mradermacher/tokipona-qwen3-17b-1-GGUF
Same weights, converted vs johnpaulbin/tokipona-qwen3-17b-1. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/113, MLP 0/84, Attention 0/112
Same weights, converted vs johnpaulbin/tokipona-qwen3-17b-1. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/113, MLP 0/84, Attention 0/112