metadata

tags:
  - text-regression
  - joy
  - emotion
  - emotion intensity
language:
  - en
widget:
  - text: I am elated!
datasets:
  - SemEval-2018-Task-1-Text-Regression-Task
co2_eq_emissions:
  emissions: 0.03988347977318191

twitter-roberta-base-joy-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: 72771139026
CO2 Emissions (in grams): 0.0399

Validation Metrics

Loss: 0.013
MSE: 0.013
MAE: 0.088
R2: 0.707
RMSE: 0.116
Explained Variance: 0.709

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 elated!"}' https://api-inference.huggingface.co/models/garrettbaber/twitter-roberta-base-joy-intensity

Or Python API:

from transformers import AutoModelForSequenceClassification, AutoTokenizer

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

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

inputs = tokenizer("I am elated!", return_tensors="pt")

outputs = model(**inputs)