Add new MultiVectorEncoder model

.gitattributes

@@ -33,3 +33,9 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+assets/example_image_0.jpg filter=lfs diff=lfs merge=lfs -text
+assets/example_image_1.jpg filter=lfs diff=lfs merge=lfs -text
+assets/image_0.jpg filter=lfs diff=lfs merge=lfs -text
+assets/image_1.jpg filter=lfs diff=lfs merge=lfs -text
+assets/image_2.jpg filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

1_Dense/config.json

@@ -0,0 +1,8 @@
+{
+    "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"
+}

1_Dense/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aee1706dce651e897768f8d9b1a03805f11f4b282021316c872263665f048111
+size 524376

2_MultiVectorMask/config.json

@@ -0,0 +1,4 @@
+{
+    "skiplist_words": [],
+    "keep_only_token_ids": null
+}

3_Normalize/config.json

@@ -0,0 +1,4 @@
+{
+    "module_input_name": "token_embeddings",
+    "module_output_name": "token_embeddings"
+}

README.md

@@ -0,0 +1,467 @@
+---
+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) <!-- at revision 9f2f7e710d6d81056aa5c0a4f04764fec6bb7bda -->
+- **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:** Unknown -->
+<!-- - **License:** Unknown -->
+
+### 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-headlr")
+# 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-headlr/resolve/main/assets/image_0.jpg',
+    'https://huggingface.co/tomaarsen/ColQwen3-VL-Embedding-2B-vdr-headlr/resolve/main/assets/image_1.jpg',
+    'https://huggingface.co/tomaarsen/ColQwen3-VL-Embedding-2B-vdr-headlr/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]])
+```
+<!--
+### Direct Usage (Transformers)
+
+<details><summary>Click to see the direct usage in Transformers</summary>
+
+</details>
+-->
+
+<!--
+### Downstream Usage (Sentence Transformers)
+
+You can finetune this model on your own dataset.
+
+<details><summary>Click to expand</summary>
+
+</details>
+-->
+
+<!--
+### Out-of-Scope Use
+
+*List how the model may foreseeably be misused and address what users ought not to do with the model.*
+-->
+
+## Evaluation
+
+### Metrics
+
+#### Multi Vector Information Retrieval
+
+* Dataset: `vdr-eval-hard`
+* Evaluated with [<code>MultiVectorInformationRetrievalEvaluator</code>](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     |
+
+<!--
+## Bias, Risks and Limitations
+
+*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
+-->
+
+<!--
+### Recommendations
+
+*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
+-->
+
+## Training Details
+
+### Training Dataset
+
+#### llamaindex-vdr-en-train-preprocessed
+
+* Dataset: llamaindex-vdr-en-train-preprocessed
+* Size: 10,000 training samples
+* Columns: <code>query</code>, <code>image</code>, and <code>negative_0</code>
+* Approximate statistics based on the first 100 samples:
+  |          | query                                                                              | image                                                                                   | negative_0                                                                              |
+  |:---------|:-----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------------|
+  | type     | string                                                                             | image                                                                                   | image                                                                                   |
+  | modality | text                                                                               | image                                                                                   | image                                                                                   |
+  | details  | <ul><li>min: 27 tokens</li><li>mean: 35.59 tokens</li><li>max: 50 tokens</li></ul> | <ul><li>min: 1000x756 px</li><li>mean: 1437x1628 px</li><li>max: 2044x1869 px</li></ul> | <ul><li>min: 1008x756 px</li><li>mean: 1450x1637 px</li><li>max: 2044x1851 px</li></ul> |
+* Samples:
+  | query                                                                                                                              | image                                      | negative_0                                         |
+  |:-----------------------------------------------------------------------------------------------------------------------------------|:-------------------------------------------|:---------------------------------------------------|
+  | <code>What are the new anthropological perspectives on development as discussed by Quarles Van Ufford and Giri in 2003?</code>     | <img src="https://huggingface.co/tomaarsen/ColQwen3-VL-Embedding-2B-vdr-headlr/resolve/main/assets/image_0.jpg" width="200"> | <img src="https://huggingface.co/tomaarsen/ColQwen3-VL-Embedding-2B-vdr-headlr/resolve/main/assets/example_image_0.jpg" width="200"> |
+  | <code>What are the three main positions anthropologists have taken in relation to development, as discussed by David Lewis?</code> | <img src="https://huggingface.co/tomaarsen/ColQwen3-VL-Embedding-2B-vdr-headlr/resolve/main/assets/image_1.jpg" width="200"> | <img src="https://huggingface.co/tomaarsen/ColQwen3-VL-Embedding-2B-vdr-headlr/resolve/main/assets/example_image_0.jpg" width="200"> |
+  | <code>Who are the three sisters known as the Fates in Greek mythology?</code>                                                      | <img src="https://huggingface.co/tomaarsen/ColQwen3-VL-Embedding-2B-vdr-headlr/resolve/main/assets/image_2.jpg" width="200"> | <img src="https://huggingface.co/tomaarsen/ColQwen3-VL-Embedding-2B-vdr-headlr/resolve/main/assets/example_image_1.jpg" width="200"> |
+* Loss: [<code>CachedMultiVectorMultipleNegativesRankingLoss</code>](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
+<details><summary>Click to expand</summary>
+
+- `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`: 30.0
+- `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`: False
+- `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`: {'^(model\\.)?1\\.linear': 0.0002}
+- `max_length`: None
+
+</details>
+
+### Training Logs
+| Epoch  | Step | Training Loss | vdr-eval-hard_maxsim_ndcg@10 |
+|:------:|:----:|:-------------:|:----------------------------:|
+| -1     | -1   | -             | 0.8244                       |
+| 0.0510 | 8    | 2.2737        | -                            |
+| 0.1019 | 16   | 0.6985        | 0.9132                       |
+| 0.1529 | 24   | 0.3765        | -                            |
+| 0.2038 | 32   | 0.3179        | 0.9133                       |
+| 0.2548 | 40   | 0.2909        | -                            |
+| 0.3057 | 48   | 0.2984        | 0.9184                       |
+| 0.3567 | 56   | 0.2649        | -                            |
+| 0.4076 | 64   | 0.2771        | 0.9232                       |
+| 0.4586 | 72   | 0.2404        | -                            |
+| 0.5096 | 80   | 0.2456        | 0.9271                       |
+| 0.5605 | 88   | 0.2933        | -                            |
+| 0.6115 | 96   | 0.2549        | 0.9224                       |
+| 0.6624 | 104  | 0.2636        | -                            |
+| 0.7134 | 112  | 0.2815        | 0.9202                       |
+| 0.7643 | 120  | 0.2829        | -                            |
+| 0.8153 | 128  | 0.2592        | 0.9206                       |
+| 0.8662 | 136  | 0.2180        | -                            |
+| 0.9172 | 144  | 0.2647        | 0.9206                       |
+| 0.9682 | 152  | 0.2411        | -                            |
+| 1.0    | 157  | -             | 0.9278                       |
+
+
+### Training Time
+- **Training**: 2.4 hours
+- **Evaluation**: 26.8 minutes
+- **Total**: 2.8 hours
+
+### Framework Versions
+- Python: 3.12.12
+- Sentence Transformers: 5.7.0.dev0
+- Transformers: 5.14.1
+- PyTorch: 2.13.0+cu130
+- Accelerate: 1.14.0
+- Datasets: 5.0.0
+- Tokenizers: 0.22.2
+
+## Additional Resources
+
+- [Sentence Transformers Documentation](https://www.sbert.net): the full documentation site, including training, evaluation, and pre-trained model catalogs.
+- [PyLate](https://github.com/lightonai/pylate): the upstream library whose features were absorbed into Sentence Transformers for multi-vector / late-interaction models.
+
+## 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}
+}
+```
+
+<!--
+## Glossary
+
+*Clearly define terms in order to be accessible across audiences.*
+-->
+
+<!--
+## Model Card Authors
+
+*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
+-->
+
+<!--
+## Model Card Contact
+
+*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
+--> 

chat_template.jinja

@@ -0,0 +1,125 @@
+{%- set default_system_message = 'Represent the user\'s input.' -%}
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {%- if messages[0].content is string %}
+            {{- messages[0].content }}
+        {%- else %}
+            {%- for content in messages[0].content %}
+                {%- if 'text' in content %}
+                    {{- content.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- '\n\n' }}
+    {%- else %}
+        {{- default_system_message + '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' }}
+        {%- if messages[0].content is string %}
+            {{- messages[0].content }}
+        {%- else %}
+            {%- for content in messages[0].content %}
+                {%- if 'text' in content %}
+                    {{- content.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- else %}
+        {{- '<|im_start|>system\n' + default_system_message + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set image_count = namespace(value=0) %}
+{%- set video_count = namespace(value=0) %}
+{%- for message in messages %}
+    {%- if message.role == "user" %}
+        {{- '<|im_start|>' + message.role + '\n' }}
+        {%- if message.content is string %}
+            {{- message.content }}
+        {%- else %}
+            {%- for content in message.content %}
+                {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
+                    {%- set image_count.value = image_count.value + 1 %}
+                    {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
+                    <|vision_start|><|image_pad|><|vision_end|>
+                {%- elif content.type == 'video' or 'video' in content %}
+                    {%- set video_count.value = video_count.value + 1 %}
+                    {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
+                    <|vision_start|><|video_pad|><|vision_end|>
+                {%- elif 'text' in content %}
+                    {{- content.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role + '\n' }}
+        {%- if message.content is string %}
+            {{- message.content }}
+        {%- else %}
+            {%- for content_item in message.content %}
+                {%- if 'text' in content_item %}
+                    {{- content_item.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and message.content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {%- if message.content is string %}
+            {{- message.content }}
+        {%- else %}
+            {%- for content in message.content %}
+                {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
+                    {%- set image_count.value = image_count.value + 1 %}
+                    {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
+                    <|vision_start|><|image_pad|><|vision_end|>
+                {%- elif content.type == 'video' or 'video' in content %}
+                    {%- set video_count.value = video_count.value + 1 %}
+                    {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
+                    <|vision_start|><|video_pad|><|vision_end|>
+                {%- elif 'text' in content %}
+                    {{- content.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

config.json

@@ -0,0 +1,69 @@
+{
+  "architectures": [
+    "Qwen3VLModel"
+  ],
+  "dtype": "bfloat16",
+  "eos_token_id": 151645,
+  "image_token_id": 151655,
+  "model_type": "qwen3_vl",
+  "pad_token_id": 151643,
+  "text_config": {
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "bos_token_id": 151643,
+    "dtype": "bfloat16",
+    "eos_token_id": 151645,
+    "head_dim": 128,
+    "hidden_act": "silu",
+    "hidden_size": 2048,
+    "initializer_range": 0.02,
+    "intermediate_size": 6144,
+    "max_position_embeddings": 262144,
+    "model_type": "qwen3_vl_text",
+    "num_attention_heads": 16,
+    "num_hidden_layers": 28,
+    "num_key_value_heads": 8,
+    "pad_token_id": null,
+    "rms_norm_eps": 1e-06,
+    "rope_parameters": {
+      "mrope_interleaved": true,
+      "mrope_section": [
+        24,
+        20,
+        20
+      ],
+      "rope_theta": 5000000,
+      "rope_type": "default"
+    },
+    "tie_word_embeddings": true,
+    "use_cache": true,
+    "vocab_size": 151936
+  },
+  "tie_word_embeddings": true,
+  "transformers_version": "5.14.1",
+  "use_cache": false,
+  "video_token_id": 151656,
+  "vision_config": {
+    "deepstack_visual_indexes": [
+      5,
+      11,
+      17
+    ],
+    "depth": 24,
+    "dtype": "bfloat16",
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 1024,
+    "in_channels": 3,
+    "initializer_range": 0.02,
+    "intermediate_size": 4096,
+    "model_type": "qwen3_vl_vision",
+    "num_heads": 16,
+    "num_position_embeddings": 2304,
+    "out_hidden_size": 2048,
+    "patch_size": 16,
+    "spatial_merge_size": 2,
+    "temporal_patch_size": 2
+  },
+  "vision_end_token_id": 151653,
+  "vision_start_token_id": 151652
+}

config_sentence_transformers.json

@@ -0,0 +1,15 @@
+{
+  "__version__": {
+    "pytorch": "2.13.0+cu130",
+    "sentence_transformers": "5.7.0.dev0",
+    "transformers": "5.14.1"
+  },
+  "default_prompt_name": "default",
+  "model_type": "MultiVectorEncoder",
+  "prompts": {
+    "default": "Represent the user's input.",
+    "document": "",
+    "query": ""
+  },
+  "similarity_fn_name": "maxsim"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba87e275316ff2a6e1f8cec80c20757909e0bd05f8e790c965d364e94acd0683
+size 4255136560

modules.json

@@ -0,0 +1,26 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.base.modules.transformer.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Dense",
+    "type": "sentence_transformers.base.modules.dense.Dense"
+  },
+  {
+    "idx": 2,
+    "name": "2",
+    "path": "2_MultiVectorMask",
+    "type": "sentence_transformers.multi_vector_encoder.modules.multi_vector_mask.MultiVectorMask"
+  },
+  {
+    "idx": 3,
+    "name": "3",
+    "path": "3_Normalize",
+    "type": "sentence_transformers.sentence_transformer.modules.normalize.Normalize"
+  }
+]

processor_config.json

@@ -0,0 +1,64 @@
+{
+  "image_processor": {
+    "data_format": "channels_first",
+    "default_to_square": true,
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_rescale": true,
+    "do_resize": true,
+    "image_mean": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "image_processor_type": "Qwen2VLImageProcessor",
+    "image_std": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "merge_size": 2,
+    "patch_size": 16,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "size": {
+      "longest_edge": 360000,
+      "shortest_edge": 784
+    },
+    "temporal_patch_size": 2
+  },
+  "processor_class": "Qwen3VLProcessor",
+  "video_processor": {
+    "data_format": "channels_first",
+    "default_to_square": true,
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_rescale": true,
+    "do_resize": true,
+    "do_sample_frames": true,
+    "fps": 2,
+    "image_mean": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "image_std": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "max_frames": 768,
+    "merge_size": 2,
+    "min_frames": 4,
+    "patch_size": 16,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "return_metadata": false,
+    "size": {
+      "longest_edge": 25165824,
+      "shortest_edge": 4096
+    },
+    "temporal_patch_size": 2,
+    "video_processor_type": "Qwen3VLVideoProcessor"
+  }
+}

sentence_bert_config.json

@@ -0,0 +1,29 @@
+{
+    "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
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4deec245f9380efa31abe72adbcae78599405bf2e69e5828180a5a6e116c67d
+size 11423970

tokenizer_config.json

@@ -0,0 +1,18 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "is_local": false,
+  "local_files_only": false,
+  "max_pixels": 360000,
+  "min_pixels": 784,
+  "model_max_length": 262144,
+  "pad_token": "<|endoftext|>",
+  "processor_class": "Qwen3VLProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}