QuantFactory/granite-3.1-3b-a800m-instruct-GGUF
Full fine-tune vs ibm-granite/granite-3.1-3b-a800m-base. QuantFactory/granite-3.1-3b-a800m-instruct-GGUF is a GGUF (Q8_0) of different weights. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: other 64/64, Norms 65/65, Attention 128/128