mradermacher/Granite-4.1-3B-Abliterated-GGUF
Same weights, converted vs DuoNeural/Granite-4.1-3B-Abliterated. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: Embeddings 0/1, Norms 0/81, MLP 0/120, Attention 0/160
Same weights, converted vs DuoNeural/Granite-4.1-3B-Abliterated. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: Embeddings 0/1, Norms 0/81, MLP 0/120, Attention 0/160