Text Classification
Transformers
TensorBoard
Safetensors
Russian
bert
Generated from Trainer
news
russian
media
Instructions to use data-silence/frozen_news_classifier_ft with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use data-silence/frozen_news_classifier_ft with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="data-silence/frozen_news_classifier_ft")# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("data-silence/frozen_news_classifier_ft") model = AutoModelForSequenceClassification.from_pretrained("data-silence/frozen_news_classifier_ft") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -28,12 +28,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 28 |
|
| 29 |
# Model description
|
| 30 |
|
| 31 |
-
The goal of this model was to create a universal model for categorizing Russian-language news that would preserve the ability of the basic LaBSE model to generate multi-lingual text embeddings in a single vector space.
|
| 32 |
-
|
| 33 |
-
|
| 34 |
-
# frozen_news_classifier_ft
|
| 35 |
-
|
| 36 |
This model is a fine-tuned version of [sentence-transformers/LaBSE](https://huggingface.co/sentence-transformers/LaBSE) on my [news dataset](https://huggingface.co/datasets/data-silence/rus_news_classifier).
|
|
|
|
| 37 |
The learning news dataset is a well-balanced sample of recent news from the last five years.
|
| 38 |
|
| 39 |
It achieves the following results on the evaluation set:
|
|
|
|
| 28 |
|
| 29 |
# Model description
|
| 30 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 31 |
This model is a fine-tuned version of [sentence-transformers/LaBSE](https://huggingface.co/sentence-transformers/LaBSE) on my [news dataset](https://huggingface.co/datasets/data-silence/rus_news_classifier).
|
| 32 |
+
The goal of this model was to create a universal model for categorizing Russian-language news that would preserve the ability of the basic LaBSE model to generate multi-lingual text embeddings in a single vector space.
|
| 33 |
The learning news dataset is a well-balanced sample of recent news from the last five years.
|
| 34 |
|
| 35 |
It achieves the following results on the evaluation set:
|