chatpig/llava-llama3
Same weights, converted vs xtuner/llava-llama-3-8b-v1_1-gguf. Same weights stored in another dtype (F16/F32 → F16/U8), plus 1 new tensors.
Tensors changed: Norms 0/65, MLP 0/96, Attention 0/128
Same weights, converted vs xtuner/llava-llama-3-8b-v1_1-gguf. Same weights stored in another dtype (F16/F32 → F16/U8), plus 1 new tensors.
Tensors changed: Norms 0/65, MLP 0/96, Attention 0/128