bartowski/granite-34b-code-instruct-GGUF
Full fine-tune vs ibm-granite/granite-34b-code-base-8k. bartowski/granite-34b-code-instruct-GGUF is a GGUF (Q8_0) of different weights. Fine-tune: 100% of the weights changed, across 88 of 88 layers.
Tensors changed: Attention 352/352, Norms 354/354, MLP 352/352, Embeddings 2/2