QuantFactory/Qwen2.5-Coder-14B-Instruct-GGUF
Full fine-tune vs Qwen/Qwen2.5-Coder-14B. QuantFactory/Qwen2.5-Coder-14B-Instruct-GGUF is a GGUF (Q8_0) of different weights. Fine-tune: 100% of the weights changed, across 48 of 48 layers.
Tensors changed: Embeddings 1/1, Norms 97/97, MLP 144/144, Attention 336/336, lm_head 1/1