README.md

metadata

tags: autonlp
language: en
widget:
  - text: I love AutoNLP 🤗
datasets:
  - philschmid/autonlp-data-banking77_vs_comprehend

Model Trained Using AutoNLP

• Problem type: Multi-class Classification
• Model ID: 3102256

Validation Metrics

• Loss: 0.27382662892341614
• Accuracy: 0.935064935064935
• Macro F1: 0.934939412967268
• Micro F1: 0.935064935064935
• Weighted F1: 0.934939412967268
• Macro Precision: 0.9372295644352715
• Micro Precision: 0.935064935064935
• Weighted Precision: 0.9372295644352717
• Macro Recall: 0.9350649350649349
• Micro Recall: 0.935064935064935
• Weighted Recall: 0.935064935064935

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/philschmid/autonlp-banking77_vs_comprehend-3102256

Or Python API:

from transformers import AutoModelForSequenceClassification, AutoTokenizer

model = AutoModelForSequenceClassification.from_pretrained("philschmid/autonlp-banking77_vs_comprehend-3102256", use_auth_token=True)

tokenizer = AutoTokenizer.from_pretrained("philschmid/autonlp-banking77_vs_comprehend-3102256", use_auth_token=True)

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

outputs = model(**inputs)