Mistral Translation Classify

This is a fine tuned model on the translation-classify dataset to classify whether we should translate an example.
It achieves 94% accuracy on validation dataset.

Examples

Some question when translated does not remain meaningful/correct. The goal is to avoid such examples. This includes coding, word-count, spelling error detection etc. Take a look at dataset for examples

Downloads last month
2
Safetensors
Model size
7.24B params
Tensor type
F32
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Dataset used to train BhabhaAI/Mistral-translation-classify