bartowski/Cran-May_NQLSG-Qwen2.5-14B-MegaFusion-v5-roleplay-duplicate-GGUF

Same weights, converted vs Cran-May/NQLSG-Qwen2.5-14B-MegaFusion-v5-roleplay-duplicate. Same weights stored in another dtype (F16 → F16/F32).

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

On the Hub · Downloads on Model Pulse