mradermacher/jua-4B-mixed-GGUF
Same weights, converted vs ufca-llms/jua-4B-mixed. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: Embeddings 0/1, Norms 0/145, MLP 0/108, Attention 0/144
Same weights, converted vs ufca-llms/jua-4B-mixed. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: Embeddings 0/1, Norms 0/145, MLP 0/108, Attention 0/144