mergekit-community/JAJUKA-WEWILLNEVERFORGETYOU-3B

Full fine-tune vs Hastagaras/L3.2-JametMini-3B-MK.III. Fine-tune: 100% of the weights changed, across 28 of 28 layers.

Tensors changed: Embeddings 1/1, Norms 24/57, MLP 84/84, Attention 112/112

1 derivatives checked

• mradermacher/JAJUKA-WEWILLNEVERFORGETYOU-3B-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse