Skip to content

EthenEthenEthen

LoginPlatformTry Ethen

Open Source Model Profile · cointegrated

rubert-tiny2-cedr-emotion-detection

rubert-tiny2-cedr-emotion-detection is a 29.2M-parameter BERT classifier from cointegrated. Its model card documents multilabel Russian emotion classification trained on the CEDR dataset.

Publisher
cointegrated
Task
text-classification
Model type
bert
License
Unknown
Library
transformers
Publication status
Accepted · not indexed

Model overview

rubert-tiny2-cedr-emotion-detection is published by cointegrated as a BERT-based text-classification model. The captured configuration identifies BertForSequenceClassification and Safetensors metadata reports 29197694 parameters. According to the model card, it fine-tunes cointegrated/rubert-tiny2 for multilabel emotion classification in Russian sentences on the CEDR dataset.

Recorded capabilities

29.2M BERT scale

Captured config identifies BertForSequenceClassification and Safetensors metadata reports 29197694 parameters.

Russian multilabel emotion task

According to the model card, the model classifies emotions in Russian sentences as multilabel output, trained on the CEDR dataset.

Documented Adam training

According to the model card, training ran Adam for 40 epochs at learning rate 1e-5 with batch size 64.

Publisher-reported AUC and F1

The captured card text reports per-label AUC and micro/macro F1 on the test set; these are publisher figures, not Ethen measurements.

Use cases in the source record

  • Multilabel emotion classification of Russian sentences where multiple emotions may co-occur.
  • Russian sentiment and emotion-analysis pipelines evaluated against the card's reported AUC and F1 figures.

Limitations and unknowns

  • No license value was extracted from this record.
  • Quality figures are publisher-reported test values captured in the card text, not independently measured or verified by Ethen.
  • Provider state is historical snapshot data, not independently refreshed current availability.

Source and provenance

Source: cointegrated/rubert-tiny2-cedr-emotion-detection

Captured: Unknown. Processed: 2026-09-07T19:34:42.598069+00:00.

This is the cointegrated/rubert-tiny2 model fine-tuned for classification of emotions in Russian sentences. The task is multilabel classification, because one sentence can contain multiple emotions. The model on the CEDR dataset described in the paper "Data-Driven Model for Emotion Detection in Russian Texts" by Sboev et al. The model has been trained with Adam optimizer for 40 epochs with learning rate 1e-5 and batch size 64 in this notebook . The quality of the predicted probabilities on the test dataset is the following: label no emotion joy sadness surprise fear anger mean mean (emotions) AUC 0.9286 0.9512 0.9564 0.8908 0.8955 0…

F001F002F003F004F005F006F008F009F010F011F012F013