Aleteian/Wayfinder

Full fine-tune vs Aleteian/saiga-vikhr-dostoevsky-ru-mn-12b. Fine-tune: 100% of the weights changed, across 40 of 40 layers.

Tensors changed: Norms 5/81, MLP 120/120, Attention 160/160

2 derivatives checked

• mradermacher/Wayfinder-i1-GGUF: Quantization
• mradermacher/Wayfinder-GGUF: Quantization

On the Hub · Downloads on Model Pulse