Instructions to use magibu/Altus with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use magibu/Altus with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("magibu/Altus", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download NOTICE from magibu/Altus: direct link, hf CLI and curl.
- Browser
- Download file 536 Bytes
-
https://huggingface.co/magibu/Altus/resolve/main/NOTICE
- Command line
-
hf download hf://magibu/Altus/NOTICE
-
curl -L -o NOTICE https://huggingface.co/magibu/Altus/resolve/main/NOTICE
536 Bytes
| Altus Tokenizer | |
| Copyright 2026 Magibu AI Research | |
| This distribution contains tokenizer and processor artifacts derived from | |
| google/gemma-4-31B-it, distributed under the Apache License, Version 2.0: | |
| https://huggingface.co/google/gemma-4-31B-it | |
| Magibu AI Research modified the vocabulary and merge rules by integrating the | |
| Magibu Turkish-focused BPE vocabulary, added an ID mapping artifact, localized | |
| the chat template, and applied the Altus product identity. | |
| This distribution contains no model weights from the upstream repository. | |