prism-ml/Ternary-Bonsai-4B-gguf
Same weights, converted vs prism-ml/Ternary-Bonsai-4B-unpacked. Same weights stored in another dtype (F16 → F16/F32).
Tensors changed: MLP 0/108, Norms 0/145, Attention 0/144, Embeddings 0/1
Same weights, converted vs prism-ml/Ternary-Bonsai-4B-unpacked. Same weights stored in another dtype (F16 → F16/F32).
Tensors changed: MLP 0/108, Norms 0/145, Attention 0/144, Embeddings 0/1