Diwanshuydv/qwen2.5-3B-coder-Instruct-ft_q
Full fine-tune vs unsloth/Qwen2.5-Coder-3B-Instruct. Diwanshuydv/qwen2.5-3B-coder-Instruct-ft_q is a GGUF (Q8_0) of different weights. Fine-tune: 100% of the weights changed, across 36 of 36 layers.
Tensors changed: Embeddings 1/1, Norms 0/73, MLP 108/108, Attention 144/252