This model is a compact Late Interaction retriever that leverages:
Pretraining with over 8.2 billion tokens in a two-phase approach (4.6B multilingual + 3.6B English tokens). Knowledge Distillation from state-of-the-art reranker models during pretraining. Efficient architecture with 33M parameters – optimized for edge deployment while maintaining high performance.
Two-Phase Pretraining Strategy:
Advanced Knowledge Distillation: Learning from powerful reranker models throughout the pretraining process
Balanced Efficiency: With 33M parameters, achieving the sweet spot between performance and deployability
With 33 million parameters – that's less than 1/200th the size of some competing models – SauerkrautLM-Multi-ColBERT-33m represents efficient pretraining at scale:
This balanced architecture combined with pretraining creates a powerful foundation for downstream applications, offering superior performance compared to the 15M variant while remaining highly efficient.
Model: VAGOsolutions/SauerkrautLM-Multi-ColBERT-33m
Type: Pretrained foundation model for Late Interaction retrieval
Architecture: PyLate / ColBERT (Late Interaction)
Languages: Multilingual (optimized for 7 European languages: German, English, Spanish, French, Italian, Dutch, Portuguese)
License: Apache 2.0
Model Size: 33M parameters
Training Data: 8.2B tokens (4.6B multilingual + 3.6B English)
ColBERT(
(0): Transformer(CompressedModernBertModel)
(1): Dense(384 -> 128 dim, no bias)
)
Our 33M parameter model undergoes sophisticated two-phase pretraining:
Unlike typical pretraining, we leverage continuous knowledge distillation:
SauerkrautLM-Multi-ColBERT-33m achieves optimal balance through:
This architecture enables Late Interaction Retrieval with significantly better performance than the 15M variant while maintaining excellent efficiency.
SauerkrautLM-Multi-ColBERT-33m delivers strong multilingual retrieval performance, demonstrating the effectiveness of our two-phase pretraining approach at this parameter scale.
Average nDCG@10 across seven European languages, showing excellent multilingual capabilities from our two-phase pretraining:
| Language | nDCG@10 | Performance Notes |
|---|---|---|
| en | 51.74 | Enhanced by Phase 2 English pretraining |
| de | 38.46 | Strong german language performance |
| es | 43.10 | Excellent spanish language capabilities |
| fr | 40.96 | Consistent cross-lingual transfer |
| it | 40.44 | Balanced multilingual representation |
| nl | 37.51 | Effective on lower-resource languages |
| pt | 39.55 | Maintains quality across language families |
Key Observations:
This pretrained model serves as an ideal foundation for:
The combination of massive pretraining and balanced efficiency enables:
SauerkrautLM-Multi-ColBERT-33m demonstrates that thoughtful parameter scaling combined with strong pretraining creates optimal foundation models. By training on 8.2 billion tokens across two phases, we've created a model that:
This model represents the optimal balance between performance and efficiency for production-grade multilingual retrieval systems.
This is a PyLate model trained. It maps sentences & paragraphs to sequences of 128-dimensional dense vectors and can be used for semantic textual similarity using the MaxSim operator.
First install the PyLate library:
pip install -U pylate
PyLate provides a streamlined interface to index and retrieve documents using ColBERT models. The index leverages the Voyager HNSW index to efficiently handle document embeddings and enable fast retrieval.
First, load the ColBERT model and initialize the Voyager index, then encode and index your documents:
from pylate import indexes, models, retrieve
# Step 1: Load the ColBERT model
model = models.ColBERT(
model_name_or_path="VAGOsolutions/SauerkrautLM-Multi-ColBERT-33m",
)
# Step 2: Initialize the Voyager index
index = indexes.Voyager(
index_folder="pylate-index",
index_name="index",
override=True, # This overwrites the existing index if any
)
# Step 3: Encode the documents
documents_ids = ["1", "2", "3"]
documents = ["document 1 text", "document 2 text", "document 3 text"]
documents_embeddings = model.encode(
documents,
batch_size=32,
is_query=False, # Ensure that it is set to False to indicate that these are documents, not queries
show_progress_bar=True,
)
# Step 4: Add document embeddings to the index by providing embeddings and corresponding ids
index.add_documents(
documents_ids=documents_ids,
documents_embeddings=documents_embeddings,
)
Note that you do not have to recreate the index and encode the documents every time. Once you have created an index and added the documents, you can re-use the index later by loading it:
# To load an index, simply instantiate it with the correct folder/name and without overriding it
index = indexes.Voyager(
index_folder="pylate-index",
index_name="index",
)
Once the documents are indexed, you can retrieve the top-k most relevant documents for a given set of queries. To do so, initialize the ColBERT retriever with the index you want to search in, encode the queries and then retrieve the top-k documents to get the top matches ids and relevance scores:
# Step 1: Initialize the ColBERT retriever
retriever = retrieve.ColBERT(index=index)
# Step 2: Encode the queries
queries_embeddings = model.encode(
["query for document 3", "query for document 1"],
batch_size=32,
is_query=True, # # Ensure that it is set to False to indicate that these are queries
show_progress_bar=True,
)
# Step 3: Retrieve top-k documents
scores = retriever.retrieve(
queries_embeddings=queries_embeddings,
k=10, # Retrieve the top 10 matches for each query
)
If you only want to use the ColBERT model to perform reranking on top of your first-stage retrieval pipeline without building an index, you can simply use rank function and pass the queries and documents to rerank:
from pylate import rank, models
queries = [
"query A",
"query B",
]
documents = [
["document A", "document B"],
["document 1", "document C", "document B"],
]
documents_ids = [
[1, 2],
[1, 3, 2],
]
model = models.ColBERT(
model_name_or_path="VAGOsolutions/SauerkrautLM-Multi-ColBERT-33m",
)
queries_embeddings = model.encode(
queries,
is_query=True,
)
documents_embeddings = model.encode(
documents,
is_query=False,
)
reranked_documents = rank.rerank(
documents_ids=documents_ids,
queries_embeddings=queries_embeddings,
documents_embeddings=documents_embeddings,
)
@misc{SauerkrautLM-Multi-ColBERT-33m,
title={SauerkrautLM-Multi-ColBERT-33m},
author={David Golchinfar},
url={https://huggingface.co/VAGOsolutions/SauerkrautLM-Multi-ColBERT-33m},
year={2025}
}
@inproceedings{reimers-2019-sentence-bert,
title = {Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks},
author = {Reimers, Nils and Gurevych, Iryna},
booktitle = {Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing},
month = {11},
year = {2019},
publisher = {Association for Computational Linguistics},
url = {https://arxiv.org/abs/1908.10084}
}
@misc{PyLate,
title={PyLate: Flexible Training and Retrieval for Late Interaction Models},
author={Chaffin, Antoine and Sourty, Raphaël},
url={https://github.com/lightonai/pylate},
year={2024}
}
We thank the PyLate team for providing the training framework that made this work possible.