Instructions to use zerofata/MS3.2-PaintedFantasy-v2-24B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use zerofata/MS3.2-PaintedFantasy-v2-24B with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("zerofata/MS3.2-PaintedFantasy-v2-24B", dtype="auto") - Notebooks
- Google Colab
- Kaggle
Nothing but praise, this is my favorite 24B
#5
by TravelingMan - opened
I've tried a lot of fantastic finetunes and merges, but this one has just been incredible for the way I use it. I don't have anything specific to add that hasn't already been said in other threads, I just wanted to leave a comment of appreciation.
My hardware is humble. I only have 12GB of VRAM, but I can still manage 16K context with the iQ3_XSS quantization, and even at that lowly level it's been fantastic. I use the recommended settings on the Model Card page. It's replaced all my 12Bs and my other 24B models. Thank you!
Awesome! Thank you for the positive feedback.