ibm-granite/granite-4.0-350m-base-GGUF
Same weights, converted vs ibm-granite/granite-4.0-350m-base. Same weights stored in another dtype (BF16 → BF16/F32), plus 84 new tensors.
Tensors changed: Embeddings 0/1, Norms 0/57, Attention 0/112
Same weights, converted vs ibm-granite/granite-4.0-350m-base. Same weights stored in another dtype (BF16 → BF16/F32), plus 84 new tensors.
Tensors changed: Embeddings 0/1, Norms 0/57, Attention 0/112