Text Classification
Laya
Safetensors
Portuguese
system-one
decision-model
football
soccer
sports-analytics
commentary
brazilian-portuguese
Instructions to use LucasRabay/lance-a-laya with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Laya
How to use LucasRabay/lance-a-laya with Laya:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
Download thresholds.json from LucasRabay/lance-a-laya: direct link, hf CLI and curl.
- Browser
- Download file 483 Bytes
-
https://huggingface.co/LucasRabay/lance-a-laya/resolve/main/thresholds.json
- Command line
-
hf download hf://LucasRabay/lance-a-laya/thresholds.json
-
curl -L -o thresholds.json https://huggingface.co/LucasRabay/lance-a-laya/resolve/main/thresholds.json
483 Bytes
| { | |
| "thresholds": { | |
| "goal": 0.9808, | |
| "big_chance": 0.6964, | |
| "controversy": 0.04, | |
| "card": 0.9794 | |
| }, | |
| "intensity": "argmax over [calm, building, peak]", | |
| "rule": "answer yes when the calibrated probability (answers[q]['noul']) >= threshold", | |
| "chosen_on": "validation matches bra-sui-2022 and eng-fra-2022, with calibration.json applied", | |
| "note": "calibrated probabilities top out near 0.98 and are rounded to 4 decimals, so thresholds near the top are brittle" | |
| } | |