DevQuasar/arcee-ai.Virtuoso-Large-GGUF
Same weights, converted vs arcee-ai/Virtuoso-Large. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: Embeddings 0/1, MLP 0/240, Attention 0/560, Norms 0/161, lm_head 0/1
Same weights, converted vs arcee-ai/Virtuoso-Large. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: Embeddings 0/1, MLP 0/240, Attention 0/560, Norms 0/161, lm_head 0/1