ibm-granite/granite-20b-code-instruct-8k-GGUF
Full fine-tune vs ibm-granite/granite-20b-code-base-8k. ibm-granite/granite-20b-code-instruct-8k-GGUF is a GGUF (Q4_K_M) of different weights. Fine-tune: 100% of the weights changed, across 52 of 52 layers.
Tensors changed: Attention 208/208, Norms 199/210, MLP 208/208, Embeddings 2/2