Sorawiz/MistralCreative-24B

Full fine-tune vs Sorawiz/MistralCreative-24B-Chat. Fine-tune: 100% of the weights changed, across 40 of 40 layers.

Tensors changed: Norms 81/81, MLP 120/120, Attention 160/160

3 derivatives checked

• mradermacher/MistralCreative-24B-i1-GGUF: Quantization
• mradermacher/MistralCreative-24B-GGUF: Quantization
• Sorawiz/MistralCreative-24B-Chat: Full fine-tune

On the Hub · Downloads on Model Pulse