wepiqx/RINIQ-GGUF
Full fine-tune vs OrionLLM/OxCoder-9B. wepiqx/RINIQ-GGUF is a GGUF (Q38) of different weights. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 6/81, MLP 96/96, Attention 32/32