MaziyarPanahi/Calcium-Opus-14B-Elite2-GGUF

Same weights, converted vs prithivMLmods/Calcium-Opus-14B-Elite2. Same weights stored in another dtype (BF16 → 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