Aratako/Ninja-v1-RP

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

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

3 derivatives checked

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

On the Hub · Downloads on Model Pulse