Add new MultiVectorEncoder model

.gitattributes

@@ -33,3 +33,10 @@ 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/example_image_2.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_MultiVectorMask/config.json

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

README.md

@@ -0,0 +1,567 @@
+---
+language:
+- en
+license: apache-2.0
+tags:
+- sentence-transformers
+- multi-vector
+- colbert
+- late-interaction
+- generated_from_trainer
+- dataset_size:3475
+- loss:MultiVectorMultipleNegativesRankingLoss
+base_model: vidore/colqwen2-v1.0-hf
+widget:
+- text: What is the aim of this book according to the introduction?
+- text: What is the purpose of a wet-bulb thermometer in a sling psychrometer?
+- text: What are the different switching states for DCC and FCC topologies of a converter?
+- text: What is the topic discussed in this page?
+- text: What do these graphs show?
+datasets:
+- vidore/syntheticDocQA_energy_train
+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: colqwen2-v1.0-hf finetuned on energy document pages
+  results:
+  - task:
+      type: multi-vector-information-retrieval
+      name: Multi Vector Information Retrieval
+    dataset:
+      name: energy dev
+      type: energy-dev
+    metrics:
+    - type: maxsim_accuracy@1
+      value: 0.935
+      name: Maxsim Accuracy@1
+    - type: maxsim_accuracy@3
+      value: 0.9675
+      name: Maxsim Accuracy@3
+    - type: maxsim_accuracy@5
+      value: 0.9725
+      name: Maxsim Accuracy@5
+    - type: maxsim_accuracy@10
+      value: 0.9825
+      name: Maxsim Accuracy@10
+    - type: maxsim_precision@1
+      value: 0.935
+      name: Maxsim Precision@1
+    - type: maxsim_precision@3
+      value: 0.3225
+      name: Maxsim Precision@3
+    - type: maxsim_precision@5
+      value: 0.1945
+      name: Maxsim Precision@5
+    - type: maxsim_precision@10
+      value: 0.09824999999999999
+      name: Maxsim Precision@10
+    - type: maxsim_recall@1
+      value: 0.935
+      name: Maxsim Recall@1
+    - type: maxsim_recall@3
+      value: 0.9675
+      name: Maxsim Recall@3
+    - type: maxsim_recall@5
+      value: 0.9725
+      name: Maxsim Recall@5
+    - type: maxsim_recall@10
+      value: 0.9825
+      name: Maxsim Recall@10
+    - type: maxsim_ndcg@10
+      value: 0.9592186005800499
+      name: Maxsim Ndcg@10
+    - type: maxsim_mrr@10
+      value: 0.9517777777777776
+      name: Maxsim Mrr@10
+    - type: maxsim_map@100
+      value: 0.952218176489611
+      name: Maxsim Map@100
+---
+
+# colqwen2-v1.0-hf finetuned on energy document pages
+
+This is a [Multi-Vector Encoder](https://www.sbert.net/docs/multi_vector_encoder/usage/usage.html) model finetuned from [vidore/colqwen2-v1.0-hf](https://huggingface.co/vidore/colqwen2-v1.0-hf) on the [synthetic_doc_qa_energy_train](https://huggingface.co/datasets/vidore/syntheticDocQA_energy_train) 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:** [vidore/colqwen2-v1.0-hf](https://huggingface.co/vidore/colqwen2-v1.0-hf) <!-- at revision 0d3e414967fde994dd99a0ccc29bcb34b5355712 -->
+- **Maximum Sequence Length:** 32768 tokens
+- **Output Dimensionality:** 128 dimensions
+- **Similarity Function:** maxsim
+- **Supported Modalities:** Text, Image
+- **Training Dataset:**
+    - [synthetic_doc_qa_energy_train](https://huggingface.co/datasets/vidore/syntheticDocQA_energy_train)
+- **Language:** en
+- **License:** apache-2.0
+
+### 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': 'retrieval', 'modality_config': {'text': {'method': 'forward', 'method_output_name': 'embeddings'}, 'image': {'method': 'forward', 'method_output_name': 'embeddings'}}, 'module_output_name': 'token_embeddings', 'architecture': 'ColQwen2ForRetrieval'})
+  (1): MultiVectorMask({'skiplist_words': [], 'keep_only_token_ids': None})
+)
+```
+
+## 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/multivector-colqwen2-v1.0-hf-docqa-energy")
+# Run inference: each input becomes a sequence of per-token vectors (variable length).
+queries = [
+    'What topics are covered in this index?',
+]
+documents = [
+    'https://huggingface.co/tomaarsen/multivector-colqwen2-v1.0-hf-docqa-energy/resolve/main/assets/image_0.jpg',
+    'https://huggingface.co/tomaarsen/multivector-colqwen2-v1.0-hf-docqa-energy/resolve/main/assets/image_1.jpg',
+    'https://huggingface.co/tomaarsen/multivector-colqwen2-v1.0-hf-docqa-energy/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)
+# (20, 128) (759, 128)
+
+# Get the MaxSim similarity scores
+similarities = model.similarity(query_embeddings, document_embeddings)
+print(similarities)
+# tensor([[15.7523,  8.2611, 11.6049]])
+```
+<!--
+### 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: `energy-dev`
+* 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   | 0.935      |
+| maxsim_accuracy@3   | 0.9675     |
+| maxsim_accuracy@5   | 0.9725     |
+| maxsim_accuracy@10  | 0.9825     |
+| maxsim_precision@1  | 0.935      |
+| maxsim_precision@3  | 0.3225     |
+| maxsim_precision@5  | 0.1945     |
+| maxsim_precision@10 | 0.0982     |
+| maxsim_recall@1     | 0.935      |
+| maxsim_recall@3     | 0.9675     |
+| maxsim_recall@5     | 0.9725     |
+| maxsim_recall@10    | 0.9825     |
+| **maxsim_ndcg@10**  | **0.9592** |
+| maxsim_mrr@10       | 0.9518     |
+| maxsim_map@100      | 0.9522     |
+
+<!--
+## 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
+
+#### synthetic_doc_qa_energy_train
+
+* Dataset: [synthetic_doc_qa_energy_train](https://huggingface.co/datasets/vidore/syntheticDocQA_energy_train) at [438dd85](https://huggingface.co/datasets/vidore/syntheticDocQA_energy_train/tree/438dd859839b0a48eba43c0e9f853195f2e61384)
+* Size: 3,475 training samples
+* Columns: <code>query</code> and <code>image</code>
+* Approximate statistics based on the first 100 samples:
+  |          | query                                                                              | image                                                                                  |
+  |:---------|:-----------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------|
+  | type     | string                                                                             | image                                                                                  |
+  | modality | text                                                                               | image                                                                                  |
+  | details  | <ul><li>min: 18 tokens</li><li>mean: 28.12 tokens</li><li>max: 48 tokens</li></ul> | <ul><li>min: 932x312 px</li><li>mean: 1717x2057 px</li><li>max: 3200x2339 px</li></ul> |
+* Samples:
+  | query                                                                                                                           | image                                              |
+  |:--------------------------------------------------------------------------------------------------------------------------------|:---------------------------------------------------|
+  | <code>What is the objective of the research task related to reactor pressure vessel steels?</code>                              | <img src="https://huggingface.co/tomaarsen/multivector-colqwen2-v1.0-hf-docqa-energy/resolve/main/assets/example_image_0.jpg" width="200"> |
+  | <code>What recommendations does this study make regarding energy policy options?</code>                                         | <img src="https://huggingface.co/tomaarsen/multivector-colqwen2-v1.0-hf-docqa-energy/resolve/main/assets/example_image_1.jpg" width="200"> |
+  | <code>What are the typical materials used for the cathode, electrolyte, and anode in conventional solid-state batteries?</code> | <img src="https://huggingface.co/tomaarsen/multivector-colqwen2-v1.0-hf-docqa-energy/resolve/main/assets/example_image_2.jpg" width="200"> |
+* Loss: [<code>MultiVectorMultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/multi_vector_encoder/losses.html#multivectormultiplenegativesrankingloss) with these parameters:
+  ```json
+  {
+      "score_metric": "colbert_scores",
+      "scale": 1.0,
+      "score_mini_batch_size": null,
+      "size_average": true,
+      "gather_across_devices": false
+  }
+  ```
+
+### Evaluation Dataset
+
+#### synthetic_doc_qa_energy_train
+
+* Dataset: [synthetic_doc_qa_energy_train](https://huggingface.co/datasets/vidore/syntheticDocQA_energy_train) at [438dd85](https://huggingface.co/datasets/vidore/syntheticDocQA_energy_train/tree/438dd859839b0a48eba43c0e9f853195f2e61384)
+* Size: 400 evaluation samples
+* Columns: <code>query</code> and <code>image</code>
+* Approximate statistics based on the first 100 samples:
+  |          | query                                                                              | image                                                                                   |
+  |:---------|:-----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------------|
+  | type     | string                                                                             | image                                                                                   |
+  | modality | text                                                                               | image                                                                                   |
+  | details  | <ul><li>min: 18 tokens</li><li>mean: 27.27 tokens</li><li>max: 44 tokens</li></ul> | <ul><li>min: 827x1125 px</li><li>mean: 1728x2103 px</li><li>max: 3400x3042 px</li></ul> |
+* Samples:
+  | query                                                                                 | image                                      |
+  |:--------------------------------------------------------------------------------------|:-------------------------------------------|
+  | <code>What topics are covered in this index?</code>                                   | <img src="https://huggingface.co/tomaarsen/multivector-colqwen2-v1.0-hf-docqa-energy/resolve/main/assets/image_0.jpg" width="200"> |
+  | <code>What are the different funding sources for projects listed in the table?</code> | <img src="https://huggingface.co/tomaarsen/multivector-colqwen2-v1.0-hf-docqa-energy/resolve/main/assets/image_1.jpg" width="200"> |
+  | <code>What are the main sections covered in this report?</code>                       | <img src="https://huggingface.co/tomaarsen/multivector-colqwen2-v1.0-hf-docqa-energy/resolve/main/assets/image_2.jpg" width="200"> |
+* Loss: [<code>MultiVectorMultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/multi_vector_encoder/losses.html#multivectormultiplenegativesrankingloss) with these parameters:
+  ```json
+  {
+      "score_metric": "colbert_scores",
+      "scale": 1.0,
+      "score_mini_batch_size": null,
+      "size_average": true,
+      "gather_across_devices": false
+  }
+  ```
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `num_train_epochs`: 1
+- `learning_rate`: 2e-05
+- `warmup_steps`: 0.05
+- `bf16`: True
+- `save_only_model`: True
+- `load_best_model_at_end`: True
+
+#### All Hyperparameters
+<details><summary>Click to expand</summary>
+
+- `per_device_train_batch_size`: 8
+- `num_train_epochs`: 1
+- `max_steps`: -1
+- `learning_rate`: 2e-05
+- `lr_scheduler_type`: linear
+- `lr_scheduler_kwargs`: None
+- `warmup_steps`: 0.05
+- `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`: True
+- `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
+
+</details>
+
+### Training Logs
+| Epoch   | Step    | Training Loss | Validation Loss | energy-dev_maxsim_ndcg@10 |
+|:-------:|:-------:|:-------------:|:---------------:|:-------------------------:|
+| -1      | -1      | -             | -               | 0.9571                    |
+| 0.0115  | 5       | 0.0964        | -               | -                         |
+| 0.0230  | 10      | 0.0489        | -               | -                         |
+| 0.0345  | 15      | 0.1147        | -               | -                         |
+| 0.0460  | 20      | 0.0682        | -               | -                         |
+| 0.0575  | 25      | 0.0311        | -               | -                         |
+| 0.0690  | 30      | 0.0563        | -               | -                         |
+| 0.0805  | 35      | 0.0086        | -               | -                         |
+| 0.0920  | 40      | 0.0599        | -               | -                         |
+| 0.1011  | 44      | -             | 0.0606          | 0.9554                    |
+| 0.1034  | 45      | 0.0014        | -               | -                         |
+| 0.1149  | 50      | 0.0163        | -               | -                         |
+| 0.1264  | 55      | 0.0684        | -               | -                         |
+| 0.1379  | 60      | 0.0364        | -               | -                         |
+| 0.1494  | 65      | 0.0973        | -               | -                         |
+| 0.1609  | 70      | 0.0744        | -               | -                         |
+| 0.1724  | 75      | 0.0444        | -               | -                         |
+| 0.1839  | 80      | 0.0047        | -               | -                         |
+| 0.1954  | 85      | 0.1064        | -               | -                         |
+| 0.2023  | 88      | -             | 0.0516          | 0.9548                    |
+| 0.2069  | 90      | 0.1071        | -               | -                         |
+| 0.2184  | 95      | 0.0783        | -               | -                         |
+| 0.2299  | 100     | 0.0627        | -               | -                         |
+| 0.2414  | 105     | 0.0181        | -               | -                         |
+| 0.2529  | 110     | 0.0073        | -               | -                         |
+| 0.2644  | 115     | 0.0430        | -               | -                         |
+| 0.2759  | 120     | 0.0013        | -               | -                         |
+| 0.2874  | 125     | 0.0500        | -               | -                         |
+| 0.2989  | 130     | 0.0044        | -               | -                         |
+| 0.3034  | 132     | -             | 0.0442          | 0.9548                    |
+| 0.3103  | 135     | 0.0891        | -               | -                         |
+| 0.3218  | 140     | 0.0260        | -               | -                         |
+| 0.3333  | 145     | 0.0302        | -               | -                         |
+| 0.3448  | 150     | 0.0229        | -               | -                         |
+| 0.3563  | 155     | 0.1208        | -               | -                         |
+| 0.3678  | 160     | 0.0367        | -               | -                         |
+| 0.3793  | 165     | 0.0361        | -               | -                         |
+| 0.3908  | 170     | 0.0409        | -               | -                         |
+| 0.4023  | 175     | 0.0103        | -               | -                         |
+| 0.4046  | 176     | -             | 0.0427          | 0.9559                    |
+| 0.4138  | 180     | 0.0072        | -               | -                         |
+| 0.4253  | 185     | 0.0649        | -               | -                         |
+| 0.4368  | 190     | 0.0405        | -               | -                         |
+| 0.4483  | 195     | 0.0026        | -               | -                         |
+| 0.4598  | 200     | 0.0352        | -               | -                         |
+| 0.4713  | 205     | 0.0342        | -               | -                         |
+| 0.4828  | 210     | 0.0098        | -               | -                         |
+| 0.4943  | 215     | 0.0057        | -               | -                         |
+| 0.5057  | 220     | 0.0235        | 0.0416          | 0.9567                    |
+| 0.5172  | 225     | 0.0026        | -               | -                         |
+| 0.5287  | 230     | 0.0119        | -               | -                         |
+| 0.5402  | 235     | 0.0013        | -               | -                         |
+| 0.5517  | 240     | 0.0417        | -               | -                         |
+| 0.5632  | 245     | 0.0118        | -               | -                         |
+| 0.5747  | 250     | 0.0060        | -               | -                         |
+| 0.5862  | 255     | 0.0069        | -               | -                         |
+| 0.5977  | 260     | 0.0620        | -               | -                         |
+| 0.6069  | 264     | -             | 0.0410          | 0.9583                    |
+| 0.6092  | 265     | 0.0700        | -               | -                         |
+| 0.6207  | 270     | 0.0287        | -               | -                         |
+| 0.6322  | 275     | 0.1266        | -               | -                         |
+| 0.6437  | 280     | 0.0015        | -               | -                         |
+| 0.6552  | 285     | 0.0147        | -               | -                         |
+| 0.6667  | 290     | 0.0145        | -               | -                         |
+| 0.6782  | 295     | 0.0976        | -               | -                         |
+| 0.6897  | 300     | 0.0027        | -               | -                         |
+| 0.7011  | 305     | 0.0341        | -               | -                         |
+| 0.7080  | 308     | -             | 0.0404          | 0.9583                    |
+| 0.7126  | 310     | 0.0570        | -               | -                         |
+| 0.7241  | 315     | 0.0302        | -               | -                         |
+| 0.7356  | 320     | 0.0047        | -               | -                         |
+| 0.7471  | 325     | 0.0238        | -               | -                         |
+| 0.7586  | 330     | 0.0514        | -               | -                         |
+| 0.7701  | 335     | 0.0022        | -               | -                         |
+| 0.7816  | 340     | 0.0579        | -               | -                         |
+| 0.7931  | 345     | 0.0030        | -               | -                         |
+| 0.8046  | 350     | 0.0407        | -               | -                         |
+| 0.8092  | 352     | -             | 0.0404          | 0.9577                    |
+| 0.8161  | 355     | 0.0363        | -               | -                         |
+| 0.8276  | 360     | 0.0570        | -               | -                         |
+| 0.8391  | 365     | 0.0031        | -               | -                         |
+| 0.8506  | 370     | 0.0603        | -               | -                         |
+| 0.8621  | 375     | 0.0067        | -               | -                         |
+| 0.8736  | 380     | 0.0022        | -               | -                         |
+| 0.8851  | 385     | 0.0129        | -               | -                         |
+| 0.8966  | 390     | 0.0072        | -               | -                         |
+| 0.9080  | 395     | 0.0052        | -               | -                         |
+| 0.9103  | 396     | -             | 0.0405          | 0.9574                    |
+| 0.9195  | 400     | 0.0165        | -               | -                         |
+| 0.9310  | 405     | 0.0060        | -               | -                         |
+| 0.9425  | 410     | 0.0020        | -               | -                         |
+| 0.9540  | 415     | 0.0144        | -               | -                         |
+| 0.9655  | 420     | 0.0572        | -               | -                         |
+| 0.9770  | 425     | 0.1479        | -               | -                         |
+| 0.9885  | 430     | 0.0381        | -               | -                         |
+| **1.0** | **435** | **0.0337**    | **0.0405**      | **0.9592**                |
+| -1      | -1      | -             | -               | 0.9592                    |
+
+* The bold row denotes the saved checkpoint.
+
+### Training Time
+- **Training**: 14.2 minutes
+- **Evaluation**: 24.0 minutes
+- **Total**: 38.2 minutes
+
+### 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",
+}
+```
+
+#### MultiVectorMultipleNegativesRankingLoss
+```bibtex
+@misc{henderson2017efficient,
+    title={Efficient Natural Language Response Suggestion for Smart Reply},
+    author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil},
+    year={2017},
+    eprint={1705.00652},
+    archivePrefix={arXiv},
+    primaryClass={cs.CL}
+}
+```
+
+<!--
+## 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 +1,7 @@
+{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system
+You are a helpful assistant.<|im_end|>
+{% endif %}<|im_start|>{{ message['role'] }}
+{% if message['content'] is string %}{{ message['content'] }}<|im_end|>
+{% 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 %}<|im_end|>
+{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant
+{% endif %}

config.json

@@ -0,0 +1,177 @@
+{
+  "architectures": [
+    "ColQwen2ForRetrieval"
+  ],
+  "dtype": "bfloat16",
+  "embedding_dim": 128,
+  "eos_token_id": 151645,
+  "initializer_range": 0.02,
+  "is_composition": false,
+  "model_type": "colqwen2",
+  "pad_token_id": 151643,
+  "transformers_version": "5.14.1",
+  "use_cache": false,
+  "vlm_config": {
+    "_name_or_path": "Qwen/Qwen2-VL-2B-Instruct",
+    "dtype": "bfloat16",
+    "image_token_id": 151655,
+    "model_type": "qwen2_vl",
+    "text_config": {
+      "_name_or_path": "vidore/colqwen2-base",
+      "add_cross_attention": false,
+      "architectures": [
+        "ColQwen2"
+      ],
+      "attention_dropout": 0.0,
+      "bos_token_id": 151643,
+      "chunk_size_feed_forward": 0,
+      "cross_attention_hidden_size": null,
+      "decoder_start_token_id": null,
+      "dtype": "bfloat16",
+      "eos_token_id": 151645,
+      "finetuning_task": null,
+      "hidden_act": "silu",
+      "hidden_size": 1536,
+      "id2label": {
+        "0": "LABEL_0",
+        "1": "LABEL_1"
+      },
+      "image_token_id": null,
+      "initializer_range": 0.02,
+      "intermediate_size": 8960,
+      "is_decoder": false,
+      "is_encoder_decoder": false,
+      "label2id": {
+        "LABEL_0": 0,
+        "LABEL_1": 1
+      },
+      "layer_types": [
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention",
+        "full_attention"
+      ],
+      "max_position_embeddings": 32768,
+      "max_window_layers": 28,
+      "model_type": "qwen2_vl_text",
+      "num_attention_heads": 12,
+      "num_hidden_layers": 28,
+      "num_key_value_heads": 2,
+      "output_attentions": false,
+      "output_hidden_states": false,
+      "pad_token_id": null,
+      "prefix": null,
+      "problem_type": null,
+      "pruned_heads": {},
+      "return_dict": true,
+      "rms_norm_eps": 1e-06,
+      "rope_parameters": {
+        "mrope_section": [
+          16,
+          24,
+          24
+        ],
+        "rope_theta": 1000000.0,
+        "rope_type": "default",
+        "type": "default"
+      },
+      "sep_token_id": null,
+      "sliding_window": null,
+      "task_specific_params": null,
+      "tf_legacy_loss": false,
+      "tie_encoder_decoder": false,
+      "tie_word_embeddings": true,
+      "tokenizer_class": null,
+      "torchscript": false,
+      "use_bfloat16": false,
+      "use_cache": true,
+      "use_sliding_window": false,
+      "video_token_id": null,
+      "vision_end_token_id": 151653,
+      "vision_start_token_id": 151652,
+      "vision_token_id": 151654,
+      "vocab_size": 151936
+    },
+    "tie_word_embeddings": false,
+    "video_token_id": 151656,
+    "vision_config": {
+      "_name_or_path": "",
+      "add_cross_attention": false,
+      "architectures": null,
+      "bos_token_id": null,
+      "chunk_size_feed_forward": 0,
+      "cross_attention_hidden_size": null,
+      "decoder_start_token_id": null,
+      "depth": 32,
+      "dtype": "bfloat16",
+      "embed_dim": 1280,
+      "eos_token_id": null,
+      "finetuning_task": null,
+      "hidden_act": "quick_gelu",
+      "hidden_size": 1536,
+      "id2label": {
+        "0": "LABEL_0",
+        "1": "LABEL_1"
+      },
+      "in_channels": 3,
+      "in_chans": 3,
+      "initializer_range": 0.02,
+      "is_decoder": false,
+      "is_encoder_decoder": false,
+      "label2id": {
+        "LABEL_0": 0,
+        "LABEL_1": 1
+      },
+      "mlp_ratio": 4,
+      "model_type": "qwen2_vl_vision",
+      "num_heads": 16,
+      "output_attentions": false,
+      "output_hidden_states": false,
+      "pad_token_id": null,
+      "patch_size": 14,
+      "prefix": null,
+      "problem_type": null,
+      "pruned_heads": {},
+      "return_dict": true,
+      "sep_token_id": null,
+      "spatial_merge_size": 2,
+      "spatial_patch_size": 14,
+      "task_specific_params": null,
+      "temporal_patch_size": 2,
+      "tf_legacy_loss": false,
+      "tie_encoder_decoder": false,
+      "tie_word_embeddings": true,
+      "tokenizer_class": null,
+      "torchscript": false,
+      "use_bfloat16": false
+    },
+    "vision_end_token_id": 151653,
+    "vision_start_token_id": 151652,
+    "vision_token_id": 151654,
+    "vocab_size": 151936
+  }
+}

config_sentence_transformers.json

@@ -0,0 +1,14 @@
+{
+  "__version__": {
+    "pytorch": "2.11.0+cu128",
+    "sentence_transformers": "5.7.0.dev0",
+    "transformers": "5.14.1"
+  },
+  "default_prompt_name": null,
+  "model_type": "MultiVectorEncoder",
+  "prompts": {
+    "document": "",
+    "query": ""
+  },
+  "similarity_fn_name": "maxsim"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:096d1f4b642ac1d95de3fd1551c20deea6333982e522f55f4919d0c31ed4dc64
+size 4418454832

modules.json

@@ -0,0 +1,14 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.base.modules.transformer.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_MultiVectorMask",
+    "type": "sentence_transformers.multi_vector_encoder.modules.multi_vector_mask.MultiVectorMask"
+  }
+]

processor_config.json

@@ -0,0 +1,31 @@
+{
+  "image_processor": {
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_rescale": true,
+    "do_resize": true,
+    "image_mean": [
+      0.48145466,
+      0.4578275,
+      0.40821073
+    ],
+    "image_processor_type": "Qwen2VLImageProcessor",
+    "image_std": [
+      0.26862954,
+      0.26130258,
+      0.27577711
+    ],
+    "merge_size": 2,
+    "patch_size": 14,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "size": {
+      "longest_edge": 602112,
+      "shortest_edge": 3136
+    },
+    "temporal_patch_size": 2
+  },
+  "processor_class": "ColQwen2Processor",
+  "query_prefix": "Query: ",
+  "visual_prompt_prefix": "<|im_start|>user\n<|vision_start|><|image_pad|><|vision_end|>Describe the image.<|im_end|><|endoftext|>"
+}

sentence_bert_config.json

@@ -0,0 +1,14 @@
+{
+    "transformer_task": "retrieval",
+    "modality_config": {
+        "text": {
+            "method": "forward",
+            "method_output_name": "embeddings"
+        },
+        "image": {
+            "method": "forward",
+            "method_output_name": "embeddings"
+        }
+    },
+    "module_output_name": "token_embeddings"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bac488975eccb4e1cbcf65979b644ac7e0ba71721f1ea36a52bd4b5fb81497b3
+size 11420634

tokenizer_config.json

@@ -0,0 +1,32 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "is_local": false,
+  "local_files_only": false,
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "left",
+  "processor_class": "ColQwen2Processor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}