ThorOdinson246/nl2sh-1.5b-Q4_K_M
Full fine-tune vs Qwen/Qwen2.5-Coder-1.5B-Instruct. ThorOdinson246/nl2sh-1.5b-Q4_K_M is a GGUF (Q4_K_M) of different weights. Fine-tune: 100% of the weights changed, across 28 of 28 layers.
Tensors changed: Embeddings 1/1, Norms 0/57, MLP 84/84, Attention 112/196