mrcuddle/Tiny-DarkLlama-OpenPlatypus

Full fine-tune vs mrcuddle/Tiny-DarkLlama. Fine-tune: 100% of the weights changed, across 22 of 22 layers.

Tensors changed: Norms 24/45, MLP 66/66, Attention 88/88

1 derivatives checked

• mradermacher/Tiny-DarkLlama-OpenPlatypus-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse