nisten/zelensky-78b
Full fine-tune vs Qwen/Qwen2.5-72B. Fine-tune: 100% of the weights changed, across 80 of 80 layers.
Tensors changed: MLP 240/240, Attention 560/560, Norms 160/161
2 derivatives checked
- mradermacher/zelensky-78b-i1-GGUF: Quantization
- mradermacher/zelensky-78b-GGUF: Quantization