wowbager/granite-cermat-cz-7b

Full fine-tune vs ibm-granite/granite-4.0-tiny-preview. Fine-tune: 98% of the weights changed, across 40 of 40 layers.

Tensors changed: Embeddings 1/1, other 339/372, Norms 106/117, MLP 80/80, Attention 16/16

3 derivatives checked

• mradermacher/granite-cermat-7b-i1-GGUF: Quantization
• mradermacher/granite-cermat-cz-7b-GGUF: Same weights, converted
• mradermacher/granite-cermat-7b-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse