Xiaojian9992024/Qwen2.5-7B-MS-Destroyer
Full fine-tune vs HoangHa/Pensez-v0.1-e5. Fine-tune: 100% of the weights changed, across 28 of 28 layers.
Tensors changed: Norms 52/57, MLP 84/84, Attention 196/196
2 derivatives checked
- mradermacher/Qwen2.5-7B-MS-Destroyer-i1-GGUF: Quantization
- mradermacher/Qwen2.5-7B-MS-Destroyer-GGUF: Same weights, converted