Text Classification
Transformers
Safetensors
Arabic
jeb
system-one
calibrated-decisions
classification
routing
scoring
guardrails
moderation
arabic
reinforcement-learning
commercial-use
Instructions to use IJyad/jeb with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use IJyad/jeb with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="IJyad/jeb")# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("IJyad/jeb", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download config.json from IJyad/jeb: direct link, hf CLI and curl.
- Browser
- Download file 600 Bytes
-
https://huggingface.co/IJyad/jeb/resolve/main/config.json
- Command line
-
hf download hf://IJyad/jeb/config.json
-
curl -L -o config.json https://huggingface.co/IJyad/jeb/resolve/main/config.json
600 Bytes
| { | |
| "architectures": [ | |
| "ArabicDecisionModel" | |
| ], | |
| "encoder": "UBC-NLP/MARBERTv2", | |
| "head_layers": 2, | |
| "max_len": 512, | |
| "head_max_len": 192, | |
| "hidden_size": 768, | |
| "num_params": 178000000, | |
| "model_name": "jeb", | |
| "language": "ar", | |
| "question_types": [ | |
| "choice", | |
| "score", | |
| "noul" | |
| ], | |
| "confidence": "(n*peak - 1) / (n - 1)", | |
| "training": { | |
| "runs": 4, | |
| "shipped_run": 3, | |
| "benchmark_overall": 0.8738 | |
| }, | |
| "_note": "Root config for the Hugging Face Hub (download counting and tooling). The model itself is loaded with model.py; see README." | |
| } |