aixonlab/RocRacoon-3b

Full fine-tune vs microsoft/Phi-3-mini-128k-instruct. Fine-tune: 100% of the weights changed, across 32 of 32 layers.

Tensors changed: Norms 65/65, MLP 64/64, Attention 64/64

1 derivatives checked

• mradermacher/RocRacoon-3b-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse