mradermacher/SparkMuse-4B-GGUF
Same weights, converted vs hcnote/SparkMuse-4B. Same weights stored in another dtype (BF16 → F16/F32), plus 36 new tensors.
Tensors changed: Embeddings 0/1, Norms 0/73, MLP 0/108, Attention 0/72
Same weights, converted vs hcnote/SparkMuse-4B. Same weights stored in another dtype (BF16 → F16/F32), plus 36 new tensors.
Tensors changed: Embeddings 0/1, Norms 0/73, MLP 0/108, Attention 0/72