prithivMLmods/Bootes-Xuange-Qwen-14B
Full fine-tune vs prithivMLmods/Galactic-Qwen-14B-Exp1. Fine-tune: 100% of the weights changed, across 48 of 48 layers.
Tensors changed: Norms 97/97, MLP 144/144, Attention 336/336
3 derivatives checked
- mradermacher/Bootes-Xuange-Qwen-14B-i1-GGUF: Quantization
- csabakecskemeti/prithivMLmods.Bootes-Xuange-Qwen-14B-GGUF: Same weights, converted
- mradermacher/Bootes-Xuange-Qwen-14B-GGUF: Quantization
1 other repos hold byte-for-byte identical weight files.