glogwa68/granite-4.0-h-1b-DISTILL-glm-4.7-think

Full fine-tune vs ibm-granite/granite-4.0-h-1b. Fine-tune: 100% of the weights changed, across 40 of 40 layers.

Tensors changed: Embeddings 1/1, Norms 73/117, other 220/252, MLP 80/80, Attention 16/16

1 derivatives checked

• glogwa68/granite-4.0-h-1b-DISTILL-glm-4.7-think-GGUF: Not comparable yet

On the Hub · Downloads on Model Pulse