mergekit-community/MN-Slush-Wayfarer

Full fine-tune vs LatitudeGames/Wayfarer-12B. Fine-tune: 97% of the weights changed, across 32 of 32 layers.

Tensors changed: Norms 34/65, MLP 93/96, Attention 124/128

2 derivatives checked

• mradermacher/MN-Slush-Wayfarer-i1-GGUF: Quantization
• mradermacher/MN-Slush-Wayfarer-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse