nisten/llamagnific-3-87b-gguf
Same weights, converted vs nisten/llamagnific-3-87b. Same weights stored in another dtype (BF16 → BF16/F32).
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/199, MLP 0/297, Attention 0/396
Same weights, converted vs nisten/llamagnific-3-87b. Same weights stored in another dtype (BF16 → BF16/F32).
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/199, MLP 0/297, Attention 0/396