prithivMLmods/Sombrero-Opus-14B-Sm5
Full fine-tune vs Qwen/Qwen2.5-14B-Instruct. Fine-tune: 100% of the weights changed, across 48 of 48 layers.
Tensors changed: Norms 97/97, MLP 144/144, Attention 336/336
2 derivatives checked
- mradermacher/Sombrero-Opus-14B-Sm5-i1-GGUF: Quantization
- mradermacher/Sombrero-Opus-14B-Sm5-GGUF: Quantization
1 other repos hold byte-for-byte identical weight files.