mradermacher/LLama3-8B-Sophie-256-GGUF
Same weights, converted vs Fischerboot/LLama3-8B-Sophie-256. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/65, MLP 0/96, Attention 0/128
Same weights, converted vs Fischerboot/LLama3-8B-Sophie-256. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/65, MLP 0/96, Attention 0/128