Sentence Similarity
sentence-transformers
PyTorch
Safetensors
Transformers
Russian
bert
pretraining
russian
fill-mask
embeddings
masked-lm
tiny
feature-extraction
text-embeddings-inference
Instructions to use cointegrated/rubert-tiny2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use cointegrated/rubert-tiny2 with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("cointegrated/rubert-tiny2") sentences = [ "The weather is lovely today.", "It's so sunny outside!", "He drove to the stadium." ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [3, 3] - Transformers
How to use cointegrated/rubert-tiny2 with Transformers:
# Load model directly from transformers import AutoTokenizer, AutoModelForPreTraining tokenizer = AutoTokenizer.from_pretrained("cointegrated/rubert-tiny2") model = AutoModelForPreTraining.from_pretrained("cointegrated/rubert-tiny2") - Inference
- Notebooks
- Google Colab
- Kaggle
Commit ·
a53f0af
1
Parent(s): 5add408
Update README.md
Browse files
README.md
CHANGED
|
@@ -14,7 +14,7 @@ license: mit
|
|
| 14 |
widget:
|
| 15 |
- text: "Миниатюрная модель для [MASK] разных задач."
|
| 16 |
---
|
| 17 |
-
This is an updated version of [cointegrated/rubert-tiny](https://huggingface.co/cointegrated/rubert-tiny): a small Russian BERT-based encoder with high-quality sentence embeddings.
|
| 18 |
|
| 19 |
The differences from the previous version include:
|
| 20 |
- a larger vocabulary: 83828 tokens instead of 29564;
|
|
|
|
| 14 |
widget:
|
| 15 |
- text: "Миниатюрная модель для [MASK] разных задач."
|
| 16 |
---
|
| 17 |
+
This is an updated version of [cointegrated/rubert-tiny](https://huggingface.co/cointegrated/rubert-tiny): a small Russian BERT-based encoder with high-quality sentence embeddings. This [post in Russian](https://habr.com/ru/post/669674/) gives more details.
|
| 18 |
|
| 19 |
The differences from the previous version include:
|
| 20 |
- a larger vocabulary: 83828 tokens instead of 29564;
|