Add Sentence Transformers usage

README.md

@@ -3,6 +3,7 @@ language:
 - en
 tags:
 - ColBERT
+- multi-vector
 - PyLate
 - sentence-transformers
 - sentence-similarity
@@ -25,14 +26,14 @@ It achieves extremely competitive performance on the [BRIGHT benchmark](https://
 
 # License
 Unfortunately, since the [ReasonIR data](https://huggingface.co/datasets/reasonir/reasonir-data) has been released under a cc-by-nc-4.0 license, we cannot release this model under an Apache 2.0 license. However, the authors of ReasonIR [released code to generate the data](https://github.com/facebookresearch/ReasonIR/tree/main/synthetic_data_generation). Anyone willing to reproduce the data could then easily reproduce this model under an Apache 2.0 license by running a fine-tuning lasting lower than 2 hours using [this boilerplate](https://gist.github.com/NohTow/d563244596548bf387f19fcd790664d3).
-# PyLate model based on lightonai/GTE-ModernColBERT-v1
+# Multi-vector embedding model based on lightonai/GTE-ModernColBERT-v1
 
-This is a [PyLate](https://github.com/lightonai/pylate) model finetuned from [lightonai/GTE-ModernColBERT-v1](https://huggingface.co/lightonai/GTE-ModernColBERT-v1) on the [reasonir-hq](https://huggingface.co/datasets/reasonir/reasonir-data) dataset. It maps sentences & paragraphs to sequences of 128-dimensional dense vectors and can be used for semantic textual similarity using the MaxSim operator.
+This is a multi-vector (ColBERT-style late interaction) embedding model finetuned from [lightonai/GTE-ModernColBERT-v1](https://huggingface.co/lightonai/GTE-ModernColBERT-v1) on the [reasonir-hq](https://huggingface.co/datasets/reasonir/reasonir-data) dataset. It maps sentences & paragraphs to sequences of 128-dimensional dense vectors and can be used for semantic textual similarity using the MaxSim operator.
 
 ## Model Details
 
 ### Model Description
-- **Model Type:** PyLate model
+- **Model Type:** Multi-vector embedding model
 - **Base model:** [lightonai/GTE-ModernColBERT-v1](https://huggingface.co/lightonai/GTE-ModernColBERT-v1) <!-- at revision 78d50a162b04dfdc45c3af6b4294ba77c24888a3 -->
 - **Document Length:** 8192 tokens
 - **Query Length:** 128 tokens
@@ -59,6 +60,41 @@ ColBERT(
 ```
 
 ## Usage
+
+### Sentence Transformers
+
+This model can be used with [Sentence Transformers](https://www.sbert.net/) as a multi-vector (ColBERT-style late interaction) retriever via the `MultiVectorEncoder`:
+
+```bash
+pip install "sentence-transformers>=6.0.0"
+```
+
+```python
+from sentence_transformers import MultiVectorEncoder
+
+model = MultiVectorEncoder("lightonai/Reason-ModernColBERT")
+
+query = "Which planet is known as the Red Planet?"
+documents = [
+    "Venus is often called Earth's twin because of its similar size and proximity.",
+    "Mars, known for its reddish appearance, is often referred to as the Red Planet.",
+    "Jupiter, the largest planet in our solar system, has a prominent red spot.",
+    "Saturn, famous for its rings, is sometimes mistaken for the Red Planet.",
+]
+
+query_embeddings = model.encode_query(query)
+document_embeddings = model.encode_document(documents)
+print(query_embeddings.shape, document_embeddings[0].shape)
+# (12, 128) (18, 128)
+
+# MaxSim late-interaction scoring (higher is more relevant)
+scores = model.similarity(query_embeddings, document_embeddings)
+print(scores)
+# tensor([[9.0512, 10.1842, 9.1238, 9.3910]])
+```
+
+### PyLate
+
 First install the PyLate library:
 
 ```bash