ufakai/ufakzeka-1

Full fine-tune vs ufakai/ufakzeka-1-base. Fine-tune: 100% of the weights changed, across 24 of 24 layers.

Tensors changed: Embeddings 1/1, Norms 97/97, MLP 72/72, Attention 96/96

1 derivatives checked

• ufakai/ufakzeka-1-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse