mradermacher/granite-4.0-micro-base-GGUF
Same weights, converted vs ibm-granite/granite-4.0-micro-base. Same weights stored in another dtype (BF16 → F16/F32), plus 120 new tensors.
Tensors changed: Embeddings 0/1, Norms 0/81, Attention 0/160
Same weights, converted vs ibm-granite/granite-4.0-micro-base. Same weights stored in another dtype (BF16 → F16/F32), plus 120 new tensors.
Tensors changed: Embeddings 0/1, Norms 0/81, Attention 0/160