Mungert/instinct-GGUF
Full fine-tune vs Qwen/Qwen2.5-Coder-7B. Mungert/instinct-GGUF is a GGUF (Q8_0) of different weights. Fine-tune: 93% of the weights changed, across 28 of 28 layers.
Tensors changed: Embeddings 0/1, Norms 55/57, MLP 84/84, Attention 196/196, lm_head 1/1