Sentence Similarity
sentence-transformers
PyTorch
Safetensors
Transformers
Russian
English
roberta
feature-extraction
russian
fill-mask
pretraining
embeddings
masked-lm
tiny
text-embeddings-inference
Instructions to use mlsa-iai-msu-lab/sci-rus-tiny with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use mlsa-iai-msu-lab/sci-rus-tiny with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("mlsa-iai-msu-lab/sci-rus-tiny") 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 mlsa-iai-msu-lab/sci-rus-tiny with Transformers:
# Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("mlsa-iai-msu-lab/sci-rus-tiny") model = AutoModel.from_pretrained("mlsa-iai-msu-lab/sci-rus-tiny", device_map="auto") - Inference
- Notebooks
- Google Colab
- Kaggle
Commit ·
48413d8
1
Parent(s): 228e636
Upload config.json
Browse files- 1_Pooling/config.json +8 -0
1_Pooling/config.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"word_embedding_dimension": 312,
|
| 3 |
+
"pooling_mode": "mean",
|
| 4 |
+
"pooling_mode_cls_token": false,
|
| 5 |
+
"pooling_mode_mean_tokens": true,
|
| 6 |
+
"pooling_mode_max_tokens": false,
|
| 7 |
+
"pooling_mode_mean_sqrt_len_tokens": false
|
| 8 |
+
}
|