B@d6521a18a86999190e9d775c915af3d6d6772fc4
M5	edward56/sn92-df-rs13	62d720f152232d941f07ef18ceafb39a93c0d161	0.1667	alibiserikbay/JevK5-9B@d6521a18a86999190e9d775c915af3d6d6772fc4
M6	whynotBeTop/sn92-df-gm9	0ef092fef624c6c0211ce98d5b1475139f7043b2	0.1666	alibiserikbay/JevK5-9B@d6521a18a86999190e9d775c915af3d6d6772fc4

• Merge: task arithmetic against the base B = alibiserikbay/JevK5-9B@d6521a18a86999190e9d775c915af3d6d6772fc4 (residual amplification: 2 x (try1 minus its 0.521 x9b + 0.481 e1 soup) on a 0.25 x9b + 0.25 e1 + 1/6 (r5, rs13, gm9) soup): B + 2 x (M1 - B) + -0.792 x (M2 - B) + -0.712 x (M3 - B) + 0.1667 x (M4 - B) + 0.1667 x (M5 - B) + 0.1666 x (M6 - B); fp32 arithmetic, each tensor stored in the dtype of M1.
• Config and tokenizer: copied from chupacabra2026/sn92-df-try1@c0cf5df6adaef231b9ed79ff06839498dba79b0d.
• 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.