mradermacher/Qwen2.5-Coder-7B-NEP-fix-GGUF
Full fine-tune vs lurf21/Qwen2.5-Coder-7B-NEP. mradermacher/Qwen2.5-Coder-7B-NEP-fix-GGUF is a GGUF (F16) of different weights. Fine-tune: 93% of the weights changed, across 28 of 28 layers.
Tensors changed: Embeddings 0/1, Norms 0/57, MLP 84/84, Attention 112/196, lm_head 1/1