Instructions to use nikraf/directionality_probe with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use nikraf/directionality_probe with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="nikraf/directionality_probe", trust_remote_code=True)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("nikraf/directionality_probe", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
| def parse_modal_api_key(modal_api_key: str) -> tuple: | |
| cleaned = modal_api_key.strip() | |
| assert cleaned != "", "modal_api_key cannot be empty." | |
| assert ":" in cleaned, "modal_api_key must be provided as '<modal_token_id>:<modal_token_secret>'." | |
| token_id, token_secret = cleaned.split(":", 1) | |
| token_id = token_id.strip() | |
| token_secret = token_secret.strip() | |
| assert token_id != "", "modal_token_id parsed from modal_api_key is empty." | |
| assert token_secret != "", "modal_token_secret parsed from modal_api_key is empty." | |
| return token_id, token_secret | |