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": 1024,
+    "pooling_mode_cls_token": false,
+    "pooling_mode_mean_tokens": false,
+    "pooling_mode_max_tokens": false,
+    "pooling_mode_mean_sqrt_len_tokens": false,
+    "pooling_mode_weightedmean_tokens": false,
+    "pooling_mode_lasttoken": true,
+    "include_prompt": true
+}

README.md

@@ -0,0 +1,616 @@
+---
+language:
+- tr
+license: apache-2.0
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- dataset_size:215676
+- loss:MatryoshkaLoss
+- loss:CachedMultipleNegativesRankingLoss
+base_model: Qwen/Qwen3-Embedding-0.6B
+widget:
+- source_sentence: Ortak Havuz Tarifesi kapsamında her bir hat için aylık sabit ücret
+    25,5 TL olarak belirlenmiştir ve bu ücret KDV ile ÖİV dahil olarak hesaplanmıştır.
+  sentences:
+  - Vodafone'un Ortak Havuz Tarifesi, müşterilere ücretsiz olarak sunulmaktadır ve
+    herhangi bir sabit ücret talep edilmemektedir.
+  - Her bir hat için Ortak Havuz Tarifesi'nin aylık sabit ücreti, vergiler dahil 25,5
+    TL'dir.
+  - Geleceğin Karakartalı, Vodafone ve Beşiktaş JK'nin ortak çalışmasıyla genç futbol
+    yeteneklerini Türkiye çapında keşfetmeyi hedefleyen bir projedir.
+- source_sentence: Taşınma durumunda, teknik altyapı eksikliği nedeniyle Vodafone
+    Evde Fiber İnternet hizmeti sağlanamazsa, cezai işlem uygulanmaz ve alternatif
+    hizmetlere geçiş yapılabilir.
+  sentences:
+  - Vodafone faturasız tarifelerinde, yenileme gününde yeterli bakiye bulunmuyorsa
+    içerikler yenilenmez, ancak daha önce yüklenen içerikler bakiye olmadan kullanılabilir.
+  - Vodafone Evde Fiber İnternet hizmeti taşınma sırasında altyapı eksikliği nedeniyle
+    sağlanamazsa, aboneye ceza uygulanır ve alternatif hizmet sunulmaz.
+  - Vodafone Evde Fiber İnternet hizmeti taşınma sırasında altyapı eksikliği nedeniyle
+    sağlanamazsa, aboneye cezai işlem uygulanmaz ve ADSL veya Fiber Hız hizmetine
+    geçiş yapılabilir.
+- source_sentence: Tarife kapsamında sunulan dakika, SMS ve internet hakları, belirli
+    bir limitin aşılması durumunda ek paketlerle ücretlendirilir.
+  sentences:
+  - Vodafone'un tarifelerinde aşım durumunda ek paketler yerine ücretsiz kullanım
+    hakkı sunulmaktadır.
+  - Vodafone'un geçmiş kampanyalarında, Samsung Note 3 Neo en pahalı cihazlardan biri
+    olarak müşterilere sunulmuştur.
+  - Uyumlu 5 Tarifesi'nde verilen dakika, SMS ve internet hakları bittiğinde, ek paketler
+    devreye girerek avantajlı fiyatlarla ücretlendirme yapılır.
+- source_sentence: Mobil numara taşınabilirliği olan ülkelerdeki Vodafone operatörlerine
+    yapılan aramalarda, diğer mobil operatörlerin prefikslerini içeren numaralar indirimli
+    tarifeden yararlanamaz.
+  sentences:
+  - Vodafone operatörlerine yapılan aramalarda, mobil numara taşınabilirliği olan
+    ülkelerdeki diğer operatörlerin prefikslerini içeren numaralar indirimli fiyatlara
+    dahil edilmez.
+  - Vodafone'un tarifelerinde ücretsiz pass paketi yer almazken, Her Şey Dahil Pasaport
+    paketi ücretli olarak sunulmaktadır.
+  - Dünya Küçük Kurumsal tarifesi, yurtdışı aramalar için tüm numaralara eşit fiyatlandırma
+    sunar ve prefiks kısıtlaması içermez.
+- source_sentence: Vodafone hattınızın aktivasyonu sırasında eksik evraklarınızın
+    tamamlanması gerektiği belirtilmiştir. Hattınızın iptal olmaması için 3 gün içinde
+    Vodafone mağazasını ziyaret etmeniz önemlidir.
+  sentences:
+  - Vodafone, boşanmış annelerin çocuklarına gençlik tarifesi tanımlaması için kimlik
+    doğrulama ve kullanıcı tanımlama süreçlerini Cep Merkezlerinde gerçekleştirmektedir.
+  - Vodafone hattınızın aktivasyonu sırasında herhangi bir evrak eksikliği bulunmamaktadır.
+    Hattınız otomatik olarak aktif hale gelecektir.
+  - Vodafone hattınızın aktif hale gelebilmesi için eksik olan abonelik sözleşmesi
+    ve kimlik belgelerinizi tamamlamanız gerekmektedir. Bu işlemi 3 gün içinde Vodafone
+    mağazasında gerçekleştirebilirsiniz.
+datasets:
+- seroe/vodex-turkish-triplets-large
+pipeline_tag: sentence-similarity
+library_name: sentence-transformers
+metrics:
+- cosine_accuracy
+model-index:
+- name: Qwen3-Embedding-0.6B Türkçe Triplet Matryoshka
+  results:
+  - task:
+      type: triplet
+      name: Triplet
+    dataset:
+      name: tr triplet dev 1024d
+      type: tr-triplet-dev-1024d
+    metrics:
+    - type: cosine_accuracy
+      value: 0.998831570148468
+      name: Cosine Accuracy
+  - task:
+      type: triplet
+      name: Triplet
+    dataset:
+      name: tr triplet dev 768d
+      type: tr-triplet-dev-768d
+    metrics:
+    - type: cosine_accuracy
+      value: 0.9987481236457825
+      name: Cosine Accuracy
+  - task:
+      type: triplet
+      name: Triplet
+    dataset:
+      name: tr triplet dev 512d
+      type: tr-triplet-dev-512d
+    metrics:
+    - type: cosine_accuracy
+      value: 0.9986646771430969
+      name: Cosine Accuracy
+  - task:
+      type: triplet
+      name: Triplet
+    dataset:
+      name: tr triplet dev 256d
+      type: tr-triplet-dev-256d
+    metrics:
+    - type: cosine_accuracy
+      value: 0.9984142780303955
+      name: Cosine Accuracy
+  - task:
+      type: triplet
+      name: Triplet
+    dataset:
+      name: all nli test 1024d
+      type: all-nli-test-1024d
+    metrics:
+    - type: cosine_accuracy
+      value: 0.9987481236457825
+      name: Cosine Accuracy
+  - task:
+      type: triplet
+      name: Triplet
+    dataset:
+      name: all nli test 768d
+      type: all-nli-test-768d
+    metrics:
+    - type: cosine_accuracy
+      value: 0.9986646771430969
+      name: Cosine Accuracy
+  - task:
+      type: triplet
+      name: Triplet
+    dataset:
+      name: all nli test 512d
+      type: all-nli-test-512d
+    metrics:
+    - type: cosine_accuracy
+      value: 0.9986646771430969
+      name: Cosine Accuracy
+  - task:
+      type: triplet
+      name: Triplet
+    dataset:
+      name: all nli test 256d
+      type: all-nli-test-256d
+    metrics:
+    - type: cosine_accuracy
+      value: 0.99833083152771
+      name: Cosine Accuracy
+---
+
+# Qwen3-Embedding-0.6B Türkçe Triplet Matryoshka
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [Qwen/Qwen3-Embedding-0.6B](https://huggingface.co/Qwen/Qwen3-Embedding-0.6B) on the [vodex-turkish-triplets-large](https://huggingface.co/datasets/seroe/vodex-turkish-triplets-large) dataset. It maps sentences & paragraphs to a 1024-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:** [Qwen/Qwen3-Embedding-0.6B](https://huggingface.co/Qwen/Qwen3-Embedding-0.6B) <!-- at revision 744169034862c8eec56628663995004342e4e449 -->
+- **Maximum Sequence Length:** 32768 tokens
+- **Output Dimensionality:** 1024 dimensions
+- **Similarity Function:** Cosine Similarity
+- **Training Dataset:**
+    - [vodex-turkish-triplets-large](https://huggingface.co/datasets/seroe/vodex-turkish-triplets-large)
+- **Language:** tr
+- **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({'max_seq_length': 32768, 'do_lower_case': False}) with Transformer model: Qwen3Model 
+  (1): Pooling({'word_embedding_dimension': 1024, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': True, 'include_prompt': True})
+  (2): Normalize()
+)
+```
+
+## 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("seroe/Qwen3-Embedding-0.6B-turkish-triplet-matryoshka-v2")
+# Run inference
+sentences = [
+    'Vodafone hattınızın aktivasyonu sırasında eksik evraklarınızın tamamlanması gerektiği belirtilmiştir. Hattınızın iptal olmaması için 3 gün içinde Vodafone mağazasını ziyaret etmeniz önemlidir.',
+    'Vodafone hattınızın aktif hale gelebilmesi için eksik olan abonelik sözleşmesi ve kimlik belgelerinizi tamamlamanız gerekmektedir. Bu işlemi 3 gün içinde Vodafone mağazasında gerçekleştirebilirsiniz.',
+    'Vodafone hattınızın aktivasyonu sırasında herhangi bir evrak eksikliği bulunmamaktadır. Hattınız otomatik olarak aktif hale gelecektir.',
+]
+embeddings = model.encode(sentences)
+print(embeddings.shape)
+# [3, 1024]
+
+# 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
+
+#### Triplet
+
+* Datasets: `tr-triplet-dev-1024d` and `all-nli-test-1024d`
+* Evaluated with [<code>TripletEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.TripletEvaluator) with these parameters:
+  ```json
+  {
+      "truncate_dim": 1024
+  }
+  ```
+
+| Metric              | tr-triplet-dev-1024d | all-nli-test-1024d |
+|:--------------------|:---------------------|:-------------------|
+| **cosine_accuracy** | **0.9988**           | **0.9987**         |
+
+#### Triplet
+
+* Datasets: `tr-triplet-dev-768d` and `all-nli-test-768d`
+* Evaluated with [<code>TripletEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.TripletEvaluator) with these parameters:
+  ```json
+  {
+      "truncate_dim": 768
+  }
+  ```
+
+| Metric              | tr-triplet-dev-768d | all-nli-test-768d |
+|:--------------------|:--------------------|:------------------|
+| **cosine_accuracy** | **0.9987**          | **0.9987**        |
+
+#### Triplet
+
+* Datasets: `tr-triplet-dev-512d` and `all-nli-test-512d`
+* Evaluated with [<code>TripletEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.TripletEvaluator) with these parameters:
+  ```json
+  {
+      "truncate_dim": 512
+  }
+  ```
+
+| Metric              | tr-triplet-dev-512d | all-nli-test-512d |
+|:--------------------|:--------------------|:------------------|
+| **cosine_accuracy** | **0.9987**          | **0.9987**        |
+
+#### Triplet
+
+* Datasets: `tr-triplet-dev-256d` and `all-nli-test-256d`
+* Evaluated with [<code>TripletEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.TripletEvaluator) with these parameters:
+  ```json
+  {
+      "truncate_dim": 256
+  }
+  ```
+
+| Metric              | tr-triplet-dev-256d | all-nli-test-256d |
+|:--------------------|:--------------------|:------------------|
+| **cosine_accuracy** | **0.9984**          | **0.9983**        |
+
+<!--
+## 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
+
+#### vodex-turkish-triplets-large
+
+* Dataset: [vodex-turkish-triplets-large](https://huggingface.co/datasets/seroe/vodex-turkish-triplets-large) at [1fe9d63](https://huggingface.co/datasets/seroe/vodex-turkish-triplets-large/tree/1fe9d63490a69cb96da6b76f4bff1a43c48cbdee)
+* Size: 215,676 training samples
+* Columns: <code>query</code>, <code>positive</code>, and <code>negative</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | query                                                                              | positive                                                                           | negative                                                                           |
+  |:--------|:-----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|
+  | type    | string                                                                             | string                                                                             | string                                                                             |
+  | details | <ul><li>min: 19 tokens</li><li>mean: 44.11 tokens</li><li>max: 90 tokens</li></ul> | <ul><li>min: 21 tokens</li><li>mean: 45.45 tokens</li><li>max: 95 tokens</li></ul> | <ul><li>min: 17 tokens</li><li>mean: 37.27 tokens</li><li>max: 76 tokens</li></ul> |
+* Samples:
+  | query                                                                                                                           | positive                                                                                                                        | negative                                                                                                                                   |
+  |:--------------------------------------------------------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------------------------------------------------|
+  | <code>Vodafone'un Mobil Form Servisi, 12 Şubat 2021 itibarıyla yeni müşteri alımına kapatılmıştır.</code>                       | <code>12 Şubat 2021 tarihinden itibaren Vodafone'un Mobil Form Servisi yeni kullanıcılar için erişime kapatılmıştır.</code>     | <code>Mobil Form Servisi, 2022 yılında yeni müşterilere açılmıştır ve aktif olarak kullanılmaktadır.</code>                                |
+  | <code>Paket, VOIP ve P2P gibi hizmetleri desteklemez ve cihazın 4.5G/3G ayarlarının yapılmış olması gereklidir.</code>          | <code>Vodafone'un paketi, VOIP ve P2P hizmetlerini içermez ve cihazın 4.5G/3G bağlantı ayarlarının aktif olması gerekir.</code> | <code>Paket, VOIP ve P2P hizmetlerini tamamen destekler ve cihaz ayarlarına gerek olmadan kullanılabilir.</code>                           |
+  | <code>Vodafone'un bireysel esnaf tarifeleri, farklı meslek gruplarına özel paket seçenekleriyle geniş bir yelpaze sunar.</code> | <code>Bireysel esnaf tarifeleri, Vodafone tarafından çeşitli meslek gruplarına uygun paketlerle desteklenmektedir.</code>       | <code>Vodafone'un bireysel esnaf tarifeleri, yalnızca belirli bir meslek grubuna hitap eder ve diğer meslekler için uygun değildir.</code> |
+* Loss: [<code>MatryoshkaLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#matryoshkaloss) with these parameters:
+  ```json
+  {
+      "loss": "CachedMultipleNegativesRankingLoss",
+      "matryoshka_dims": [
+          1024,
+          768,
+          512,
+          256
+      ],
+      "matryoshka_weights": [
+          1,
+          1,
+          1,
+          1
+      ],
+      "n_dims_per_step": -1
+  }
+  ```
+
+### Evaluation Dataset
+
+#### vodex-turkish-triplets-large
+
+* Dataset: [vodex-turkish-triplets-large](https://huggingface.co/datasets/seroe/vodex-turkish-triplets-large) at [1fe9d63](https://huggingface.co/datasets/seroe/vodex-turkish-triplets-large/tree/1fe9d63490a69cb96da6b76f4bff1a43c48cbdee)
+* Size: 11,982 evaluation samples
+* Columns: <code>query</code>, <code>positive</code>, and <code>negative</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | query                                                                              | positive                                                                           | negative                                                                           |
+  |:--------|:-----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|
+  | type    | string                                                                             | string                                                                             | string                                                                             |
+  | details | <ul><li>min: 23 tokens</li><li>mean: 44.51 tokens</li><li>max: 97 tokens</li></ul> | <ul><li>min: 20 tokens</li><li>mean: 45.89 tokens</li><li>max: 93 tokens</li></ul> | <ul><li>min: 19 tokens</li><li>mean: 37.23 tokens</li><li>max: 89 tokens</li></ul> |
+* Samples:
+  | query                                                                                                                                                                                                        | positive                                                                                                                                                                                      | negative                                                                                                                                                        |
+  |:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------------------------------------------------------------------------------------|
+  | <code>Vodafone'un 'Yarına Hazır Cihaz Kampanyaları' kapsamında farklı marka ve modellerde cihazlar, çeşitli depolama seçenekleri ve renk alternatifleriyle sunulmaktadır.</code>                             | <code>Vodafone'un cihaz kampanyaları, geniş ürün yelpazesiyle farklı depolama kapasiteleri ve renk seçenekleri sunarak kullanıcıların ihtiyaçlarına hitap etmektedir.</code>                  | <code>Vodafone'un cihaz kampanyaları yalnızca belirli bir marka ve modelle sınırlıdır, diğer seçenekler sunulmamaktadır.</code>                                 |
+  | <code>Devreden ve duran tarifeler, kullanıcıların kullanılmayan internet haklarını bir sonraki döneme taşımasına olanak tanır ve ek paketlerle bu haklar genişletilebilir.</code>                            | <code>Kullanıcılar, devreden ve duran tarifeler sayesinde kullanılmayan internet haklarını bir sonraki aya aktarabilir ve ek paketlerle bu haklarını artırabilir.</code>                      | <code>Devreden ve duran tarifeler, kullanıcıların internet haklarını bir sonraki döneme taşımasına izin vermez, yalnızca mevcut dönemde kullanım sağlar.</code> |
+  | <code>Cebinize Uyan İnternet kampanyası, numara taşıma, yeni hat tesisi veya tarifeler arası geçiş yapan abonelere otomatik olarak tanımlanır. Bu haklar, diğer promosyonlardan sonra kullanılabilir.</code> | <code>Vodafone'un kampanyası, numara taşıma, yeni hat açma veya tarifeler arası geçiş yapan abonelere otomatik olarak tanımlanır ve kullanım sırası diğer promosyonlardan sonra gelir.</code> | <code>Evcil hayvan sahiplenme kampanyasında, yeni bir evcil hayvan edinen kişilere ücretsiz mama ve bakım hizmeti sunulur.</code>                               |
+* Loss: [<code>MatryoshkaLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#matryoshkaloss) with these parameters:
+  ```json
+  {
+      "loss": "CachedMultipleNegativesRankingLoss",
+      "matryoshka_dims": [
+          1024,
+          768,
+          512,
+          256
+      ],
+      "matryoshka_weights": [
+          1,
+          1,
+          1,
+          1
+      ],
+      "n_dims_per_step": -1
+  }
+  ```
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `eval_strategy`: steps
+- `per_device_train_batch_size`: 2048
+- `per_device_eval_batch_size`: 256
+- `weight_decay`: 0.01
+- `num_train_epochs`: 1
+- `lr_scheduler_type`: cosine
+- `warmup_ratio`: 0.05
+- `save_only_model`: True
+- `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`: 2048
+- `per_device_eval_batch_size`: 256
+- `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`: 0.01
+- `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`: cosine
+- `lr_scheduler_kwargs`: {}
+- `warmup_ratio`: 0.05
+- `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`: True
+- `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`: True
+- `fp16`: False
+- `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`: False
+- `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
+- `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`: False
+- `use_liger_kernel`: False
+- `eval_use_gather_object`: False
+- `average_tokens_across_devices`: False
+- `prompts`: None
+- `batch_sampler`: no_duplicates
+- `multi_dataset_batch_sampler`: proportional
+
+</details>
+
+### Training Logs
+| Epoch  | Step | Training Loss | Validation Loss | tr-triplet-dev-1024d_cosine_accuracy | tr-triplet-dev-768d_cosine_accuracy | tr-triplet-dev-512d_cosine_accuracy | tr-triplet-dev-256d_cosine_accuracy | all-nli-test-1024d_cosine_accuracy | all-nli-test-768d_cosine_accuracy | all-nli-test-512d_cosine_accuracy | all-nli-test-256d_cosine_accuracy |
+|:------:|:----:|:-------------:|:---------------:|:------------------------------------:|:-----------------------------------:|:-----------------------------------:|:-----------------------------------:|:----------------------------------:|:---------------------------------:|:---------------------------------:|:---------------------------------:|
+| -1     | -1   | -             | -               | 0.8870                               | 0.8923                              | 0.8932                              | 0.8857                              | -                                  | -                                 | -                                 | -                                 |
+| 0.1132 | 12   | 3.4225        | 0.2848          | 0.9895                               | 0.9901                              | 0.9899                              | 0.9893                              | -                                  | -                                 | -                                 | -                                 |
+| 0.2264 | 24   | 0.8769        | 0.1916          | 0.9935                               | 0.9945                              | 0.9943                              | 0.9937                              | -                                  | -                                 | -                                 | -                                 |
+| 0.3396 | 36   | 0.6888        | 0.1444          | 0.9967                               | 0.9972                              | 0.9969                              | 0.9969                              | -                                  | -                                 | -                                 | -                                 |
+| 0.4528 | 48   | 0.6153        | 0.1289          | 0.9975                               | 0.9978                              | 0.9977                              | 0.9977                              | -                                  | -                                 | -                                 | -                                 |
+| 0.5660 | 60   | 0.5698        | 0.1169          | 0.9981                               | 0.9982                              | 0.9981                              | 0.9977                              | -                                  | -                                 | -                                 | -                                 |
+| 0.6792 | 72   | 0.5513        | -               | 0.9976                               | -                                   | -                                   | -                                   | -                                  | -                                 | -                                 | -                                 |
+| 0.1132 | 12   | 0.4944        | 0.1167          | 0.9977                               | 0.9977                              | 0.9977                              | 0.9974                              | -                                  | -                                 | -                                 | -                                 |
+| 0.2264 | 24   | 0.4464        | 0.1220          | 0.9983                               | 0.9983                              | 0.9982                              | 0.9981                              | -                                  | -                                 | -                                 | -                                 |
+| 0.3396 | 36   | 0.371         | 0.1116          | 0.9982                               | 0.9982                              | 0.9980                              | 0.9976                              | -                                  | -                                 | -                                 | -                                 |
+| 0.4528 | 48   | 0.3369        | 0.1068          | 0.9983                               | 0.9983                              | 0.9983                              | 0.9979                              | -                                  | -                                 | -                                 | -                                 |
+| 0.5660 | 60   | 0.3243        | 0.1006          | 0.9986                               | 0.9986                              | 0.9984                              | 0.9981                              | -                                  | -                                 | -                                 | -                                 |
+| 0.6792 | 72   | 0.3895        | 0.0945          | 0.9987                               | 0.9986                              | 0.9984                              | 0.9984                              | -                                  | -                                 | -                                 | -                                 |
+| 0.7925 | 84   | 0.4668        | 0.0908          | 0.9987                               | 0.9987                              | 0.9985                              | 0.9982                              | -                                  | -                                 | -                                 | -                                 |
+| 0.9057 | 96   | 0.4319        | 0.0863          | 0.9988                               | 0.9987                              | 0.9987                              | 0.9984                              | -                                  | -                                 | -                                 | -                                 |
+| -1     | -1   | -             | -               | -                                    | -                                   | -                                   | -                                   | 0.9987                             | 0.9987                            | 0.9987                            | 0.9983                            |
+
+
+### Framework Versions
+- Python: 3.10.12
+- Sentence Transformers: 4.2.0.dev0
+- Transformers: 4.52.3
+- PyTorch: 2.7.0+cu126
+- Accelerate: 1.7.0
+- Datasets: 3.6.0
+- Tokenizers: 0.21.1
+
+## 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",
+}
+```
+
+#### MatryoshkaLoss
+```bibtex
+@misc{kusupati2024matryoshka,
+    title={Matryoshka Representation Learning},
+    author={Aditya Kusupati and Gantavya Bhatt and Aniket Rege and Matthew Wallingford and Aditya Sinha and Vivek Ramanujan and William Howard-Snyder and Kaifeng Chen and Sham Kakade and Prateek Jain and Ali Farhadi},
+    year={2024},
+    eprint={2205.13147},
+    archivePrefix={arXiv},
+    primaryClass={cs.LG}
+}
+```
+
+#### CachedMultipleNegativesRankingLoss
+```bibtex
+@misc{gao2021scaling,
+    title={Scaling Deep Contrastive Learning Batch Size under Memory Limited Setup},
+    author={Luyu Gao and Yunyi Zhang and Jiawei Han and Jamie Callan},
+    year={2021},
+    eprint={2101.06983},
+    archivePrefix={arXiv},
+    primaryClass={cs.LG}
+}
+```
+
+<!--
+## Glossary
+
+*Clearly define terms in order to be accessible across audiences.*
+-->
+
+<!--
+## Model Card Authors
+
+*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
+-->
+
+<!--
+## Model Card Contact
+
+*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
+-->

added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

chat_template.jinja

@@ -0,0 +1,85 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set content = message.content %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in message.content %}
+                {%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
+                {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

config.json

@@ -0,0 +1,30 @@
+{
+  "architectures": [
+    "Qwen3Model"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen3",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.52.3",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151669
+}

config_sentence_transformers.json

@@ -0,0 +1,13 @@
+{
+  "prompts": {
+    "query": "Instruct: Given a web search query, retrieve relevant passages that answer the query\nQuery:",
+    "document": ""
+  },
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine",
+  "__version__": {
+    "sentence_transformers": "4.2.0.dev0",
+    "transformers": "4.52.3",
+    "pytorch": "2.7.0+cu126"
+  }
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe683b4c4ea8dbc0e020871f996d11ca60386b1ddb25f1d6c327b025e8a1a02d
+size 2383139480

modules.json

@@ -0,0 +1,20 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  },
+  {
+    "idx": 2,
+    "name": "2",
+    "path": "2_Normalize",
+    "type": "sentence_transformers.models.Normalize"
+  }
+]

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+    "max_seq_length": 32768,
+    "do_lower_case": false
+}

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_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|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f45684bb3bd50e1eb753e6bc438efc14329c293af236ecd331667b46657a3cc
+size 11423973

tokenizer_config.json

@@ -0,0 +1,239 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_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|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}