Lunzima/NQLSG-Qwen2.5-14B-MegaFusion-v8
Full fine-tune vs Lunzima/NQLSG-Qwen2.5-14B-MegaFusion-v3. 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
4 derivatives checked
- mradermacher/NQLSG-Qwen2.5-14B-MegaFusion-v8-GGUF: Quantization
- Lunzima/NQLSG-Qwen2.5-14B-MegaFusion-v8.7: Full fine-tune
- marcuscedricridia/etr1o-v1.2: Full fine-tune
- Lunzima/NQLSG-Qwen2.5-14B-OriginalFusion: Full fine-tune