---
tags:
- sentence-transformers
- multi-vector
- colbert
- late-interaction
- generated_from_trainer
- dataset_size:10000
- loss:CachedMultiVectorMultipleNegativesRankingLoss
base_model: Qwen/Qwen3-VL-Embedding-2B
widget:
- text: What are the traditional practices of indigenous peoples in managing their
lands and territories?
- text: How does the tracking and commission distribution work in affiliate marketing
when a user makes a purchase?
- text: How many climate adaptation activities by Indigenous peoples are identified?
- text: What is the founding novel of the cyberpunk subgenre?
- text: Where can observable equity security prices be found, as per ASC 321-10?
pipeline_tag: feature-extraction
library_name: sentence-transformers
metrics:
- maxsim_accuracy@1
- maxsim_accuracy@3
- maxsim_accuracy@5
- maxsim_accuracy@10
- maxsim_precision@1
- maxsim_precision@3
- maxsim_precision@5
- maxsim_precision@10
- maxsim_recall@1
- maxsim_recall@3
- maxsim_recall@5
- maxsim_recall@10
- maxsim_ndcg@10
- maxsim_mrr@10
- maxsim_map@100
model-index:
- name: Multi-Vector Encoder
results:
- task:
type: multi-vector-information-retrieval
name: Multi Vector Information Retrieval
dataset:
name: vdr eval hard
type: vdr-eval-hard
metrics:
- type: maxsim_accuracy@1
value: 0.8466666666666667
name: Maxsim Accuracy@1
- type: maxsim_accuracy@3
value: 0.9566666666666667
name: Maxsim Accuracy@3
- type: maxsim_accuracy@5
value: 0.98
name: Maxsim Accuracy@5
- type: maxsim_accuracy@10
value: 0.9966666666666667
name: Maxsim Accuracy@10
- type: maxsim_precision@1
value: 0.8466666666666667
name: Maxsim Precision@1
- type: maxsim_precision@3
value: 0.31888888888888883
name: Maxsim Precision@3
- type: maxsim_precision@5
value: 0.19599999999999998
name: Maxsim Precision@5
- type: maxsim_precision@10
value: 0.09966666666666665
name: Maxsim Precision@10
- type: maxsim_recall@1
value: 0.8466666666666667
name: Maxsim Recall@1
- type: maxsim_recall@3
value: 0.9566666666666667
name: Maxsim Recall@3
- type: maxsim_recall@5
value: 0.98
name: Maxsim Recall@5
- type: maxsim_recall@10
value: 0.9966666666666667
name: Maxsim Recall@10
- type: maxsim_ndcg@10
value: 0.9277675716215076
name: Maxsim Ndcg@10
- type: maxsim_mrr@10
value: 0.9049907407407407
name: Maxsim Mrr@10
- type: maxsim_map@100
value: 0.905293771043771
name: Maxsim Map@100
---
# Multi-Vector Encoder
This is a [Multi-Vector Encoder](https://www.sbert.net/docs/multi_vector_encoder/usage/usage.html) model finetuned from [Qwen/Qwen3-VL-Embedding-2B](https://huggingface.co/Qwen/Qwen3-VL-Embedding-2B) on the llamaindex-vdr-en-train-preprocessed dataset using the [sentence-transformers](https://www.SBERT.net) library. It maps inputs to sequences of 128-dimensional token-level vectors and scores them with late interaction (MaxSim), useful for semantic search with late interaction.
## Model Details
### Model Description
- **Model Type:** Multi-Vector Encoder
- **Base model:** [Qwen/Qwen3-VL-Embedding-2B](https://huggingface.co/Qwen/Qwen3-VL-Embedding-2B)
- **Maximum Sequence Length:** 262144 tokens
- **Output Dimensionality:** 128 dimensions
- **Similarity Function:** maxsim
- **Supported Modalities:** Text, Image, Video, Message
- **Training Dataset:**
- llamaindex-vdr-en-train-preprocessed
### Model Sources
- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
- **Documentation:** [Multi-Vector Encoder Documentation](https://www.sbert.net/docs/multi_vector_encoder/usage/usage.html)
- **Repository:** [Sentence Transformers on GitHub](https://github.com/huggingface/sentence-transformers)
- **Hugging Face:** [Multi-Vector Encoders on Hugging Face](https://huggingface.co/models?library=sentence-transformers&other=multi-vector)
### Full Model Architecture
```
MultiVectorEncoder(
(0): Transformer({'transformer_task': 'feature-extraction', 'modality_config': {'text': {'method': 'forward', 'method_output_name': 'last_hidden_state'}, 'image': {'method': 'forward', 'method_output_name': 'last_hidden_state'}, 'video': {'method': 'forward', 'method_output_name': 'last_hidden_state'}, 'message': {'method': 'forward', 'method_output_name': 'last_hidden_state', 'format': 'structured'}}, 'module_output_name': 'token_embeddings', 'processing_kwargs': {'chat_template': {'add_generation_prompt': True}}, 'unpad_inputs': False, 'architecture': 'Qwen3VLModel'})
(1): Dense({'in_features': 2048, 'out_features': 128, 'bias': False, 'activation_function': 'torch.nn.modules.linear.Identity', 'module_input_name': 'token_embeddings', 'module_output_name': 'token_embeddings'})
(2): MultiVectorMask({'skiplist_words': [], 'keep_only_token_ids': None})
(3): Normalize({'module_input_name': 'token_embeddings', 'module_output_name': 'token_embeddings'})
)
```
## Usage
### Direct Usage (Sentence Transformers)
First install the Sentence Transformers library:
```bash
pip install -U sentence-transformers
```
Then you can load this model and run inference.
```python
from sentence_transformers import MultiVectorEncoder
# Download from the 🤗 Hub
model = MultiVectorEncoder("tomaarsen/ColQwen3-VL-Embedding-2B-vdr")
# Run inference: each input becomes a sequence of per-token vectors (variable length).
queries = [
'What are the new anthropological perspectives on development as discussed by Quarles Van Ufford and Giri in 2003?',
]
documents = [
'https://huggingface.co/tomaarsen/ColQwen3-VL-Embedding-2B-vdr/resolve/main/assets/image_0.jpg',
'https://huggingface.co/tomaarsen/ColQwen3-VL-Embedding-2B-vdr/resolve/main/assets/image_1.jpg',
'https://huggingface.co/tomaarsen/ColQwen3-VL-Embedding-2B-vdr/resolve/main/assets/image_2.jpg',
]
query_embeddings = model.encode_query(queries)
document_embeddings = model.encode_document(documents)
print(query_embeddings[0].shape, document_embeddings[0].shape)
# (48, 128) (352, 128)
# Get the MaxSim similarity scores
similarities = model.similarity(query_embeddings, document_embeddings)
print(similarities)
# tensor([[37.0712, 33.5348, 23.2705]])
```
## Evaluation
### Metrics
#### Multi Vector Information Retrieval
* Dataset: `vdr-eval-hard`
* Evaluated with [MultiVectorInformationRetrievalEvaluator](https://sbert.net/docs/package_reference/multi_vector_encoder/evaluation.html#sentence_transformers.multi_vector_encoder.evaluation.MultiVectorInformationRetrievalEvaluator)
| Metric | Value |
|:--------------------|:-----------|
| maxsim_accuracy@1 | 0.8467 |
| maxsim_accuracy@3 | 0.9567 |
| maxsim_accuracy@5 | 0.98 |
| maxsim_accuracy@10 | 0.9967 |
| maxsim_precision@1 | 0.8467 |
| maxsim_precision@3 | 0.3189 |
| maxsim_precision@5 | 0.196 |
| maxsim_precision@10 | 0.0997 |
| maxsim_recall@1 | 0.8467 |
| maxsim_recall@3 | 0.9567 |
| maxsim_recall@5 | 0.98 |
| maxsim_recall@10 | 0.9967 |
| **maxsim_ndcg@10** | **0.9278** |
| maxsim_mrr@10 | 0.905 |
| maxsim_map@100 | 0.9053 |
## Training Details
### Training Dataset
#### llamaindex-vdr-en-train-preprocessed
* Dataset: llamaindex-vdr-en-train-preprocessed
* Size: 10,000 training samples
* Columns: query, image, and negative_0
* Approximate statistics based on the first 100 samples:
| | query | image | negative_0 |
|:---------|:-----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------------|
| type | string | image | image |
| modality | text | image | image |
| details |
What are the new anthropological perspectives on development as discussed by Quarles Van Ufford and Giri in 2003? |
|
|
| What are the three main positions anthropologists have taken in relation to development, as discussed by David Lewis? |
|
|
| Who are the three sisters known as the Fates in Greek mythology? |
|
|
* Loss: [CachedMultiVectorMultipleNegativesRankingLoss](https://sbert.net/docs/package_reference/multi_vector_encoder/losses.html#cachedmultivectormultiplenegativesrankingloss) with these parameters:
```json
{
"score_metric": "colbert_scores",
"mini_batch_size": 1,
"mini_batch_num_tokens": null,
"score_mini_batch_size": 1,
"scale": 1.0,
"size_average": true,
"gather_across_devices": false
}
```
### Training Hyperparameters
#### Non-Default Hyperparameters
- `per_device_train_batch_size`: 64
- `num_train_epochs`: 1
- `learning_rate`: 2e-05
- `warmup_steps`: 0.1
- `max_grad_norm`: 30.0
- `bf16`: True
- `learning_rate_mapping`: {'^(model\\.)?1\\.linear': 0.0002}
#### All Hyperparameters