Sorawiz/MistralCreative-24B-Chat
Full fine-tune vs Sorawiz/MistralCreative-24B. Fine-tune: 100% of the weights changed, across 40 of 40 layers.
Tensors changed: Norms 81/81, MLP 120/120, Attention 160/160
4 derivatives checked
- mradermacher/MistralCreative-24B-Chat-i1-GGUF: Quantization
- mradermacher/MistralCreative-24B-Chat-GGUF: Quantization
- Entropicengine/Trifecta-Max-24b: Full fine-tune
- Sorawiz/MistralCreative-24B: Full fine-tune