savasy

/

bert-base-turkish-sentiment-cased

like 33

Output of conversion script (to be able to use it on mobile using CoreML):

- Core ML model is classifier, validating output
        -[✓] predicted class negative matches negative
        -[✓] number of classes 2 matches 2
        -[✓] all values close (atol: 0.0001)
All good, model saved at: bert-base-turkish-sentiment-cased/Model.mlpackage