Instructions to use rootonchair/MiniMax-H3-nunchaku-lite-int4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use rootonchair/MiniMax-H3-nunchaku-lite-int4 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("rootonchair/MiniMax-H3-nunchaku-lite-int4", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
please update kernels build for torch==2.14
#2
by vladmandic - opened
as the title says, current stable version of torch is 2.14...
vladmandic changed discussion title from update kernels build for torch==2.14 to please update kernels build for torch==2.14
I just pushed the build for torch 2.14: https://huggingface.co/kernels/rootonchair/nunchaku-lite-kernels