Instructions to use chaoliangUNSW/Jev-Style-Cascade-9B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- jev-style
How to use chaoliangUNSW/Jev-Style-Cascade-9B with jev-style:
pip install "jev-style[torch]"
from jev_style import JevStyle, noul, choice js = JevStyle.from_pretrained("chaoliangUNSW/Jev-Style-Cascade-9B") out = js.decide("I was charged twice for one order.", { "billing": noul("This message is about billing."), "team": choice("Which team should handle it?", ["billing", "shipping", "tech"]), }) print(out["answers"]["team"]["choice"]) - Notebooks
- Google Colab
- Kaggle
Jev-Style-Cascade-9B: frozen cascade (Jev-Style-2B-Decision-v3 -> JevK5-9B), calibration record and evaluation
8c09135 verified Download cascade.json from chaoliangUNSW/Jev-Style-Cascade-9B: direct link, hf CLI and curl.
- Browser
- Download file 783 Bytes
-
https://huggingface.co/chaoliangUNSW/Jev-Style-Cascade-9B/resolve/main/cascade.json
- Command line
-
hf download hf://chaoliangUNSW/Jev-Style-Cascade-9B/cascade.json
-
curl -L -o cascade.json https://huggingface.co/chaoliangUNSW/Jev-Style-Cascade-9B/resolve/main/cascade.json
783 Bytes
| { | |
| "id": "jev-style-cascade-9b", | |
| "description": "Jev-Style 2B Decision v3 (in-process, PyTorch) -> JevK5-9B v0.3.3 by alibiserikbay (third party, Apache-2.0, in-process via allebee/jevk5); one threshold on normalized confidence", | |
| "tiers": [ | |
| { | |
| "name": "2b", | |
| "model_id": "jev-style-2b-decision-v3", | |
| "target": "local:2b-v3:torch", | |
| "dtype": "float32" | |
| }, | |
| { | |
| "name": "jevk5-9b", | |
| "model_id": "alibiserikbay/JevK5-9B", | |
| "target": "jevk5:alibiserikbay/JevK5-9B", | |
| "revision": "d6521a18a86999190e9d775c915af3d6d6772fc4" | |
| } | |
| ], | |
| "thresholds": [ | |
| 0.75 | |
| ], | |
| "confidence": "normalized_pmax", | |
| "frozen_utc": "2026-10-02T21:53:31Z", | |
| "calibration_sha256": "580962e4b2bc86b32b42731eda42536f57321c7d1ca9ac1e3b970bf7dbd7e2d2" | |
| } | |