README.md

metadata

tags: autotrain
language: ar
widget:
  - text: I love AutoTrain 🤗
datasets:
  - zenkri/autotrain-data-Arabic_Poetry_by_Subject-1d8ba412
co2_eq_emissions: 0.06170374019107819

Model Trained Using AutoTrain

• Problem type: Multi-class Classification
• Model ID: 920730227
• CO2 Emissions (in grams): 0.06170374019107819

Validation Metrics

• Loss: 0.5905918478965759
• Accuracy: 0.8687837028160575
• Macro F1: 0.7777187122151491
• Micro F1: 0.8687837028160575
• Weighted F1: 0.8673230166815299
• Macro Precision: 0.796117563625016
• Micro Precision: 0.8687837028160575
• Weighted Precision: 0.8692944353097692
• Macro Recall: 0.7732013751753718
• Micro Recall: 0.8687837028160575
• Weighted Recall: 0.8687837028160575

Usage

You can use cURL to access this model:

$ curl -X POST -H "Authorization: Bearer YOUR_API_KEY" -H "Content-Type: application/json" -d '{"inputs": "I love AutoTrain"}' https://api-inference.huggingface.co/models/zenkri/autotrain-Arabic_Poetry_by_Subject-920730227

Or Python API:

from transformers import AutoModelForSequenceClassification, AutoTokenizer

model = AutoModelForSequenceClassification.from_pretrained("zenkri/autotrain-Arabic_Poetry_by_Subject-920730227", use_auth_token=True)

tokenizer = AutoTokenizer.from_pretrained("zenkri/autotrain-Arabic_Poetry_by_Subject-920730227", use_auth_token=True)

inputs = tokenizer("I love AutoTrain", return_tensors="pt")

outputs = model(**inputs)