Add new SentenceTransformer model

README.md

@@ -0,0 +1,646 @@
+---
+language:
+- en
+license: apache-2.0
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- dense
+- generated_from_trainer
+- dataset_size:10000
+- loss:MultipleNegativesRankingLoss
+base_model: google/siglip-base-patch16-512
+widget:
+- source_sentence: A man standing next to a little girl riding a horse.
+  sentences:
+  - The woman is working on her computer at the desk.
+  - A young man holding an umbrella next to a herd of cattle.
+  - 'a person sitting at a desk with a keyboard and monitor '
+- source_sentence: 'A car at an intersection while a man is crossing the street. '
+  sentences:
+  - A plane that is flying in the air.
+  - a small girl sitting on a chair holding a white bear
+  - A young toddler walks across the grass in a park.
+- source_sentence: A lady riding her bicycle on the side of a street.
+  sentences:
+  - Flowers hang from a small decorative post in a yard.
+  - Flowers in a clear vase sitting on a table.
+  - The toilet is near the door in the bathroom.
+- source_sentence: 'A group of zebras standing beside each other in the desert. '
+  sentences:
+  - The bathroom is clean and ready for us to use.
+  - A woman throwing a frisbee as a child looks on.
+  - a bird with a pink eye is sitting on a branch in the woods.
+- source_sentence: A large desk by a window is neatly arranged.
+  sentences:
+  - An old toilet sits in dirt with a helmet on top.
+  - A lady sitting at an enormous dining table with lots of food.
+  - A long hot dog on a plate on a table.
+datasets:
+- jxie/coco_captions
+pipeline_tag: sentence-similarity
+library_name: sentence-transformers
+metrics:
+- cosine_accuracy@1
+- cosine_accuracy@3
+- cosine_accuracy@5
+- cosine_accuracy@10
+- cosine_precision@1
+- cosine_precision@3
+- cosine_precision@5
+- cosine_precision@10
+- cosine_recall@1
+- cosine_recall@3
+- cosine_recall@5
+- cosine_recall@10
+- cosine_ndcg@10
+- cosine_mrr@10
+- cosine_map@100
+co2_eq_emissions:
+  emissions: 14.565152777100327
+  energy_consumed: 0.054424347688532056
+  source: codecarbon
+  training_type: fine-tuning
+  on_cloud: false
+  cpu_model: 13th Gen Intel(R) Core(TM) i7-13700K
+  ram_total_size: 31.777088165283203
+  hours_used: 0.169
+  hardware_used: 1 x NVIDIA GeForce RTX 3090
+model-index:
+- name: Google SigLIP (512x512 resolution) model trained on COCO Captions
+  results:
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: coco eval
+      type: coco-eval
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.755
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.944
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.975
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.992
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.755
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.31466666666666665
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.19500000000000003
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.09920000000000001
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.755
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.944
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.975
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.992
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.8860228540949219
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.8505285714285713
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.8508208051006964
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: coco test
+      type: coco-test
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.754
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.935
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.976
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.992
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.754
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.31166666666666665
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.1952
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.09920000000000001
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.754
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.935
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.976
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.992
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.8848518154761025
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.8490460317460323
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.849432976701497
+      name: Cosine Map@100
+---
+
+# Google SigLIP (512x512 resolution) model trained on COCO Captions
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [google/siglip-base-patch16-512](https://huggingface.co/google/siglip-base-patch16-512) on the [coco_captions](https://huggingface.co/datasets/jxie/coco_captions) dataset. It maps sentences & paragraphs to a None-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
+
+## Model Details
+
+### Model Description
+- **Model Type:** Sentence Transformer
+- **Base model:** [google/siglip-base-patch16-512](https://huggingface.co/google/siglip-base-patch16-512) <!-- at revision 753a949581523b60257d93e18391e8c27f72eb22 -->
+- **Maximum Sequence Length:** None tokens
+- **Output Dimensionality:** None dimensions
+- **Similarity Function:** Cosine Similarity
+- **Training Dataset:**
+    - [coco_captions](https://huggingface.co/datasets/jxie/coco_captions)
+- **Language:** en
+- **License:** apache-2.0
+
+### Model Sources
+
+- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
+- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
+- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
+
+### Full Model Architecture
+
+```
+SentenceTransformer(
+  (0): Transformer({'transformer_task': 'feature-extraction', 'modality_config': {'text': {'method': 'get_text_features', 'method_output_name': None}, 'image': {'method': 'get_image_features', 'method_output_name': None}}, 'module_output_name': 'sentence_embedding', 'architecture': 'SiglipModel'})
+)
+```
+
+## 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 SentenceTransformer
+
+# Download from the 🤗 Hub
+model = SentenceTransformer("tomaarsen/google-siglip-base-coco")
+# Run inference
+sentences = [
+    'A large desk by a window is neatly arranged.',
+    'A long hot dog on a plate on a table.',
+    'A lady sitting at an enormous dining table with lots of food.',
+]
+embeddings = model.encode(sentences)
+print(embeddings.shape)
+# [3, 1024]
+
+# Get the similarity scores for the embeddings
+similarities = model.similarity(embeddings, embeddings)
+print(similarities)
+# tensor([[1.0000, 0.1848, 0.1578],
+#         [0.1848, 1.0000, 0.5058],
+#         [0.1578, 0.5058, 1.0000]])
+```
+
+<!--
+### 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
+
+#### Information Retrieval
+
+* Datasets: `coco-eval` and `coco-test`
+* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
+
+| Metric              | coco-eval | coco-test  |
+|:--------------------|:----------|:-----------|
+| cosine_accuracy@1   | 0.755     | 0.754      |
+| cosine_accuracy@3   | 0.944     | 0.935      |
+| cosine_accuracy@5   | 0.975     | 0.976      |
+| cosine_accuracy@10  | 0.992     | 0.992      |
+| cosine_precision@1  | 0.755     | 0.754      |
+| cosine_precision@3  | 0.3147    | 0.3117     |
+| cosine_precision@5  | 0.195     | 0.1952     |
+| cosine_precision@10 | 0.0992    | 0.0992     |
+| cosine_recall@1     | 0.755     | 0.754      |
+| cosine_recall@3     | 0.944     | 0.935      |
+| cosine_recall@5     | 0.975     | 0.976      |
+| cosine_recall@10    | 0.992     | 0.992      |
+| **cosine_ndcg@10**  | **0.886** | **0.8849** |
+| cosine_mrr@10       | 0.8505    | 0.849      |
+| cosine_map@100      | 0.8508    | 0.8494     |
+
+<!--
+## 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
+
+#### coco_captions
+
+* Dataset: [coco_captions](https://huggingface.co/datasets/jxie/coco_captions) at [a2ed90d](https://huggingface.co/datasets/jxie/coco_captions/tree/a2ed90d49b61dd13dd71f399c70f5feb897f8bec)
+* Size: 10,000 training samples
+* Columns: <code>image</code> and <code>caption</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | image                             | caption                                                                                         |
+  |:--------|:----------------------------------|:------------------------------------------------------------------------------------------------|
+  | type    | PIL.JpegImagePlugin.JpegImageFile | string                                                                                          |
+  | details | <ul><li></li></ul>                | <ul><li>min: 28 characters</li><li>mean: 52.56 characters</li><li>max: 156 characters</li></ul> |
+* Samples:
+  | image                                                                                         | caption                                                             |
+  |:----------------------------------------------------------------------------------------------|:--------------------------------------------------------------------|
+  | <code><PIL.JpegImagePlugin.JpegImageFile image mode=RGB size=640x480 at 0x16B60463F10></code> | <code>A woman wearing a net on her head cutting a cake. </code>     |
+  | <code><PIL.JpegImagePlugin.JpegImageFile image mode=RGB size=640x480 at 0x16B5EB45F10></code> | <code>A woman cutting a large white sheet cake.</code>              |
+  | <code><PIL.JpegImagePlugin.JpegImageFile image mode=RGB size=640x480 at 0x16B6048B990></code> | <code>A woman wearing a hair net cutting a large sheet cake.</code> |
+* Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
+  ```json
+  {
+      "scale": 20.0,
+      "similarity_fct": "cos_sim",
+      "gather_across_devices": false
+  }
+  ```
+
+### Evaluation Dataset
+
+#### coco_captions
+
+* Dataset: [coco_captions](https://huggingface.co/datasets/jxie/coco_captions) at [a2ed90d](https://huggingface.co/datasets/jxie/coco_captions/tree/a2ed90d49b61dd13dd71f399c70f5feb897f8bec)
+* Size: 1,000 evaluation samples
+* Columns: <code>image</code> and <code>caption</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | image                             | caption                                                                                         |
+  |:--------|:----------------------------------|:------------------------------------------------------------------------------------------------|
+  | type    | PIL.JpegImagePlugin.JpegImageFile | string                                                                                          |
+  | details | <ul><li></li></ul>                | <ul><li>min: 27 characters</li><li>mean: 52.45 characters</li><li>max: 151 characters</li></ul> |
+* Samples:
+  | image                                                                                         | caption                                                                          |
+  |:----------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|
+  | <code><PIL.JpegImagePlugin.JpegImageFile image mode=RGB size=500x336 at 0x16B5EE1A550></code> | <code>A child holding a flowered umbrella and petting a yak.</code>              |
+  | <code><PIL.JpegImagePlugin.JpegImageFile image mode=RGB size=500x336 at 0x16B5E41C1D0></code> | <code>A young man holding an umbrella next to a herd of cattle.</code>           |
+  | <code><PIL.JpegImagePlugin.JpegImageFile image mode=RGB size=500x336 at 0x16B5F276AD0></code> | <code>a young boy barefoot holding an umbrella touching the horn of a cow</code> |
+* Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
+  ```json
+  {
+      "scale": 20.0,
+      "similarity_fct": "cos_sim",
+      "gather_across_devices": false
+  }
+  ```
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `eval_strategy`: steps
+- `per_device_train_batch_size`: 16
+- `per_device_eval_batch_size`: 16
+- `learning_rate`: 2e-05
+- `num_train_epochs`: 1
+- `warmup_ratio`: 0.1
+- `bf16`: True
+- `batch_sampler`: no_duplicates
+
+#### All Hyperparameters
+<details><summary>Click to expand</summary>
+
+- `overwrite_output_dir`: False
+- `do_predict`: False
+- `eval_strategy`: steps
+- `prediction_loss_only`: True
+- `per_device_train_batch_size`: 16
+- `per_device_eval_batch_size`: 16
+- `gradient_accumulation_steps`: 1
+- `eval_accumulation_steps`: None
+- `torch_empty_cache_steps`: None
+- `learning_rate`: 2e-05
+- `weight_decay`: 0.0
+- `adam_beta1`: 0.9
+- `adam_beta2`: 0.999
+- `adam_epsilon`: 1e-08
+- `max_grad_norm`: 1.0
+- `num_train_epochs`: 1
+- `max_steps`: -1
+- `lr_scheduler_type`: linear
+- `lr_scheduler_kwargs`: {}
+- `warmup_ratio`: 0.1
+- `warmup_steps`: 0
+- `log_level`: passive
+- `log_level_replica`: warning
+- `log_on_each_node`: True
+- `logging_nan_inf_filter`: True
+- `save_safetensors`: True
+- `save_on_each_node`: False
+- `save_only_model`: False
+- `restore_callback_states_from_checkpoint`: False
+- `use_cpu`: False
+- `seed`: 42
+- `data_seed`: None
+- `jit_mode_eval`: False
+- `bf16`: True
+- `fp16`: False
+- `half_precision_backend`: None
+- `bf16_full_eval`: False
+- `fp16_full_eval`: False
+- `tf32`: None
+- `local_rank`: 0
+- `ddp_backend`: None
+- `tpu_num_cores`: None
+- `debug`: []
+- `dataloader_drop_last`: False
+- `dataloader_num_workers`: 0
+- `dataloader_prefetch_factor`: None
+- `past_index`: -1
+- `disable_tqdm`: False
+- `remove_unused_columns`: True
+- `label_names`: None
+- `load_best_model_at_end`: False
+- `ignore_data_skip`: False
+- `fsdp`: []
+- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': 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
+- `deepspeed`: None
+- `label_smoothing_factor`: 0.0
+- `optim`: adamw_torch_fused
+- `optim_args`: None
+- `group_by_length`: False
+- `length_column_name`: length
+- `ddp_find_unused_parameters`: None
+- `ddp_bucket_cap_mb`: None
+- `ddp_broadcast_buffers`: False
+- `dataloader_pin_memory`: True
+- `dataloader_persistent_workers`: False
+- `skip_memory_metrics`: True
+- `use_legacy_prediction_loop`: False
+- `push_to_hub`: False
+- `resume_from_checkpoint`: None
+- `hub_model_id`: None
+- `hub_strategy`: every_save
+- `hub_private_repo`: None
+- `hub_always_push`: False
+- `hub_revision`: None
+- `gradient_checkpointing`: False
+- `gradient_checkpointing_kwargs`: None
+- `include_for_metrics`: []
+- `eval_do_concat_batches`: True
+- `mp_parameters`: 
+- `auto_find_batch_size`: False
+- `full_determinism`: False
+- `ray_scope`: last
+- `ddp_timeout`: 1800
+- `torch_compile`: False
+- `torch_compile_backend`: None
+- `torch_compile_mode`: None
+- `include_tokens_per_second`: False
+- `include_num_input_tokens_seen`: no
+- `neftune_noise_alpha`: None
+- `optim_target_modules`: None
+- `batch_eval_metrics`: False
+- `eval_on_start`: False
+- `use_liger_kernel`: False
+- `liger_kernel_config`: None
+- `eval_use_gather_object`: False
+- `average_tokens_across_devices`: True
+- `prompts`: None
+- `batch_sampler`: no_duplicates
+- `multi_dataset_batch_sampler`: proportional
+- `router_mapping`: {}
+- `learning_rate_mapping`: {}
+
+</details>
+
+### Training Logs
+| Epoch  | Step | Training Loss | Validation Loss | coco-eval_cosine_ndcg@10 | coco-test_cosine_ndcg@10 |
+|:------:|:----:|:-------------:|:---------------:|:------------------------:|:------------------------:|
+| -1     | -1   | -             | -               | 0.2242                   | -                        |
+| 0.0112 | 7    | 2.6924        | -               | -                        | -                        |
+| 0.0224 | 14   | 3.1613        | -               | -                        | -                        |
+| 0.0336 | 21   | 3.1706        | -               | -                        | -                        |
+| 0.0448 | 28   | 2.5607        | -               | -                        | -                        |
+| 0.056  | 35   | 2.5325        | -               | -                        | -                        |
+| 0.0672 | 42   | 2.353         | -               | -                        | -                        |
+| 0.0784 | 49   | 1.5503        | -               | -                        | -                        |
+| 0.0896 | 56   | 1.5149        | -               | -                        | -                        |
+| 0.1008 | 63   | 1.404         | 0.8206          | 0.7171                   | -                        |
+| 0.112  | 70   | 1.0411        | -               | -                        | -                        |
+| 0.1232 | 77   | 0.748         | -               | -                        | -                        |
+| 0.1344 | 84   | 0.5821        | -               | -                        | -                        |
+| 0.1456 | 91   | 0.3756        | -               | -                        | -                        |
+| 0.1568 | 98   | 0.7135        | -               | -                        | -                        |
+| 0.168  | 105  | 0.5058        | -               | -                        | -                        |
+| 0.1792 | 112  | 0.4432        | -               | -                        | -                        |
+| 0.1904 | 119  | 0.428         | -               | -                        | -                        |
+| 0.2016 | 126  | 0.3416        | 0.3792          | 0.8132                   | -                        |
+| 0.2128 | 133  | 0.2572        | -               | -                        | -                        |
+| 0.224  | 140  | 0.1803        | -               | -                        | -                        |
+| 0.2352 | 147  | 0.2389        | -               | -                        | -                        |
+| 0.2464 | 154  | 0.3825        | -               | -                        | -                        |
+| 0.2576 | 161  | 0.2629        | -               | -                        | -                        |
+| 0.2688 | 168  | 0.4079        | -               | -                        | -                        |
+| 0.28   | 175  | 0.2106        | -               | -                        | -                        |
+| 0.2912 | 182  | 0.2089        | -               | -                        | -                        |
+| 0.3024 | 189  | 0.2215        | 0.2772          | 0.8425                   | -                        |
+| 0.3136 | 196  | 0.2142        | -               | -                        | -                        |
+| 0.3248 | 203  | 0.2895        | -               | -                        | -                        |
+| 0.336  | 210  | 0.2901        | -               | -                        | -                        |
+| 0.3472 | 217  | 0.2332        | -               | -                        | -                        |
+| 0.3584 | 224  | 0.2538        | -               | -                        | -                        |
+| 0.3696 | 231  | 0.1969        | -               | -                        | -                        |
+| 0.3808 | 238  | 0.2055        | -               | -                        | -                        |
+| 0.392  | 245  | 0.2135        | -               | -                        | -                        |
+| 0.4032 | 252  | 0.2177        | 0.2362          | 0.8513                   | -                        |
+| 0.4144 | 259  | 0.2228        | -               | -                        | -                        |
+| 0.4256 | 266  | 0.3378        | -               | -                        | -                        |
+| 0.4368 | 273  | 0.1516        | -               | -                        | -                        |
+| 0.448  | 280  | 0.1068        | -               | -                        | -                        |
+| 0.4592 | 287  | 0.1817        | -               | -                        | -                        |
+| 0.4704 | 294  | 0.1007        | -               | -                        | -                        |
+| 0.4816 | 301  | 0.1488        | -               | -                        | -                        |
+| 0.4928 | 308  | 0.1713        | -               | -                        | -                        |
+| 0.504  | 315  | 0.1963        | 0.2124          | 0.8633                   | -                        |
+| 0.5152 | 322  | 0.2033        | -               | -                        | -                        |
+| 0.5264 | 329  | 0.1321        | -               | -                        | -                        |
+| 0.5376 | 336  | 0.1642        | -               | -                        | -                        |
+| 0.5488 | 343  | 0.1352        | -               | -                        | -                        |
+| 0.56   | 350  | 0.1918        | -               | -                        | -                        |
+| 0.5712 | 357  | 0.1315        | -               | -                        | -                        |
+| 0.5824 | 364  | 0.2275        | -               | -                        | -                        |
+| 0.5936 | 371  | 0.0844        | -               | -                        | -                        |
+| 0.6048 | 378  | 0.0854        | 0.2052          | 0.8689                   | -                        |
+| 0.616  | 385  | 0.1572        | -               | -                        | -                        |
+| 0.6272 | 392  | 0.1111        | -               | -                        | -                        |
+| 0.6384 | 399  | 0.1958        | -               | -                        | -                        |
+| 0.6496 | 406  | 0.0896        | -               | -                        | -                        |
+| 0.6608 | 413  | 0.1532        | -               | -                        | -                        |
+| 0.672  | 420  | 0.1387        | -               | -                        | -                        |
+| 0.6832 | 427  | 0.0942        | -               | -                        | -                        |
+| 0.6944 | 434  | 0.1696        | -               | -                        | -                        |
+| 0.7056 | 441  | 0.1501        | 0.1898          | 0.8742                   | -                        |
+| 0.7168 | 448  | 0.143         | -               | -                        | -                        |
+| 0.728  | 455  | 0.1221        | -               | -                        | -                        |
+| 0.7392 | 462  | 0.1082        | -               | -                        | -                        |
+| 0.7504 | 469  | 0.1601        | -               | -                        | -                        |
+| 0.7616 | 476  | 0.1504        | -               | -                        | -                        |
+| 0.7728 | 483  | 0.1513        | -               | -                        | -                        |
+| 0.784  | 490  | 0.1108        | -               | -                        | -                        |
+| 0.7952 | 497  | 0.1086        | -               | -                        | -                        |
+| 0.8064 | 504  | 0.11          | 0.1689          | 0.8782                   | -                        |
+| 0.8176 | 511  | 0.1562        | -               | -                        | -                        |
+| 0.8288 | 518  | 0.1291        | -               | -                        | -                        |
+| 0.84   | 525  | 0.0687        | -               | -                        | -                        |
+| 0.8512 | 532  | 0.0966        | -               | -                        | -                        |
+| 0.8624 | 539  | 0.0977        | -               | -                        | -                        |
+| 0.8736 | 546  | 0.089         | -               | -                        | -                        |
+| 0.8848 | 553  | 0.0697        | -               | -                        | -                        |
+| 0.896  | 560  | 0.0561        | -               | -                        | -                        |
+| 0.9072 | 567  | 0.1078        | 0.1779          | 0.8860                   | -                        |
+| 0.9184 | 574  | 0.1425        | -               | -                        | -                        |
+| 0.9296 | 581  | 0.1273        | -               | -                        | -                        |
+| 0.9408 | 588  | 0.1215        | -               | -                        | -                        |
+| 0.952  | 595  | 0.1311        | -               | -                        | -                        |
+| 0.9632 | 602  | 0.0512        | -               | -                        | -                        |
+| 0.9744 | 609  | 0.0735        | -               | -                        | -                        |
+| 0.9856 | 616  | 0.1125        | -               | -                        | -                        |
+| 0.9968 | 623  | 0.1359        | -               | -                        | -                        |
+| -1     | -1   | -             | -               | -                        | 0.8849                   |
+
+
+### Environmental Impact
+Carbon emissions were measured using [CodeCarbon](https://github.com/mlco2/codecarbon).
+- **Energy Consumed**: 0.054 kWh
+- **Carbon Emitted**: 0.015 kg of CO2
+- **Hours Used**: 0.169 hours
+
+### Training Hardware
+- **On Cloud**: No
+- **GPU Model**: 1 x NVIDIA GeForce RTX 3090
+- **CPU Model**: 13th Gen Intel(R) Core(TM) i7-13700K
+- **RAM Size**: 31.78 GB
+
+### Framework Versions
+- Python: 3.11.6
+- Sentence Transformers: 5.2.0.dev0
+- Transformers: 4.57.0.dev0
+- PyTorch: 2.8.0+cu128
+- Accelerate: 1.6.0
+- Datasets: 3.6.0
+- Tokenizers: 0.22.1
+
+## 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",
+}
+```
+
+#### MultipleNegativesRankingLoss
+```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.*
+-->

config.json

@@ -0,0 +1,37 @@
+{
+  "architectures": [
+    "SiglipModel"
+  ],
+  "dtype": "float32",
+  "initializer_factor": 1.0,
+  "model_type": "siglip",
+  "text_config": {
+    "attention_dropout": 0.0,
+    "dtype": "float32",
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 768,
+    "intermediate_size": 3072,
+    "layer_norm_eps": 1e-06,
+    "max_position_embeddings": 64,
+    "model_type": "siglip_text_model",
+    "num_attention_heads": 12,
+    "num_hidden_layers": 12,
+    "projection_size": 768,
+    "vocab_size": 32000
+  },
+  "transformers_version": "4.57.0.dev0",
+  "vision_config": {
+    "attention_dropout": 0.0,
+    "dtype": "float32",
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 768,
+    "image_size": 512,
+    "intermediate_size": 3072,
+    "layer_norm_eps": 1e-06,
+    "model_type": "siglip_vision_model",
+    "num_attention_heads": 12,
+    "num_channels": 3,
+    "num_hidden_layers": 12,
+    "patch_size": 16
+  }
+}

config_sentence_transformers.json

@@ -0,0 +1,14 @@
+{
+  "model_type": "SentenceTransformer",
+  "__version__": {
+    "sentence_transformers": "5.2.0.dev0",
+    "transformers": "4.57.0.dev0",
+    "pytorch": "2.8.0+cu128"
+  },
+  "prompts": {
+    "query": "",
+    "document": ""
+  },
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ecf495ea7c4acb8a9b426f035ab89bf5d0fb9717d5c9b268871187b988f6bf93
+size 815215944

modules.json

@@ -0,0 +1,8 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  }
+]

sentence_bert_config.json

@@ -0,0 +1,14 @@
+{
+    "transformer_task": "feature-extraction",
+    "modality_config": {
+        "text": {
+            "method": "get_text_features",
+            "method_output_name": null
+        },
+        "image": {
+            "method": "get_image_features",
+            "method_output_name": null
+        }
+    },
+    "module_output_name": "sentence_embedding"
+}

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": true,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "</s>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": true,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": true,
+    "single_word": false
+  }
+}

spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e5036bed065526c3c212dfbe288752391797c4bb1a284aa18c9a0b23fcaf8ec
+size 798330

tokenizer_config.json

@@ -0,0 +1,35 @@
+{
+  "added_tokens_decoder": {
+    "1": {
+      "content": "</s>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<unk>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "clean_up_tokenization_spaces": true,
+  "do_convert_rgb": true,
+  "do_lower_case": true,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "model_input_names": [
+    "input_ids"
+  ],
+  "model_max_length": 64,
+  "pad_token": "</s>",
+  "processor_class": "SiglipProcessor",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "SiglipTokenizer",
+  "unk_token": "<unk>"
+}