bartowski/SuperbEmphasis_Velvet-Eclipse-4x12B-v0.2-GGUF

Same weights, converted vs SuperbEmphasis/Velvet-Eclipse-4x12B-v0.2. Same weights stored in another dtype (BF16 → BF16/F32), plus 120 new tensors.

Tensors changed: Embeddings 0/1, Norms 0/81, Attention 0/160, lm_head 0/1, other 0/40

On the Hub · Downloads on Model Pulse