Instructions to use XiaomiMiMo/MiMo-7B-MTPs with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use XiaomiMiMo/MiMo-7B-MTPs with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="XiaomiMiMo/MiMo-7B-MTPs", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("XiaomiMiMo/MiMo-7B-MTPs", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download configuration_mimo.py from XiaomiMiMo/MiMo-7B-MTPs: direct link, hf CLI and curl.
- Browser
- Download file 376 Bytes
-
https://huggingface.co/XiaomiMiMo/MiMo-7B-MTPs/resolve/main/configuration_mimo.py
- Command line
-
hf download hf://XiaomiMiMo/MiMo-7B-MTPs/configuration_mimo.py
-
curl -L -o configuration_mimo.py https://huggingface.co/XiaomiMiMo/MiMo-7B-MTPs/resolve/main/configuration_mimo.py
376 Bytes
| from transformers.models.qwen2.configuration_qwen2 import Qwen2Config | |
| class MiMoConfig(Qwen2Config): | |
| model_type = "mimo" | |
| def __init__( | |
| self, | |
| *args, | |
| num_nextn_predict_layers=0, | |
| **kwargs | |
| ): | |
| self.num_nextn_predict_layers = num_nextn_predict_layers | |
| super().__init__( | |
| *args, | |
| **kwargs, | |
| ) | |