powermove72/Granite-3.3-2B-Avg

Full fine-tune vs ibm-granite/granite-3.3-2b-instruct. Fine-tune: 100% of the weights changed, across 40 of 40 layers.

Tensors changed: Norms 81/81, MLP 120/120, Attention 160/160

1 derivatives checked

• mradermacher/Granite-3.3-2B-Avg-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse