Add new SentenceTransformer model

.gitattributes

@@ -33,3 +33,4 @@ 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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+  "word_embedding_dimension": 768,
+  "pooling_mode_cls_token": false,
+  "pooling_mode_mean_tokens": true,
+  "pooling_mode_max_tokens": false,
+  "pooling_mode_mean_sqrt_len_tokens": false,
+  "pooling_mode_weightedmean_tokens": false,
+  "pooling_mode_lasttoken": false,
+  "include_prompt": true
+}

README.md

@@ -0,0 +1,482 @@
+---
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- dataset_size:2602
+- loss:ContrastiveLoss
+base_model: sentence-transformers/paraphrase-multilingual-mpnet-base-v2
+widget:
+- source_sentence: Data triwulanan GDS, investasi non-fin, pinjaman neto pemerintah
+    (triliun) 2010
+  sentences:
+  - 'Nilai Ekspor Menurut Pelabuhan Utama (Nilai FOB: juta US$) 2000-2023'
+  - Suhu Minimum, Rata-Rata, dan Maksimum di Stasiun Pengamatan BMKG (oC), 2011-2015
+  - 'Nilai Ekspor Menurut Negara Tujuan Utama (Nilai FOB: juta US$), 2000-2023'
+- source_sentence: Data triwulanan GDS, investasi non-fin, pinjaman neto pemerintah
+    (triliun) 2010
+  sentences:
+  - Tabungan Bruto, Investasi Nonfinansial, dan Pinjaman Neto Triwulanan Sektor Pemerintahan
+    Umum (triliun rupiah), 2009-2015
+  - Produksi Perikanan Budidaya Menurut Provinsi dan Jenis Budidaya, 2000-2020
+  - Rata-rata Pendapatan Bersih Berusaha Sendiri Menurut Provinsi dan Kelompok Umur
+    (ribu rupiah), 2017
+- source_sentence: Gaji bersih vs kelompok umur dan lapangan pekerjaan, 2023
+  sentences:
+  - Investasi Nonfinansial Menurut Sektor (triliun rupiah), 2008-2014
+  - Posisi Kredit Usaha Mikro, Kecil, dan Menengah (UMKM) 1 pada Bank Umum (miliar
+    rupiah), 2012-2016
+  - Ringkasan Neraca Arus Dana, Triwulan I, 2013*), (Miliar Rupiah)
+- source_sentence: Data utang luar negeri Indonesia (pemerintah dan BI), detail kreditor
+    dan syarat, tahun 2010
+  sentences:
+  - Angka Partisipasi Sekolah (APS) Penduduk Umur 7-18 Tahun Menurut Klasifikasi Desa,
+    Jenis Kelamin, dan Kelompok Umur, 2009-2023
+  - Indeks Integritas Ujian Nasional
+  - Rekapitulasi Luas Penutupan Lahan Hutan dan Non Hutan Menurut Provinsi Tahun 2014-2022
+    (Ribu Ha)
+- source_sentence: Laporan keuangan perusahaan asuransi wajib & BPJS akhir 2015
+  sentences:
+  - Indeks Harga Konsumen Menurut Kelompok Pengeluaran, 2020-2023
+  - Ringkasan Neraca Arus Dana, Triwulan I, 2013*), (Miliar Rupiah)
+  - Rata-rata Konsumsi dan Pengeluaran Perkapita Seminggu Menurut Komoditi Makanan
+    dan Golongan Pengeluaran per Kapita Seminggu di Provinsi Jawa Timur, 2018-2023
+datasets:
+- yahyaabd/bps-statictable-query-title-pairs
+pipeline_tag: sentence-similarity
+library_name: sentence-transformers
+metrics:
+- pearson_cosine
+- spearman_cosine
+model-index:
+- name: SentenceTransformer based on sentence-transformers/paraphrase-multilingual-mpnet-base-v2
+  results:
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: allstats semantic base v1 eval
+      type: allstats-semantic-base-v1-eval
+    metrics:
+    - type: pearson_cosine
+      value: 0.8898188833771716
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.779923841631983
+      name: Spearman Cosine
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: allstat semantic base v1 test
+      type: allstat-semantic-base-v1-test
+    metrics:
+    - type: pearson_cosine
+      value: 0.9039024076661341
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.8077065435723709
+      name: Spearman Cosine
+---
+
+# SentenceTransformer based on sentence-transformers/paraphrase-multilingual-mpnet-base-v2
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [sentence-transformers/paraphrase-multilingual-mpnet-base-v2](https://huggingface.co/sentence-transformers/paraphrase-multilingual-mpnet-base-v2) on the [bps-statictable-query-title-pairs](https://huggingface.co/datasets/yahyaabd/bps-statictable-query-title-pairs) dataset. It maps sentences & paragraphs to a 768-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:** [sentence-transformers/paraphrase-multilingual-mpnet-base-v2](https://huggingface.co/sentence-transformers/paraphrase-multilingual-mpnet-base-v2) <!-- at revision 75c57757a97f90ad739aca51fa8bfea0e485a7f2 -->
+- **Maximum Sequence Length:** 128 tokens
+- **Output Dimensionality:** 768 dimensions
+- **Similarity Function:** Cosine Similarity
+- **Training Dataset:**
+    - [bps-statictable-query-title-pairs](https://huggingface.co/datasets/yahyaabd/bps-statictable-query-title-pairs)
+<!-- - **Language:** Unknown -->
+<!-- - **License:** Unknown -->
+
+### 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({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: XLMRobertaModel 
+  (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
+)
+```
+
+## 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("yahyaabd/allstats-ir-mpnet-base-v1")
+# Run inference
+sentences = [
+    'Laporan keuangan perusahaan asuransi wajib & BPJS akhir 2015',
+    'Ringkasan Neraca Arus Dana, Triwulan I, 2013*), (Miliar Rupiah)',
+    'Rata-rata Konsumsi dan Pengeluaran Perkapita Seminggu Menurut Komoditi Makanan dan Golongan Pengeluaran per Kapita Seminggu di Provinsi Jawa Timur, 2018-2023',
+]
+embeddings = model.encode(sentences)
+print(embeddings.shape)
+# [3, 768]
+
+# Get the similarity scores for the embeddings
+similarities = model.similarity(embeddings, embeddings)
+print(similarities.shape)
+# [3, 3]
+```
+
+<!--
+### 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
+
+#### Semantic Similarity
+
+* Datasets: `allstats-semantic-base-v1-eval` and `allstat-semantic-base-v1-test`
+* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
+
+| Metric              | allstats-semantic-base-v1-eval | allstat-semantic-base-v1-test |
+|:--------------------|:-------------------------------|:------------------------------|
+| pearson_cosine      | 0.8898                         | 0.9039                        |
+| **spearman_cosine** | **0.7799**                     | **0.8077**                    |
+
+<!--
+## 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
+
+#### bps-statictable-query-title-pairs
+
+* Dataset: [bps-statictable-query-title-pairs](https://huggingface.co/datasets/yahyaabd/bps-statictable-query-title-pairs) at [c7df38f](https://huggingface.co/datasets/yahyaabd/bps-statictable-query-title-pairs/tree/c7df38f8b228efe13b1589b94c78fc7b57f02b58)
+* Size: 2,602 training samples
+* Columns: <code>query</code>, <code>doc</code>, and <code>label</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | query                                                                             | doc                                                                               | label                                           |
+  |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:------------------------------------------------|
+  | type    | string                                                                            | string                                                                            | int                                             |
+  | details | <ul><li>min: 5 tokens</li><li>mean: 18.35 tokens</li><li>max: 35 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 25.83 tokens</li><li>max: 58 tokens</li></ul> | <ul><li>0: ~66.50%</li><li>1: ~33.50%</li></ul> |
+* Samples:
+  | query                                                                                                            | doc                                                                                                        | label          |
+  |:-----------------------------------------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------------------------------|:---------------|
+  | <code>Pertumbuhan populasi provinsi di Indonesia 1971-2024</code>                                                | <code>Kecepatan Angin dan Kelembaban di Stasiun Pengamatan BMKG, 2000-2010</code>                          | <code>0</code> |
+  | <code>Perbandingan upah nominal dan riil pekerja pertanian di Indonesia (tahun dasar 2012), periode 2017.</code> | <code>Upah Nominal dan Riil Buruh Tani di Indonesia (Rupiah), 2009-2019 (2012=100)</code>                  | <code>1</code> |
+  | <code>Laporan singkat cash flow statement Q4/2005</code>                                                         | <code>Nilai Produksi dan Biaya Produksi per Hektar Usaha Tanaman Bawang Merah dan Cabai Merah, 2014</code> | <code>0</code> |
+* Loss: [<code>ContrastiveLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#contrastiveloss) with these parameters:
+  ```json
+  {
+      "distance_metric": "SiameseDistanceMetric.COSINE_DISTANCE",
+      "margin": 0.5,
+      "size_average": true
+  }
+  ```
+
+### Evaluation Dataset
+
+#### bps-statictable-query-title-pairs
+
+* Dataset: [bps-statictable-query-title-pairs](https://huggingface.co/datasets/yahyaabd/bps-statictable-query-title-pairs) at [c7df38f](https://huggingface.co/datasets/yahyaabd/bps-statictable-query-title-pairs/tree/c7df38f8b228efe13b1589b94c78fc7b57f02b58)
+* Size: 558 evaluation samples
+* Columns: <code>query</code>, <code>doc</code>, and <code>label</code>
+* Approximate statistics based on the first 558 samples:
+  |         | query                                                                             | doc                                                                               | label                                           |
+  |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:------------------------------------------------|
+  | type    | string                                                                            | string                                                                            | int                                             |
+  | details | <ul><li>min: 4 tokens</li><li>mean: 18.45 tokens</li><li>max: 35 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 26.04 tokens</li><li>max: 58 tokens</li></ul> | <ul><li>0: ~70.97%</li><li>1: ~29.03%</li></ul> |
+* Samples:
+  | query                                                                                                                   | doc                                                                                                                                                                                 | label          |
+  |:------------------------------------------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:---------------|
+  | <code>Data pengeluaran makanan rata-rata warga Sulteng per minggu di tahun 2022, berdasarkan kelompok pendapatan</code> | <code>Sistem Neraca Sosial Ekonomi Indonesia Tahun 2022 (84 x 84)</code>                                                                                                            | <code>0</code> |
+  | <code>Konsumsi & belanja makanan per orang di NTB, beda kelompok pengeluaran, 2021</code>                               | <code>Rata-rata Konsumsi dan Pengeluaran Perkapita Seminggu Menurut Komoditi Makanan dan Golongan Pengeluaran per Kapita Seminggu di Provinsi Nusa Tenggara Barat, 2018-2023</code> | <code>1</code> |
+  | <code>Bagaimana perbandingan PNS pria dan wanita di berbagai golongan tahun 2014?</code>                                | <code>Penduduk Berumur 15 Tahun Ke Atas Menurut Provinsi dan Jenis Kegiatan Selama Seminggu yang Lalu, 2008 - 2024</code>                                                           | <code>0</code> |
+* Loss: [<code>ContrastiveLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#contrastiveloss) with these parameters:
+  ```json
+  {
+      "distance_metric": "SiameseDistanceMetric.COSINE_DISTANCE",
+      "margin": 0.5,
+      "size_average": true
+  }
+  ```
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `eval_strategy`: steps
+- `per_device_train_batch_size`: 32
+- `per_device_eval_batch_size`: 32
+- `num_train_epochs`: 4
+- `warmup_ratio`: 0.1
+- `fp16`: True
+- `load_best_model_at_end`: True
+- `eval_on_start`: True
+
+#### 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`: 32
+- `per_device_eval_batch_size`: 32
+- `per_gpu_train_batch_size`: None
+- `per_gpu_eval_batch_size`: None
+- `gradient_accumulation_steps`: 1
+- `eval_accumulation_steps`: None
+- `torch_empty_cache_steps`: None
+- `learning_rate`: 5e-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`: 4
+- `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
+- `no_cuda`: False
+- `use_cpu`: False
+- `use_mps_device`: False
+- `seed`: 42
+- `data_seed`: None
+- `jit_mode_eval`: False
+- `use_ipex`: False
+- `bf16`: False
+- `fp16`: True
+- `fp16_opt_level`: O1
+- `half_precision_backend`: auto
+- `bf16_full_eval`: False
+- `fp16_full_eval`: False
+- `tf32`: None
+- `local_rank`: 0
+- `ddp_backend`: None
+- `tpu_num_cores`: None
+- `tpu_metrics_debug`: False
+- `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`: True
+- `ignore_data_skip`: False
+- `fsdp`: []
+- `fsdp_min_num_params`: 0
+- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
+- `fsdp_transformer_layer_cls_to_wrap`: None
+- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
+- `deepspeed`: None
+- `label_smoothing_factor`: 0.0
+- `optim`: adamw_torch
+- `optim_args`: None
+- `adafactor`: False
+- `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
+- `gradient_checkpointing`: False
+- `gradient_checkpointing_kwargs`: None
+- `include_inputs_for_metrics`: False
+- `include_for_metrics`: []
+- `eval_do_concat_batches`: True
+- `fp16_backend`: auto
+- `push_to_hub_model_id`: None
+- `push_to_hub_organization`: None
+- `mp_parameters`: 
+- `auto_find_batch_size`: False
+- `full_determinism`: False
+- `torchdynamo`: None
+- `ray_scope`: last
+- `ddp_timeout`: 1800
+- `torch_compile`: False
+- `torch_compile_backend`: None
+- `torch_compile_mode`: None
+- `dispatch_batches`: None
+- `split_batches`: None
+- `include_tokens_per_second`: False
+- `include_num_input_tokens_seen`: False
+- `neftune_noise_alpha`: None
+- `optim_target_modules`: None
+- `batch_eval_metrics`: False
+- `eval_on_start`: True
+- `use_liger_kernel`: False
+- `eval_use_gather_object`: False
+- `average_tokens_across_devices`: False
+- `prompts`: None
+- `batch_sampler`: batch_sampler
+- `multi_dataset_batch_sampler`: proportional
+
+</details>
+
+### Training Logs
+| Epoch      | Step    | Training Loss | Validation Loss | allstats-semantic-base-v1-eval_spearman_cosine | allstat-semantic-base-v1-test_spearman_cosine |
+|:----------:|:-------:|:-------------:|:---------------:|:----------------------------------------------:|:---------------------------------------------:|
+| 0          | 0       | -             | 0.0099          | 0.7449                                         | -                                             |
+| 0.1220     | 10      | 0.0091        | 0.0065          | 0.7640                                         | -                                             |
+| 0.2439     | 20      | 0.0059        | 0.0040          | 0.7743                                         | -                                             |
+| 0.3659     | 30      | 0.0045        | 0.0036          | 0.7688                                         | -                                             |
+| 0.4878     | 40      | 0.0045        | 0.0036          | 0.7694                                         | -                                             |
+| 0.6098     | 50      | 0.0032        | 0.0037          | 0.7758                                         | -                                             |
+| 0.7317     | 60      | 0.003         | 0.0025          | 0.7753                                         | -                                             |
+| 0.8537     | 70      | 0.0035        | 0.0029          | 0.7710                                         | -                                             |
+| 0.9756     | 80      | 0.0028        | 0.0026          | 0.7745                                         | -                                             |
+| 1.0976     | 90      | 0.0015        | 0.0023          | 0.7754                                         | -                                             |
+| 1.2195     | 100     | 0.0013        | 0.0021          | 0.7760                                         | -                                             |
+| 1.3415     | 110     | 0.0013        | 0.0022          | 0.7751                                         | -                                             |
+| 1.4634     | 120     | 0.002         | 0.0021          | 0.7746                                         | -                                             |
+| 1.5854     | 130     | 0.0012        | 0.0020          | 0.7750                                         | -                                             |
+| 1.7073     | 140     | 0.0007        | 0.0019          | 0.7740                                         | -                                             |
+| 1.8293     | 150     | 0.0008        | 0.0019          | 0.7738                                         | -                                             |
+| 1.9512     | 160     | 0.0026        | 0.0018          | 0.7772                                         | -                                             |
+| 2.0732     | 170     | 0.0009        | 0.0019          | 0.7785                                         | -                                             |
+| 2.1951     | 180     | 0.0005        | 0.0020          | 0.7781                                         | -                                             |
+| 2.3171     | 190     | 0.0009        | 0.0017          | 0.7777                                         | -                                             |
+| 2.4390     | 200     | 0.0005        | 0.0017          | 0.7773                                         | -                                             |
+| 2.5610     | 210     | 0.0004        | 0.0018          | 0.7766                                         | -                                             |
+| 2.6829     | 220     | 0.0006        | 0.0018          | 0.7762                                         | -                                             |
+| 2.8049     | 230     | 0.0006        | 0.0019          | 0.7756                                         | -                                             |
+| 2.9268     | 240     | 0.0016        | 0.0019          | 0.7777                                         | -                                             |
+| 3.0488     | 250     | 0.0008        | 0.0018          | 0.7796                                         | -                                             |
+| 3.1707     | 260     | 0.0005        | 0.0017          | 0.7802                                         | -                                             |
+| **3.2927** | **270** | **0.0006**    | **0.0017**      | **0.7802**                                     | **-**                                         |
+| 3.4146     | 280     | 0.0004        | 0.0017          | 0.7805                                         | -                                             |
+| 3.5366     | 290     | 0.0004        | 0.0017          | 0.7805                                         | -                                             |
+| 3.6585     | 300     | 0.0003        | 0.0018          | 0.7802                                         | -                                             |
+| 3.7805     | 310     | 0.0006        | 0.0018          | 0.7800                                         | -                                             |
+| 3.9024     | 320     | 0.0003        | 0.0018          | 0.7799                                         | -                                             |
+| -1         | -1      | -             | -               | -                                              | 0.8077                                        |
+
+* The bold row denotes the saved checkpoint.
+
+### Framework Versions
+- Python: 3.10.12
+- Sentence Transformers: 3.4.0
+- Transformers: 4.48.1
+- PyTorch: 2.5.1+cu124
+- Accelerate: 1.3.0
+- Datasets: 3.2.0
+- Tokenizers: 0.21.0
+
+## 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",
+}
+```
+
+#### ContrastiveLoss
+```bibtex
+@inproceedings{hadsell2006dimensionality,
+    author={Hadsell, R. and Chopra, S. and LeCun, Y.},
+    booktitle={2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06)},
+    title={Dimensionality Reduction by Learning an Invariant Mapping},
+    year={2006},
+    volume={2},
+    number={},
+    pages={1735-1742},
+    doi={10.1109/CVPR.2006.100}
+}
+```
+
+<!--
+## 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 +1,29 @@
+{
+  "_name_or_path": "sentence-transformers/paraphrase-multilingual-mpnet-base-v2",
+  "architectures": [
+    "XLMRobertaModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.48.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.4.0",
+    "transformers": "4.48.1",
+    "pytorch": "2.5.1+cu124"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60fd383aad3df49ab7bee85f88a813c97003cf19083b2b0f81f4f0648ad597fb
+size 1112197096

modules.json

@@ -0,0 +1,14 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  }
+]

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 128,
+  "do_lower_case": false
+}

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cad551d5600a84242d0973327029452a1e3672ba6313c2a3c3d69c4310e12719
+size 17082987

tokenizer_config.json

@@ -0,0 +1,62 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "max_length": 128,
+  "model_max_length": 128,
+  "pad_to_multiple_of": null,
+  "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "</s>",
+  "stride": 0,
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<unk>"
+}