QuantFactory/Qwen2.5-Coder-7B-3x-Instruct-TIES-v1.0-GGUF
Full fine-tune vs Etherll/Qwen2.5-Coder-7B-Instruct-Ties. QuantFactory/Qwen2.5-Coder-7B-3x-Instruct-TIES-v1.0-GGUF is a GGUF (Q8_0) of different weights. Fine-tune: 100% of the weights changed, across 28 of 28 layers.
Tensors changed: Norms 15/57, MLP 84/84, Attention 170/196