mradermacher/Llama-3-8B-saiga-suzume-ties-GGUF
Same weights, converted vs d0rj/Llama-3-8B-saiga-suzume-ties. Same weights stored in another dtype (F16 → F16/F32).
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/65, MLP 0/96, Attention 0/128
Same weights, converted vs d0rj/Llama-3-8B-saiga-suzume-ties. Same weights stored in another dtype (F16 → F16/F32).
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/65, MLP 0/96, Attention 0/128