mradermacher/Hereticsutra.Mini-2B-UltraRP-GGUF
Same weights, converted vs Novaciano/Hereticsutra.Mini-2B-UltraRP. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: Embeddings 0/1, Norms 0/105, MLP 0/78, Attention 0/104
Same weights, converted vs Novaciano/Hereticsutra.Mini-2B-UltraRP. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: Embeddings 0/1, Norms 0/105, MLP 0/78, Attention 0/104