DevQuasar-8/ibm-granite.granite-20b-functioncalling-GGUF

Same weights, converted vs ibm-granite/granite-20b-functioncalling. Same weights stored in another dtype (BF16 → F16/F32).

Tensors changed: Attention 0/208, Norms 0/210, MLP 0/208, Embeddings 0/2

On the Hub · Downloads on Model Pulse