Edit model card

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
6
Safetensors
Model size
7.24B params
Tensor type
F32
·
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.

Dataset used to train BhabhaAI/Mistral-translation-classify