Upload folder using huggingface_hub

.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": true,
+    "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": false,
+    "include_prompt": true
+}

2_Dense/config.json

@@ -0,0 +1,6 @@
+{
+    "in_features": 768,
+    "out_features": 768,
+    "bias": true,
+    "activation_function": "torch.nn.modules.activation.Tanh"
+}

2_Dense/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cbca3add16f6ce5eb01f49f13c20c8067073ba0b489f8f113f7f3e2654c141fa
+size 2362528

README.md

@@ -0,0 +1,617 @@
+---
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- dense
+- generated_from_trainer
+- dataset_size:317
+- loss:MultipleNegativesRankingLoss
+base_model: sentence-transformers/LaBSE
+widget:
+- source_sentence: rab 'byor 'di ji snyam du sems| de bzhin gshegs pas de bzhin gshegs
+    pa mar me mdzad las gang bla na med pa yang dag par rdzogs pa'i byang chub mngon
+    par rdzogs par sangs rgyas pa'i chos de gang  yang yod dam|
+  sentences:
+  - youn-du čü orošil  ügei sedkil öüsken üyiledkü.
+  - tere  youni tula kemēbēsü. subudi tögünčilen boluqsan  zöb nomlon sayitur nomlon
+    tögünčilen činartu  nomloxu bui. tögünčilen  boluqsan buruu nomloxu busuyin tula-da.
+  - subudi öün-dü you sedkikü. tögünčilen boluqsan dhi  paṃ ҟa ra-ēce tögünčilen  boluqsani
+    ali dēre ügei  sayitur dousuqsan bodhidu. ilerkei dousun burxan  boluqsan ali
+    tere nom bui  kemēn sedkikü buyu. teyin  kemēn zarliq boluqsan-du.  burxan-du
+    nasu tögüs subudi  eyin kemēn ayiladxabai. ilaγun tögüsüqsen tögünčilen boluqsan
+    dhi-paṃ-ҟara burxan-ēce tögünčilen  boluqsani ali dēre ügei sayitur  dousuqsan
+    bodhi-du ilerkei dousun burxan boluqsan nom tere oγōto ügei. eyin kemēn ayiladxaqsan-du.  burxan
+    nasu tögüs subudidu eyin kemēn zarliq bolboi. subudi tere tögünčilen tere  tögünčilen
+    küq tögünčilen  boluqsan dhi-paṃ-ҟa-raēce tögünčilen boluqsani  ali dēre ügei
+    sayitur  dousuqsan bodhi-du ilerkei dousun burxan boluqsan nom tere oγōto ügei  subudi
+    kerbe tögünčilen boluqsan ali ilerkei dousun burxan  boluqsan nom zarim bui bolxulā.
+    tögünčilen boluqsan  dhi paṃ ҟa ra. nada biraman  küböün či irē ödüi caqtu. tögünčilen
+    boluqsan  dayini darun sayitur dousuqsan šakyamuni burxan kemēkü bolxu kemēn esi
+    ülü  üzüülkü atala. subudi  ene metü tögünčilen boluqsan ali dēre ügei sayitur  dousuqsan
+    bodhi-du ilerkei  dousun burxan boluqsan  nom tere oγōto ügei töüni tula tögünčilen
+    boluqsan  dhi-paṃ-ҟa-ra. nada biraman küböün či irē ödüi  caqtu. tögünčilen boluqsan  dayini
+    darun sayitur dousuqsan šakyamuni burxan kemēkü bolxu kemēn eši üzüülbei. tere
+    youni tula kemēbēsü. subudi tögünčilen  boluqsan kemēkü inu. ünen  tögünčilen
+    činariyin üge  xadaqsan müni tulada. subudi ali zarim eyin kemēn.  tögünčilen
+    boluqsan dayini  darun sayitur dousuqsan  burxan. dēre ügei sayitur  dousuqsan
+    bodhi-du ilerkei dousun burxan bolboi kemēn  öguulekülē tere buruu ögüülekü mün.
+- source_sentence: 'de ci''i phyir zhe na| rab ''byor gal te byang chub sems dpa''
+    sems dpa'' chen po de dag chos su ''du shes ''jug na de nyid de dag gi bdag tu
+    ''dzin par ''gyur zhing| sems can du ''dzin pa dang| srog tu ''dzin pa dang| gang
+    zag tu ''dzin par ''gyur ba''i phyir ro. '
+  sentences:
+  - 'tere youni  tula kemēbēsü. subudi  kerbe bodhi-sadv mahā-sadv  tede nom kemēn
+    xurān  meden üyiledkülē tede  töüni bidu barixu bolun.  amitan-du barin amin-du  barin
+    budγali-du barixu bolxuyin tulada. '
+  - tere  youni tula kemēbēsü. subudi  oroni zoҟōl-noγoud  oroni zoҟōl-noγoud  kemēkü.
+    zoҟōl tede ügei  kemēn tögünčilen boluqsan  nomloqsoni tulada. töüni  tula oroni
+    zoҟōl-noγoud  kemēyü.
+  - ilaγün tögüsüqsen Ānanda-du  zarliq bolboi
+- source_sentence: bcom ldan 'das kyis bka' stsal pa| yang rab 'byor skyes pa'am|
+    bud med gang gis lus gang gā'i klung gi bye ma snyed yongs su gtong ba bas gang
+    gis chos kyi rnam grangs 'di las tha na tshig bzhi pa'i tshigs su bcad pa tsam
+    bzung ste| gzhan dag  la yang bstan na de gzhi de las bsod nams ches mang du grangs
+    med dpag tu med pa bskyed do.
+  sentences:
+  - 'teyin  kemēn ayiladxaqsan-du burxan  nasu tögüs subudi-du eyin  kemēn zarliq
+    bolbui. '
+  - 'tere youni tula  kemēbēsü. subudi alii amitan-du xurān medekülē.  töüni bodhi-sadv
+    kemēn ülü  ögüüleküyin tulada. '
+  - burxan zarliq  bolboi. subudi ere buyu  eme zarim γangγa müreni  xumakiyin tödüi
+    beye  oγōto ögüqsen-ēce.  ken nomiyin züyil öünēce yadaba čü dörbön  ügetü šülügiyin
+    tödüi  toqtōǰi. busudtu zöb  üzüükülē tere oron  töün-ēce tōloši ügei  caqlaši
+    ügei buyan maši  ülemǰi öüskekü..
+- source_sentence: da yang sangs rgyas spyan drangs nas chos thos ma thag tub yang
+    chung thob par gyur to
+  sentences:
+  - tere youni tula kemēbēsü. subudi sedkiliyin ürgülǰi sedkiliyin ürgülǰi kemēküi.
+    töüni  ürgülǰi ügegüye tögünčilen  boluqsan nomloqsoni tulada.  töüni tula sedkiliyin
+    ürgülǰi kemēn ögüüleyü.
+  - 'subudi tögünčilen baroun kigēd šinggeküi zöün kigēd dēdü  dorodu züq zügiyin  zabsar-luγā
+    arban zügiyin oqtorγuyin kemǰē  caqla kemǰikü kilbar kemēkü  buyu. '
+  - 'ödügē basa burxani zalād nom sonosōd  saca bodhi-yi olun üyiledbei '
+- source_sentence: 'de ci''i phyir zhe na| rab ''byor gal te byang chub sems dpa''
+    sems can du ''du shes ''jug na| de byang chub sems dpa'' zhes mi bya ba''i phyir
+    ro. '
+  sentences:
+  - tere youni  tula kemēbēsü. subudi dēdü  činadu kürüqsen öüni  tögünčilen boluqsan
+    zarluq  bolboi.
+  - ' tere youni tula kemēbēsü.  subudi kerbe bodhi-sadvnar amitan-du xurān medekülē.
+    töüni bodhi-sadv  kemēn ülü ögüüleküyin  tulada. '
+  - subudi basa nomiyin züyil  ene sedkiši ügei adalidxaši ügei. öüni bolbosuraqsan
+    üre-yi čü sedkiši ügegüye uxan üyiled.  nomiyin züyil öüni dēdü  külgün-dü sayitur
+    oroqson  amitan-noγoudiyin tusa  kigēd ketürkei boluqsan  külgün-du sayaitur oroqson
+    amitan-noγoudiyin  tusayin tula tögünčilen  boluqsan nomloboi.
+pipeline_tag: sentence-similarity
+library_name: sentence-transformers
+---
+
+# SentenceTransformer based on sentence-transformers/LaBSE
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [sentence-transformers/LaBSE](https://huggingface.co/sentence-transformers/LaBSE). 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/LaBSE](https://huggingface.co/sentence-transformers/LaBSE) <!-- at revision 836121a0533e5664b21c7aacc5d22951f2b8b25b -->
+- **Maximum Sequence Length:** 256 tokens
+- **Output Dimensionality:** 768 dimensions
+- **Similarity Function:** Cosine Similarity
+<!-- - **Training Dataset:** Unknown -->
+<!-- - **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': 256, 'do_lower_case': False, 'architecture': 'BertModel'})
+  (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': True, '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': False, 'include_prompt': True})
+  (2): Dense({'in_features': 768, 'out_features': 768, 'bias': True, 'activation_function': 'torch.nn.modules.activation.Tanh'})
+  (3): 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("sentence_transformers_model_id")
+# Run inference
+sentences = [
+    "de ci'i phyir zhe na| rab 'byor gal te byang chub sems dpa' sems can du 'du shes 'jug na| de byang chub sems dpa' zhes mi bya ba'i phyir ro. ",
+    ' tere youni tula kemēbēsü.  subudi kerbe bodhi-sadvnar amitan-du xurān medekülē. töüni bodhi-sadv  kemēn ülü ögüüleküyin  tulada. ',
+    'tere youni  tula kemēbēsü. subudi dēdü  činadu kürüqsen öüni  tögünčilen boluqsan zarluq  bolboi.',
+]
+embeddings = model.encode(sentences)
+print(embeddings.shape)
+# [3, 768]
+
+# Get the similarity scores for the embeddings
+similarities = model.similarity(embeddings, embeddings)
+print(similarities)
+# tensor([[1.0000, 0.7387, 0.5014],
+#         [0.7387, 1.0000, 0.6236],
+#         [0.5014, 0.6236, 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.*
+-->
+
+<!--
+## 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
+
+#### Unnamed Dataset
+
+* Size: 317 training samples
+* Columns: <code>sentence_0</code>, <code>sentence_1</code>, and <code>label</code>
+* Approximate statistics based on the first 317 samples:
+  |         | sentence_0                                                                          | sentence_1                                                                         | label                                                         |
+  |:--------|:------------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|:--------------------------------------------------------------|
+  | type    | string                                                                              | string                                                                             | float                                                         |
+  | details | <ul><li>min: 11 tokens</li><li>mean: 62.13 tokens</li><li>max: 256 tokens</li></ul> | <ul><li>min: 9 tokens</li><li>mean: 57.18 tokens</li><li>max: 256 tokens</li></ul> | <ul><li>min: 1.0</li><li>mean: 1.0</li><li>max: 1.0</li></ul> |
+* Samples:
+  | sentence_0                                                                                                                                                                                                                                                                                                        | sentence_1                                                                                                                                                                                                                                                                          | label            |
+  |:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-----------------|
+  | <code>de ci'i phyir zhe na\| rab 'byor de bzhin gshegs pas gang bkrol ba'i sems can de dag gang yang med pa'i phyir ro.</code>                                                                                                                                                                                    | <code>tere  youni tula kemēbēsü. subudi tögünčilen boluqsani ali  tonilγoxui amitan tede  aliba ügeyin tulada. subudi kerbe tögünčilen boluqsan  ali zarim amitani tonilγoxulā. tögünčilen boluqsan  bidü barixu boluyu. amitandu barin amin-du barin budγali barixu boluyu.</code> | <code>1.0</code> |
+  | <code>yang rab 'byor ma 'ongs pa'i dus lnga brgya tha ma la dam pa'i chos rab tu rnam par 'jig par 'gyur ba na byang chub sems dpa' sems dpa' chen po tshul khrims dang ldan pa\| yon tan dang ldan pa\| shes rab dang ldan pa dag 'byung ste\| </code>                                                           | <code>subudi  irē ödüi ecüs tabun  zouni caqtu dēdü nom  maši ebderekui-dü. šaqšabādtai erdemtei biliq  tögüsüqsen bodhi-sadv  mahā-sadv-nar törökü. </code>                                                                                                                        | <code>1.0</code> |
+  | <code>bcom ldan 'das kyis bka' stsal pa\| rab 'byor khyod 'di skad du ma 'ongs pa'i dus lnga brgya tha ma la dam pa'i chos rab tu rnam par 'jig par 'gyur ba na sems can gang la la dag 'di lta bu'i mdo sde'i tshig bshad pa 'di la yang dag par 'du shes skyed par 'gyur ba mchis sam zhes ma zer cig\| </code> | <code>burxan  zarliq bolboi. subudi či  eyin kemēn irē ödüi  ēcüs tabun zöüni caqtu  dēdü nom maši ebdereküi-dü. ali zarim amitan  ene metü suduriyin ayimagiyin üge nomloxuyidu  ünēr xurān medeküi öüsken üyiledkü bui buyu kemēn  tere metü bu ögüüle. </code>                   | <code>1.0</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`: 6
+- `per_device_eval_batch_size`: 6
+- `num_train_epochs`: 25
+- `fp16`: True
+- `multi_dataset_batch_sampler`: round_robin
+
+#### 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`: 6
+- `per_device_eval_batch_size`: 6
+- `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
+- `num_train_epochs`: 25
+- `max_steps`: -1
+- `lr_scheduler_type`: linear
+- `lr_scheduler_kwargs`: {}
+- `warmup_ratio`: 0.0
+- `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`: 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}
+- `parallelism_config`: None
+- `deepspeed`: None
+- `label_smoothing_factor`: 0.0
+- `optim`: adamw_torch_fused
+- `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
+- `hub_revision`: None
+- `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
+- `liger_kernel_config`: None
+- `eval_use_gather_object`: False
+- `average_tokens_across_devices`: False
+- `prompts`: None
+- `batch_sampler`: batch_sampler
+- `multi_dataset_batch_sampler`: round_robin
+- `router_mapping`: {}
+- `learning_rate_mapping`: {}
+
+</details>
+
+### Training Logs
+<details><summary>Click to expand</summary>
+
+| Epoch   | Step | Training Loss |
+|:-------:|:----:|:-------------:|
+| 0.0566  | 3    | -             |
+| 0.1132  | 6    | -             |
+| 0.1698  | 9    | -             |
+| 0.2264  | 12   | -             |
+| 0.2830  | 15   | -             |
+| 0.3396  | 18   | -             |
+| 0.3962  | 21   | -             |
+| 0.4528  | 24   | -             |
+| 0.5094  | 27   | -             |
+| 0.5660  | 30   | -             |
+| 0.6226  | 33   | -             |
+| 0.6792  | 36   | -             |
+| 0.7358  | 39   | -             |
+| 0.7925  | 42   | -             |
+| 0.8491  | 45   | -             |
+| 0.9057  | 48   | -             |
+| 0.9623  | 51   | -             |
+| 1.0     | 53   | -             |
+| 1.0189  | 54   | -             |
+| 1.0755  | 57   | -             |
+| 1.1321  | 60   | -             |
+| 1.1887  | 63   | -             |
+| 1.2453  | 66   | -             |
+| 1.3019  | 69   | -             |
+| 1.3585  | 72   | -             |
+| 1.4151  | 75   | -             |
+| 1.4717  | 78   | -             |
+| 1.5283  | 81   | -             |
+| 1.5849  | 84   | -             |
+| 1.6415  | 87   | -             |
+| 1.6981  | 90   | -             |
+| 1.7547  | 93   | -             |
+| 1.8113  | 96   | -             |
+| 1.8679  | 99   | -             |
+| 1.9245  | 102  | -             |
+| 1.9811  | 105  | -             |
+| 2.0     | 106  | -             |
+| 2.0377  | 108  | -             |
+| 2.0943  | 111  | -             |
+| 2.1509  | 114  | -             |
+| 2.2075  | 117  | -             |
+| 2.2642  | 120  | -             |
+| 2.3208  | 123  | -             |
+| 2.3774  | 126  | -             |
+| 2.4340  | 129  | -             |
+| 2.4906  | 132  | -             |
+| 2.5472  | 135  | -             |
+| 2.6038  | 138  | -             |
+| 2.6604  | 141  | -             |
+| 2.7170  | 144  | -             |
+| 2.7736  | 147  | -             |
+| 2.8302  | 150  | -             |
+| 2.8868  | 153  | -             |
+| 2.9434  | 156  | -             |
+| 3.0     | 159  | -             |
+| 3.0566  | 162  | -             |
+| 3.1132  | 165  | -             |
+| 3.1698  | 168  | -             |
+| 3.2264  | 171  | -             |
+| 3.2830  | 174  | -             |
+| 3.3396  | 177  | -             |
+| 3.3962  | 180  | -             |
+| 3.4528  | 183  | -             |
+| 3.5094  | 186  | -             |
+| 3.5660  | 189  | -             |
+| 3.6226  | 192  | -             |
+| 3.6792  | 195  | -             |
+| 3.7358  | 198  | -             |
+| 3.7925  | 201  | -             |
+| 3.8491  | 204  | -             |
+| 3.9057  | 207  | -             |
+| 3.9623  | 210  | -             |
+| 4.0     | 212  | -             |
+| 4.0189  | 213  | -             |
+| 4.0755  | 216  | -             |
+| 4.1321  | 219  | -             |
+| 4.1887  | 222  | -             |
+| 4.2453  | 225  | -             |
+| 4.3019  | 228  | -             |
+| 4.3585  | 231  | -             |
+| 4.4151  | 234  | -             |
+| 4.4717  | 237  | -             |
+| 4.5283  | 240  | -             |
+| 4.5849  | 243  | -             |
+| 4.6415  | 246  | -             |
+| 4.6981  | 249  | -             |
+| 4.7547  | 252  | -             |
+| 4.8113  | 255  | -             |
+| 4.8679  | 258  | -             |
+| 4.9245  | 261  | -             |
+| 4.9811  | 264  | -             |
+| 5.0     | 265  | -             |
+| 5.0377  | 267  | -             |
+| 5.0943  | 270  | -             |
+| 5.1509  | 273  | -             |
+| 5.2075  | 276  | -             |
+| 5.2642  | 279  | -             |
+| 5.3208  | 282  | -             |
+| 5.3774  | 285  | -             |
+| 5.4340  | 288  | -             |
+| 5.4906  | 291  | -             |
+| 5.5472  | 294  | -             |
+| 5.6038  | 297  | -             |
+| 5.6604  | 300  | -             |
+| 5.7170  | 303  | -             |
+| 5.7736  | 306  | -             |
+| 5.8302  | 309  | -             |
+| 5.8868  | 312  | -             |
+| 5.9434  | 315  | -             |
+| 6.0     | 318  | -             |
+| 6.0566  | 321  | -             |
+| 6.1132  | 324  | -             |
+| 6.1698  | 327  | -             |
+| 6.2264  | 330  | -             |
+| 6.2830  | 333  | -             |
+| 6.3396  | 336  | -             |
+| 6.3962  | 339  | -             |
+| 6.4528  | 342  | -             |
+| 6.5094  | 345  | -             |
+| 6.5660  | 348  | -             |
+| 6.6226  | 351  | -             |
+| 6.6792  | 354  | -             |
+| 6.7358  | 357  | -             |
+| 6.7925  | 360  | -             |
+| 6.8491  | 363  | -             |
+| 6.9057  | 366  | -             |
+| 6.9623  | 369  | -             |
+| 7.0     | 371  | -             |
+| 7.0189  | 372  | -             |
+| 7.0755  | 375  | -             |
+| 7.1321  | 378  | -             |
+| 7.1887  | 381  | -             |
+| 7.2453  | 384  | -             |
+| 7.3019  | 387  | -             |
+| 7.3585  | 390  | -             |
+| 7.4151  | 393  | -             |
+| 7.4717  | 396  | -             |
+| 7.5283  | 399  | -             |
+| 7.5849  | 402  | -             |
+| 7.6415  | 405  | -             |
+| 7.6981  | 408  | -             |
+| 7.7547  | 411  | -             |
+| 7.8113  | 414  | -             |
+| 7.8679  | 417  | -             |
+| 7.9245  | 420  | -             |
+| 7.9811  | 423  | -             |
+| 8.0     | 424  | -             |
+| 8.0377  | 426  | -             |
+| 8.0943  | 429  | -             |
+| 8.1509  | 432  | -             |
+| 8.2075  | 435  | -             |
+| 8.2642  | 438  | -             |
+| 8.3208  | 441  | -             |
+| 8.3774  | 444  | -             |
+| 8.4340  | 447  | -             |
+| 8.4906  | 450  | -             |
+| 8.5472  | 453  | -             |
+| 8.6038  | 456  | -             |
+| 8.6604  | 459  | -             |
+| 8.7170  | 462  | -             |
+| 8.7736  | 465  | -             |
+| 8.8302  | 468  | -             |
+| 8.8868  | 471  | -             |
+| 8.9434  | 474  | -             |
+| 9.0     | 477  | -             |
+| 9.0566  | 480  | -             |
+| 9.1132  | 483  | -             |
+| 9.1698  | 486  | -             |
+| 9.2264  | 489  | -             |
+| 9.2830  | 492  | -             |
+| 9.3396  | 495  | -             |
+| 9.3962  | 498  | -             |
+| 9.4340  | 500  | 0.6328        |
+| 9.4528  | 501  | -             |
+| 9.5094  | 504  | -             |
+| 9.5660  | 507  | -             |
+| 9.6226  | 510  | -             |
+| 9.6792  | 513  | -             |
+| 9.7358  | 516  | -             |
+| 9.7925  | 519  | -             |
+| 9.8491  | 522  | -             |
+| 9.9057  | 525  | -             |
+| 9.9623  | 528  | -             |
+| 10.0    | 530  | -             |
+| 10.0189 | 531  | -             |
+| 10.0755 | 534  | -             |
+| 10.1321 | 537  | -             |
+| 10.1887 | 540  | -             |
+| 10.2453 | 543  | -             |
+| 10.3019 | 546  | -             |
+| 10.3585 | 549  | -             |
+| 10.4151 | 552  | -             |
+| 10.4717 | 555  | -             |
+| 10.5283 | 558  | -             |
+| 10.5849 | 561  | -             |
+| 10.6415 | 564  | -             |
+| 10.6981 | 567  | -             |
+| 10.7547 | 570  | -             |
+| 10.8113 | 573  | -             |
+| 10.8679 | 576  | -             |
+
+</details>
+
+### Framework Versions
+- Python: 3.12.11
+- Sentence Transformers: 5.1.0
+- Transformers: 4.56.0
+- PyTorch: 2.8.0+cu126
+- Accelerate: 1.10.1
+- Datasets: 4.0.0
+- Tokenizers: 0.22.0
+
+## 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",
+}
+```
+
+#### 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 +1,31 @@
+{
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "dtype": "float32",
+  "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-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.56.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 501153
+}

config_sentence_transformers.json

@@ -0,0 +1,14 @@
+{
+  "__version__": {
+    "sentence_transformers": "5.1.0",
+    "transformers": "4.56.0",
+    "pytorch": "2.8.0+cu126"
+  },
+  "model_type": "SentenceTransformer",
+  "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:e6e2951a46ba231936b0b5b4a751869612128ba4461faf827a75a0992d2f952d
+size 1883730160

modules.json

@@ -0,0 +1,26 @@
+[
+  {
+    "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_Dense",
+    "type": "sentence_transformers.models.Dense"
+  },
+  {
+    "idx": 3,
+    "name": "3",
+    "path": "3_Normalize",
+    "type": "sentence_transformers.models.Normalize"
+  }
+]

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+    "max_seq_length": 256,
+    "do_lower_case": false
+}

special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "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 sha256:92262b29204f8fdc169a63f9005a0e311a16262cef4d96ecfe2a7ed638662ed3
+size 13632172

tokenizer_config.json

@@ -0,0 +1,59 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "extra_special_tokens": {},
+  "full_tokenizer_file": null,
+  "mask_token": "[MASK]",
+  "model_max_length": 256,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}