ibm-granite/granite-4.0-tiny-preview-GGUF

Full fine-tune vs ibm-granite/granite-4.0-tiny-base-preview. ibm-granite/granite-4.0-tiny-preview-GGUF is a GGUF (F16) of different weights. Fine-tune: 100% of the weights changed, across 40 of 40 layers.

Tensors changed: other 80/80, Norms 81/81, MLP 40/40, Attention 16/16

On the Hub · Downloads on Model Pulse