Text Classification
Transformers
PyTorch
TensorFlow
JAX
Safetensors
Russian
bert
sentiment-analysis
multi-class-classification
sentiment analysis
rubert
sentiment
tiny
russian
multiclass
classification
text-embeddings-inference
Instructions to use seara/rubert-tiny2-russian-sentiment with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use seara/rubert-tiny2-russian-sentiment with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="seara/rubert-tiny2-russian-sentiment")# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("seara/rubert-tiny2-russian-sentiment") model = AutoModelForSequenceClassification.from_pretrained("seara/rubert-tiny2-russian-sentiment", device_map="auto") - Inference
- Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -65,11 +65,11 @@ This model was trained on the union of the following datasets:
|
|
| 65 |
|
| 66 |
An overview of the training data can be found on [S. Smetanin Github repository](https://github.com/sismetanin/sentiment-analysis-in-russian).
|
| 67 |
|
| 68 |
-
__Download links for all Russian sentiment datasets collected by Smetanin can be found in this [repository](https://github.com/searayeah/russian-sentiment-
|
| 69 |
|
| 70 |
## Training
|
| 71 |
|
| 72 |
-
Training were done in this [project](https://github.com/searayeah/
|
| 73 |
|
| 74 |
```yaml
|
| 75 |
tokenizer.max_length: 512
|
|
|
|
| 65 |
|
| 66 |
An overview of the training data can be found on [S. Smetanin Github repository](https://github.com/sismetanin/sentiment-analysis-in-russian).
|
| 67 |
|
| 68 |
+
__Download links for all Russian sentiment datasets collected by Smetanin can be found in this [repository](https://github.com/searayeah/russian-sentiment-emotion-datasets).__
|
| 69 |
|
| 70 |
## Training
|
| 71 |
|
| 72 |
+
Training were done in this [project](https://github.com/searayeah/bert-russian-sentiment-emotion) with this parameters:
|
| 73 |
|
| 74 |
```yaml
|
| 75 |
tokenizer.max_length: 512
|