Zero-Shot Classification
Transformers
Safetensors
Arabic
llama
feature-extraction
arabic
prompt-routing
router
text-generation-inference
Instructions to use oddadmix/Nawah-Router-v3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use oddadmix/Nawah-Router-v3 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("zero-shot-classification", model="oddadmix/Nawah-Router-v3")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("oddadmix/Nawah-Router-v3") model = AutoModel.from_pretrained("oddadmix/Nawah-Router-v3", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Commit History
-
Nawah-Router-v3: 52M, 0.9305 unseen lanes / 0.6976 unseen domains
Verified signatureTrained on the 233,720-row arabic-prompt-routing corpus with 12 routing axes. Adds an unseen_axis eval: two routing dimensions absent from training entirely.9f0cc33