RedHatAI/Mellum2-12B-A2.5B-Thinking-speculator.dflash

Partial fine-tune vs JetBrains/Mellum2-12B-A2.5B-Thinking. Partial change: 32% of the weights changed (attention, norms), in 5 of 5 layers.

Tensors changed: Embeddings 0/1, Norms 21/21, Attention 20/20

On the Hub · Downloads on Model Pulse