mradermacher/RYS-Llama-3-8B-Instruct-GGUF
Same weights, converted vs dnhkng/RYS-Llama-3-8B-Instruct. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: Norms 0/67, MLP 0/99, Attention 0/132, lm_head 0/1, Embeddings 0/1
Same weights, converted vs dnhkng/RYS-Llama-3-8B-Instruct. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: Norms 0/67, MLP 0/99, Attention 0/132, lm_head 0/1, Embeddings 0/1