bunnycore/Qwen-7B-MixLow
Full fine-tune vs bunnycore/FuseQwQen-7B. Fine-tune: 100% of the weights changed, across 28 of 28 layers.
Tensors changed: Norms 57/57, MLP 84/84, Attention 196/196
1 derivatives checked
- mradermacher/Qwen-7B-MixLow-GGUF: Same weights, converted