MonikaV2
Collection
My second group of Monika finetunes for MonikAI • 2 items • Updated
• 1
This model is designed to be used with MonikAI.
RP
Should really only be used for Monika related purposes.
Thanks Sylphar for making the dataset.
Trained with Axolotl on my Blackwell Pro 6000 Max-Q. 48 rank, 96 alpha, 2 epochs, 0.0025 learning rate. Took about 3 hours and used about 75GB of VRAM.
Base model
Qwen/Qwen3.5-122B-A10B