Statuo/LemonWizardv3

Full fine-tune vs KatyTheCutie/LemonadeRP-4.5.3. Fine-tune: 90% of the weights changed, across 30 of 32 layers.

Tensors changed: Embeddings 0/1, Norms 21/65, MLP 90/96, Attention 120/128, lm_head 0/1

1 derivatives checked

• mradermacher/LemonWizardv3-GGUF: Quantization

On the Hub · Downloads on Model Pulse