QuantFactory/mergekit-slerp-zgbgjeh-GGUF
Full fine-tune vs dat-lequoc/fast-apply-v0.2-qwen2.5-Coder-7B-ft. QuantFactory/mergekit-slerp-zgbgjeh-GGUF is a GGUF (Q8_0) of different weights. Fine-tune: 100% of the weights changed, across 28 of 28 layers.
Tensors changed: Embeddings 1/1, Norms 52/57, MLP 84/84, Attention 190/196, lm_head 1/1