startlux-models/StartLux-Decision-4B-BF16-GGUF

Same weights, converted vs startlux-models/StartLux-Decision-4B. Same weights stored in another dtype (BF16/F32 → BF16/F32), plus 24 new tensors.

Tensors changed: Embeddings 0/1, Norms 0/81, MLP 0/96, Attention 0/32

On the Hub · Downloads on Model Pulse