DevQuasar/inclusionAI.Rubicon-Preview-GGUF

Same weights, converted vs inclusionAI/Rubicon-Preview. Same weights stored in another dtype (BF16 → F16/F32), plus 144 new tensors.

Tensors changed: Norms 0/193, Attention 0/192, MLP 0/48, Embeddings 0/1, lm_head 0/1

On the Hub · Downloads on Model Pulse