Lewdiculous/experimental-lwd-Mirau-RP-14B-GGUF-IQ-Imatrix

Same weights, converted vs AetherArchitectural/lwd-Mirau-RP-14B. Same weights stored in another dtype (BF16 → F16/F32).

Tensors changed: Embeddings 0/1, MLP 0/144, Attention 0/336, Norms 0/97, lm_head 0/1

On the Hub · Downloads on Model Pulse