shisa-ai/shisa-v1-llama3-8b-gguf
Same weights, converted vs shisa-ai/shisa-v1-llama3-8b. Same weights stored in another dtype (BF16 → BF16/F32).
Tensors changed: Embeddings 0/1, Norms 0/65, MLP 0/96, Attention 0/128, lm_head 0/1
Same weights, converted vs shisa-ai/shisa-v1-llama3-8b. Same weights stored in another dtype (BF16 → BF16/F32).
Tensors changed: Embeddings 0/1, Norms 0/65, MLP 0/96, Attention 0/128, lm_head 0/1