DevQuasar-5/ibm-granite.granite-3b-code-instruct-128k-GGUF
Full fine-tune vs ibm-granite/granite-3b-code-instruct-128k. DevQuasar-5/ibm-granite.granite-3b-code-instruct-128k-GGUF is a GGUF (Q8_0) of different weights. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 1/1, Norms 0/65, MLP 96/192, Attention 192/256