README.md

metadata

tags: autonlp
language: unk
widget:
  - text: I love AutoNLP 🤗
datasets:
  - emekaboris/autonlp-data-new_tx
co2_eq_emissions: 3.842950628218143

Model Trained Using AutoNLP

• Problem type: Multi-class Classification
• Model ID: 607517182
• CO2 Emissions (in grams): 3.842950628218143

Validation Metrics

• Loss: 0.4033123552799225
• Accuracy: 0.8679706601466992
• Macro F1: 0.719846919916469
• Micro F1: 0.8679706601466993
• Weighted F1: 0.8622411469250695
• Macro Precision: 0.725309168791155
• Micro Precision: 0.8679706601466992
• Weighted Precision: 0.8604370906049568
• Macro Recall: 0.7216672806300003
• Micro Recall: 0.8679706601466992
• Weighted Recall: 0.8679706601466992

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 AutoNLP"}' https://api-inference.huggingface.co/models/emekaboris/autonlp-new_tx-607517182

Or Python API:

from transformers import AutoModelForSequenceClassification, AutoTokenizer

model = AutoModelForSequenceClassification.from_pretrained("emekaboris/autonlp-new_tx-607517182", use_auth_token=True)

tokenizer = AutoTokenizer.from_pretrained("emekaboris/autonlp-new_tx-607517182", use_auth_token=True)

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

outputs = model(**inputs)