---
license: mit
---


This classification model is based on [cointegrated/rubert-tiny2](https://huggingface.co/cointegrated/rubert-tiny2).
The model should be used to produce relevance and specificity of the last message in the context of a dialog.

It is pretrained on corpus of dialog data from social networks and finetuned on [tinkoff-ai/context_similarity](https://huggingface.co/tinkoff-ai/context_similarity). 
The performance of the model on validation split [tinkoff-ai/context_similarity](https://huggingface.co/tinkoff-ai/context_similarity) (with the best thresholds for validation samples):

<table>
    <thead>
        <tr>
            <td colspan="2"><center>relevance</center></td>
            <td colspan="2"><center>specificity</center></td>
        </tr>
    </thead>
    <tbody>
        <tr>
            <td><center>f0.5</center></td>
            <td><center>roc-auc</center></td>
            <td><center>f0.5</center></td>
            <td><center>roc-auc</center></td>
        </tr>
        <tr>
            <td><center>0.82</center></td>
            <td><center>0.74</center></td>
            <td><center>0.81</center></td>
            <td><center>0.8</center></td>
        </tr>
    </tbody>
</table>

The model can be loaded as follows:

```python
# pip install transformers
from transformers import AutoTokenizer, AutoModel
tokenizer = AutoTokenizer.from_pretrained("tinkoff-ai/context_similarity")
model = AutoModel.from_pretrained("tinkoff-ai/context_similarity")
# model.cuda()
```