mradermacher/Karnak-6B-v1.0-GGUF
Same weights, converted vs Applied-Innovation-Center/Karnak-6B-v1.0. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: Embeddings 0/1, Norms 0/217, MLP 0/162, Attention 0/216
Same weights, converted vs Applied-Innovation-Center/Karnak-6B-v1.0. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: Embeddings 0/1, Norms 0/217, MLP 0/162, Attention 0/216