Instructions to use FriendliAI/Keye-VL-8B-Preview with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use FriendliAI/Keye-VL-8B-Preview with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("FriendliAI/Keye-VL-8B-Preview", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download processor_config.json from FriendliAI/Keye-VL-8B-Preview: direct link, hf CLI and curl.
- Browser
- Download file 115 Bytes
-
https://huggingface.co/FriendliAI/Keye-VL-8B-Preview/resolve/main/processor_config.json
- Command line
-
hf download hf://FriendliAI/Keye-VL-8B-Preview/processor_config.json
-
curl -L -o processor_config.json https://huggingface.co/FriendliAI/Keye-VL-8B-Preview/resolve/main/processor_config.json
115 Bytes
| { | |
| "auto_map": { | |
| "AutoProcessor": "processing_keye.KeyeProcessor" | |
| }, | |
| "processor_class": "KeyeProcessor" | |
| } | |