Image Feature Extraction
Transformers
Safetensors
mimo26_vision
feature-extraction
vision
mimo
custom_code
Instructions to use immanuelpeter/MiMoViT-2.6-Pro with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use immanuelpeter/MiMoViT-2.6-Pro with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-feature-extraction", model="immanuelpeter/MiMoViT-2.6-Pro", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("immanuelpeter/MiMoViT-2.6-Pro", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download NOTICE from immanuelpeter/MiMoViT-2.6-Pro: direct link, hf CLI and curl.
- Browser
- Download file 557 Bytes
-
https://huggingface.co/immanuelpeter/MiMoViT-2.6-Pro/resolve/main/NOTICE
- Command line
-
hf download hf://immanuelpeter/MiMoViT-2.6-Pro/NOTICE
-
curl -L -o NOTICE https://huggingface.co/immanuelpeter/MiMoViT-2.6-Pro/resolve/main/NOTICE
557 Bytes
| Weights: XiaomiMiMo/MiMo-V2.6-Pro-RL at b61f21852680ee02a29e946e18cf8697f4844061. | |
| The pinned model card declares MIT; the upstream repository supplies no separate LICENSE file. | |
| LICENSE reproduces the standard MIT terms, with the Xiaomi copyright attribution. | |
| The extracted vision implementation retains its upstream Apache-2.0 header. | |
| See LICENSE-CODE for the Apache-2.0 terms. | |
| Only visual tensors are included. No language/audio weights. | |
| Standalone modification: omitted the three checkpoint-absent merger biases. All other vision arithmetic is preserved. | |