Aratako/Ninja-v1-RP-expressive-breadcrumbs

Full fine-tune vs Aratako/Ninja-v1-RP. Fine-tune: 100% of the weights changed, across 32 of 32 layers.

Tensors changed: Embeddings 1/1, Norms 61/65, MLP 96/96, Attention 128/128, lm_head 1/1

1 derivatives checked

• Aratako/Ninja-v1-RP-expressive-breadcrumbs-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse