Sentence Similarity
Safetensors
sentence-transformers
PyLate
modernbert
multi-vector
ColBERT
feature-extraction
multilingual
late-interaction
retrieval
pretrained
loss:Distillation
text-embeddings-inference
Instructions to use VAGOsolutions/SauerkrautLM-Multi-ModernColBERT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use VAGOsolutions/SauerkrautLM-Multi-ModernColBERT with sentence-transformers:
from pylate import models queries = [ "Which planet is known as the Red Planet?", "What is the largest planet in our solar system?", ] documents = [ ["Mars is the Red Planet.", "Venus is Earth's twin."], ["Jupiter is the largest planet.", "Saturn has rings."], ] model = models.ColBERT(model_name_or_path="VAGOsolutions/SauerkrautLM-Multi-ModernColBERT") queries_emb = model.encode(queries, is_query=True) docs_emb = model.encode(documents, is_query=False) - Notebooks
- Google Colab
- Kaggle
Add `do_query_expansion: false` to load without query expansion
#2
by tomaarsen HF Staff - opened
config_sentence_transformers.json
CHANGED
|
@@ -10,6 +10,7 @@
|
|
| 10 |
"query_prefix": "[Q] ",
|
| 11 |
"document_prefix": "[D] ",
|
| 12 |
"query_length": 32,
|
|
|
|
| 13 |
"document_length": 300,
|
| 14 |
"attend_to_expansion_tokens": false,
|
| 15 |
"skiplist_words": [
|
|
|
|
| 10 |
"query_prefix": "[Q] ",
|
| 11 |
"document_prefix": "[D] ",
|
| 12 |
"query_length": 32,
|
| 13 |
+
"do_query_expansion": false,
|
| 14 |
"document_length": 300,
|
| 15 |
"attend_to_expansion_tokens": false,
|
| 16 |
"skiplist_words": [
|