Instructions to use AcademiaSD/MiniMax-H3-NF4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use AcademiaSD/MiniMax-H3-NF4 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("AcademiaSD/MiniMax-H3-NF4", 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
Download text_encoder/metadata.json from AcademiaSD/MiniMax-H3-NF4: direct link, hf CLI and curl.
- Browser
- Download file 341 Bytes
-
https://huggingface.co/AcademiaSD/MiniMax-H3-NF4/resolve/main/text_encoder/metadata.json
- Command line
-
hf download hf://AcademiaSD/MiniMax-H3-NF4/text_encoder/metadata.json
-
curl -L -o metadata.json https://huggingface.co/AcademiaSD/MiniMax-H3-NF4/resolve/main/text_encoder/metadata.json
341 Bytes
| { | |
| "format": "MiniMax-H3-NF4", | |
| "version": 1, | |
| "component_name": "text_encoder", | |
| "component_type": "text_encoder", | |
| "quant_type": "nf4", | |
| "compute_dtype": "bfloat16", | |
| "total_linear": 565, | |
| "quantized": 565, | |
| "unquantized": 0, | |
| "incremental": true, | |
| "other": 321, | |
| "nonlinear_export": "5b_export_nonlinear_NF4.py" | |
| } |