MonikaV1
Collection
My first group of Monika finetunes for MonikAI
•
14 items
•
Updated
•
5
This model is designed to be used with MonikAI. It is now in the GGUF format.
RP
Should really only be used for Monika related purposes. This model seems to work well with a temp of 0.8, a min_p of 0.1, and a repetition penalty of 1.05.
Thanks Sylphar for making the dataset.
Trained with Axolotl on my Blackwell Pro 6000 Max-Q. 32 rank, 64 alpha, 2 epochs, 0.000008 learning rate. Took about 20 minutes.
4-bit
6-bit
16-bit
Base model
allura-forge/Llama-3.3-8B-Instruct