Sentence Similarity
Transformers
PyTorch
Safetensors
sentence-transformers
English
Russian
xlm-roberta
feature-extraction
mteb
retrieval
retriever
pruned
e5
Eval Results (legacy)
text-embeddings-inference
Instructions to use d0rj/e5-large-en-ru with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use d0rj/e5-large-en-ru with Transformers:
# Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("d0rj/e5-large-en-ru") model = AutoModel.from_pretrained("d0rj/e5-large-en-ru") - sentence-transformers
How to use d0rj/e5-large-en-ru with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("d0rj/e5-large-en-ru") sentences = [ "That is a happy person", "That is a happy dog", "That is a very happy person", "Today is a sunny day" ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [4, 4] - Notebooks
- Google Colab
- Kaggle
Method for pruning
#3
by DiTy - opened
You said that you used an pruned dictionary from a multilingual model.
- Tell me how you shortened the dictionary (what is your method and how you did it)
- and whether there was training with a new dictionary and if so, how (at least briefly)
Thank you in advance for the answer.
- The dictionary has been shortened by the method described in this article by David Dale;
- After that, I did not finish training the model in any way
DiTy changed discussion status to closed