Lunzima/NQLSG-Qwen2.5-14B-MegaFusion
Full fine-tune vs Lunzima/NQLSG-Qwen2.5-14B-MegaFusion-TIES-1. Fine-tune: 100% of the weights changed, across 48 of 48 layers.
Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 86/97, MLP 144/144, Attention 335/336
2 derivatives checked
- mradermacher/NQLSG-Qwen2.5-14B-MegaFusion-i1-GGUF: Quantization
- mradermacher/NQLSG-Qwen2.5-14B-MegaFusion-GGUF: Quantization