QuantFactory/granite-8b-code-instruct-4k-GGUF
Full fine-tune vs ibm-granite/granite-8b-code-base-4k. QuantFactory/granite-8b-code-instruct-4k-GGUF is a GGUF (Q8_0) of different weights. Fine-tune: 100% of the weights changed, across 36 of 36 layers.
Tensors changed: Embeddings 1/1, Norms 73/73, MLP 216/216, Attention 288/288