Feature Extraction
sentence-transformers
Safetensors
Transformers
bert
fill-mask
learned sparse
opensearch
retrieval
passage-retrieval
document-expansion
bag-of-words
sparse-encoder
sparse
asymmetric
inference-free
splade
text-embeddings-inference
Instructions to use opensearch-project/opensearch-neural-sparse-encoding-multilingual-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use opensearch-project/opensearch-neural-sparse-encoding-multilingual-v1 with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("opensearch-project/opensearch-neural-sparse-encoding-multilingual-v1") 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 opensearch-project/opensearch-neural-sparse-encoding-multilingual-v1 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="opensearch-project/opensearch-neural-sparse-encoding-multilingual-v1")# Load model directly from transformers import AutoTokenizer, AutoModelForMaskedLM tokenizer = AutoTokenizer.from_pretrained("opensearch-project/opensearch-neural-sparse-encoding-multilingual-v1") model = AutoModelForMaskedLM.from_pretrained("opensearch-project/opensearch-neural-sparse-encoding-multilingual-v1", device_map="auto") - Inference
- Notebooks
- Google Colab
- Kaggle
| { | |
| "types": { | |
| "query_0_SparseStaticEmbedding": "sentence_transformers.sparse_encoder.models.SparseStaticEmbedding.SparseStaticEmbedding", | |
| "": "sentence_transformers.sparse_encoder.models.MLMTransformer.MLMTransformer", | |
| "document_1_SpladePooling": "sentence_transformers.sparse_encoder.models.SpladePooling.SpladePooling" | |
| }, | |
| "structure": { | |
| "query": [ | |
| "query_0_SparseStaticEmbedding" | |
| ], | |
| "document": [ | |
| "", | |
| "document_1_SpladePooling" | |
| ] | |
| }, | |
| "parameters": { | |
| "default_route": "document", | |
| "allow_empty_key": true | |
| } | |
| } |