This is a Multi-Vector Encoder model finetuned from Qwen/Qwen3-VL-Embedding-2B on the llamaindex-vdr-en-train-preprocessed dataset using the sentence-transformers 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
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
Language: en
License: apache-2.0

Model Sources

Documentation: Sentence Transformers Documentation
Documentation: Multi-Vector Encoder Documentation
Repository: Sentence Transformers on GitHub
Hugging Face: Multi-Vector Encoders on Hugging Face

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:

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-lora")
# 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-lora/resolve/main/assets/image_0.jpg',
    'https://huggingface.co/tomaarsen/ColQwen3-VL-Embedding-2B-vdr-lora/resolve/main/assets/image_1.jpg',
    'https://huggingface.co/tomaarsen/ColQwen3-VL-Embedding-2B-vdr-lora/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([[35.4085, 33.2571, 23.4033]])

Evaluation

Metrics

Multi Vector Information Retrieval

Dataset: vdr-eval-hard
Evaluated with MultiVectorInformationRetrievalEvaluator

Metric	Value
maxsim_accuracy@1	0.8333
maxsim_accuracy@3	0.9367
maxsim_accuracy@5	0.9767
maxsim_accuracy@10	0.9967
maxsim_precision@1	0.8333
maxsim_precision@3	0.3122
maxsim_precision@5	0.1953
maxsim_precision@10	0.0997
maxsim_recall@1	0.8333
maxsim_recall@3	0.9367
maxsim_recall@5	0.9767
maxsim_recall@10	0.9967
maxsim_ndcg@10	0.9164
maxsim_mrr@10	0.8903
maxsim_map@100	0.8905

Training Details

Training Dataset

llamaindex-vdr-en-train-preprocessed

Dataset: llamaindex-vdr-en-train-preprocessed at 2323dab
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	min: 27 tokens mean: 35.59 tokens max: 50 tokens	min: 1000x756 px mean: 1437x1628 px max: 2044x1869 px	min: 1008x756 px mean: 1450x1637 px max: 2044x1851 px

Samples:

query	image	negative_0
`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 with these parameters:
json
1{ 2 "score_metric": "colbert_scores", 3 "mini_batch_size": 1, 4 "mini_batch_num_tokens": null, 5 "score_mini_batch_size": 1, 6 "scale": 1.0, 7 "size_average": true, 8 "gather_across_devices": false 9}

Training Hyperparameters

Non-Default Hyperparameters

per_device_train_batch_size: 64
num_train_epochs: 1
learning_rate: 2e-05
warmup_steps: 0.1
bf16: True
save_only_model: True

All Hyperparameters

Click to expand

per_device_train_batch_size: 64
num_train_epochs: 1
max_steps: -1
learning_rate: 2e-05
lr_scheduler_type: linear
lr_scheduler_kwargs: None
warmup_steps: 0.1
optim: adamw_torch_fused
optim_args: None
weight_decay: 0.0
adam_beta1: 0.9
adam_beta2: 0.999
adam_epsilon: 1e-08
optim_target_modules: None
gradient_accumulation_steps: 1
average_tokens_across_devices: True
max_grad_norm: 1.0
label_smoothing_factor: 0.0
bf16: True
fp16: False
bf16_full_eval: False
fp16_full_eval: False
tf32: None
gradient_checkpointing: False
gradient_checkpointing_kwargs: None
torch_compile: False
torch_compile_backend: None
torch_compile_mode: None
use_liger_kernel: False
liger_kernel_config: None
use_cache: False
neftune_noise_alpha: None
torch_empty_cache_steps: None
auto_find_batch_size: False
log_on_each_node: True
logging_nan_inf_filter: True
include_num_input_tokens_seen: no
log_level: passive
log_level_replica: warning
disable_tqdm: False
project: huggingface
trackio_space_id: None
trackio_bucket_id: None
trackio_static_space_id: None
per_device_eval_batch_size: 8
prediction_loss_only: True
eval_on_start: False
eval_do_concat_batches: True
eval_use_gather_object: False
eval_accumulation_steps: None
include_for_metrics: []
batch_eval_metrics: False
save_only_model: True
save_on_each_node: False
enable_jit_checkpoint: False
push_to_hub: False
hub_private_repo: None
hub_model_id: None
hub_strategy: every_save
hub_always_push: False
hub_revision: None
load_best_model_at_end: False
ignore_data_skip: False
restore_callback_states_from_checkpoint: False
full_determinism: False
seed: 42
data_seed: None
use_cpu: False
accelerator_config: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
parallelism_config: None
dataloader_drop_last: False
dataloader_num_workers: 0
dataloader_pin_memory: True
dataloader_persistent_workers: False
dataloader_prefetch_factor: None
remove_unused_columns: True
label_names: None
train_sampling_strategy: random
length_column_name: length
ddp_find_unused_parameters: None
ddp_bucket_cap_mb: None
ddp_broadcast_buffers: False
ddp_static_graph: None
ddp_backend: None
ddp_timeout: 1800
fsdp: None
fsdp_config: None
deepspeed: None
debug: []
skip_memory_metrics: True
do_predict: False
resume_from_checkpoint: None
warmup_ratio: None
local_rank: -1
prompts: None
batch_sampler: batch_sampler
multi_dataset_batch_sampler: proportional
router_mapping: {}
learning_rate_mapping: {}
max_length: None

Training Logs

Epoch	Step	Training Loss	vdr-eval-hard_maxsim_ndcg@10
-1	-1	-	0.8168
0.0510	8	2.5752	-
0.1019	16	2.1695	0.8606
0.1529	24	1.0907	-
0.2038	32	0.5869	0.8959
0.2548	40	0.4569	-
0.3057	48	0.4087	0.9043
0.3567	56	0.3991	-
0.4076	64	0.3467	0.9008
0.4586	72	0.3264	-
0.5096	80	0.3270	0.9023
0.5605	88	0.3572	-
0.6115	96	0.3229	0.9087
0.6624	104	0.3304	-
0.7134	112	0.3375	0.9151
0.7643	120	0.3506	-
0.8153	128	0.3091	0.9120
0.8662	136	0.2801	-
0.9172	144	0.3189	0.9141
0.9682	152	0.2963	-
1.0	157	-	0.9164
-1	-1	-	0.9164

Training Time

Training: 2.3 hours
Evaluation: 30.0 minutes
Total: 2.8 hours

Framework Versions

Python: 3.11.13
Sentence Transformers: 5.7.0.dev0
Transformers: 5.14.1
PyTorch: 2.11.0+cu128
Accelerate: 1.5.2
Datasets: 3.5.0
Tokenizers: 0.22.2

Citation

BibTeX

Sentence Transformers

bibtex

@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",
}

CachedMultiVectorMultipleNegativesRankingLoss

bibtex

@misc{gao2021scaling,
    title={Scaling Deep Contrastive Learning Batch Size under Memory Limited Setup},
    author={Luyu Gao and Yunyi Zhang and Jiawei Han and Jamie Callan},
    year={2021},
    eprint={2101.06983},
    archivePrefix={arXiv},
    primaryClass={cs.LG}
}