Mungert/granite-3.0-8b-instruct-GGUF
Full fine-tune vs ibm-granite/granite-3.0-8b-base. Mungert/granite-3.0-8b-instruct-GGUF is a GGUF (Q8_0) of different weights. Fine-tune: 100% of the weights changed, across 40 of 40 layers.
Tensors changed: Norms 81/81, MLP 120/120, Attention 160/160