README.md

metadata

tags:
  - autotrain
  - text-classification
language:
  - unk
widget:
  - text: I love AutoTrain 🤗
datasets:
  - sasha/autotrain-data-BERTBase-TweetEval
co2_eq_emissions:
  emissions: 0.07527533186093606

Model Trained Using AutoTrain

• Problem type: Multi-class Classification
• Model ID: 1281248997
• CO2 Emissions (in grams): 0.0753

Validation Metrics

• Loss: 0.605
• Accuracy: 0.743
• Macro F1: 0.719
• Micro F1: 0.743
• Weighted F1: 0.741
• Macro Precision: 0.735
• Micro Precision: 0.743
• Weighted Precision: 0.742
• Macro Recall: 0.708
• Micro Recall: 0.743
• Weighted Recall: 0.743

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/sasha/autotrain-BERTBase-TweetEval-1281248997

Or Python API:

from transformers import AutoModelForSequenceClassification, AutoTokenizer

model = AutoModelForSequenceClassification.from_pretrained("sasha/autotrain-BERTBase-TweetEval-1281248997", use_auth_token=True)

tokenizer = AutoTokenizer.from_pretrained("sasha/autotrain-BERTBase-TweetEval-1281248997", use_auth_token=True)

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

outputs = model(**inputs)