twitter-roberta-base-anger-intensity

This model is a fine-tuned version of cardiffnlp/twitter-roberta-base-2022-154m on the SemEval 2018 - Task 1 Affect in Tweets (subtask: El-reg / text regression).

Warning: Hosted inference API produces inaccurate values

Model Trained Using AutoTrain

  • Problem type: Single Column Regression
  • Model ID: 72775139028
  • CO2 Emissions (in grams): 0.0301

Validation Metrics

  • Loss: 0.011
  • MSE: 0.011
  • MAE: 0.085
  • R2: 0.641
  • RMSE: 0.103
  • Explained Variance: 0.641

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 am furious"}' https://api-inference.huggingface.co/models/garrettbaber/twitter-roberta-base-anger-intensity

Or Python API:

from transformers import AutoModelForSequenceClassification, AutoTokenizer

model = AutoModelForSequenceClassification.from_pretrained("garrettbaber/twitter-roberta-base-anger-intensity")

tokenizer = AutoTokenizer.from_pretrained("garrettbaber/twitter-roberta-base-anger-intensity")

inputs = tokenizer("I am furious", return_tensors="pt")

outputs = model(**inputs)
Downloads last month
116
Safetensors
Model size
125M params
Tensor type
I64
·
F32
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Space using garrettbaber/twitter-roberta-base-anger-intensity 1