metadata
license: mit
widget:
- text: >-
привет[SEP]привет![SEP]как дела?[RESPONSE_TOKEN]да, супер, вот только
проснулся
This classification model is based on 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. The performance of the model on validation split tinkoff-ai/context_similarity (with the best thresholds for validation samples):
| f0.5 | ROC AUC | |
|---|---|---|
| relevance | 0.82 | 0.74 |
| specificity | 0.81 | 0.8 |
The model can be loaded as follows:
# 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()