Lunzima/NQLSG-Qwen2.5-14B-MegaFusion-v9.3
Full fine-tune vs Cran-May/tempmotacilla-cinerea-0308. Fine-tune: 100% of the weights changed, across 48 of 48 layers.
Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 97/97, MLP 144/144, Attention 336/336
3 derivatives checked
- mradermacher/NQLSG-Qwen2.5-14B-MegaFusion-v9.3-GGUF: Quantization
- Lunzima/NQLSG-Qwen2.5-14B-MegaFusion-v9.3-Coder: LoRA-style
- Lunzima/NQLSG-Qwen2.5-14B-MegaFusion-v9.4-Coder: LoRA-style