Upload ModernBERT model

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
+}

README.md

@@ -0,0 +1,650 @@
+---
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- dataset_size:7059200
+- loss:MultipleNegativesRankingLoss
+base_model: Shuu12121/CodeModernBERT-Owl-3.0
+widget:
+- source_sentence: 'The maximum value of the slider. (default 0) <P>
+
+    @return Returns the value of the attribute, or 0, if it hasn''t been set by the
+    JSF file.'
+  sentences:
+  - "@Override\n    public UpdateSmsChannelResult updateSmsChannel(UpdateSmsChannelRequest\
+    \ request) {\n        request = beforeClientExecution(request);\n        return\
+    \ executeUpdateSmsChannel(request);\n    }"
+  - "async function isValidOrigin(origin, sourceOrigin) {\n    // This will fetch\
+    \ the caches from https://cdn.ampproject.org/caches.json the first time it's\n\
+    \    // called. Subsequent calls will receive a cached version.\n    const officialCacheList\
+    \ = await caches.list();\n    // Calculate the cache specific origin\n    const\
+    \ cacheSubdomain = `https://${await createCacheSubdomain(sourceOrigin)}.`;\n \
+    \   // Check all caches listed on ampproject.org\n    for (const cache of officialCacheList)\
+    \ {\n      const cachedOrigin = cacheSubdomain + cache.cacheDomain;\n      if\
+    \ (origin === cachedOrigin) {\n        return true;\n      }\n    }\n    return\
+    \ false;\n  }"
+  - "public java.lang.Object getMin() {\n\t\treturn (java.lang.Object) getStateHelper().eval(PropertyKeys.min,\
+    \ 0);\n\t}"
+- source_sentence: 'The Method from the Date.getMinutes is deprecated. This is a helper-Method.
+
+
+    @param date
+
+    The Date-object to get the minutes.
+
+    @return The minutes from the Date-object.'
+  sentences:
+  - "public static int getMinutes(final Date date)\n\t{\n\t\tfinal Calendar calendar\
+    \ = Calendar.getInstance();\n\t\tcalendar.setTime(date);\n\t\treturn calendar.get(Calendar.MINUTE);\n\
+    \t}"
+  - "func (opts BeeOptions) Bind(name string, dst interface{}) error {\n\tv := opts.Value(name)\n\
+    \tif v == nil {\n\t\treturn errors.New(\"Option with name \" + name + \" not found\"\
+    )\n\t}\n\n\treturn ConvertValue(v, dst)\n}"
+  - "public function createFor(Customer $customer, array $options = [], array $filters\
+    \ = [])\n    {\n        $this->parentId = $customer->id;\n\n        return parent::rest_create($options,\
+    \ $filters);\n    }"
+- source_sentence: "Return a list of all dates from 11/12/2015 to the present.\n\n\
+    \  Args:\n    boo: if true, list contains Numbers (20151230); if false, list contains\
+    \ Strings (\"2015-12-30\")\n  Returns:\n    list of either Numbers or Strings"
+  sentences:
+  - "def all_days(boo):\n  \n  earliest = datetime.strptime(('2015-11-12').replace('-',\
+    \ ' '), '%Y %m %d')\n  latest = datetime.strptime(datetime.today().date().isoformat().replace('-',\
+    \ ' '), '%Y %m %d')\n  num_days = (latest - earliest).days + 1\n  all_days = [latest\
+    \ - timedelta(days=x) for x in range(num_days)]\n  all_days.reverse()\n\n  output\
+    \ = []\n\n  if boo:\n    # Return as Integer, yyyymmdd\n    for d in all_days:\n\
+    \      output.append(int(str(d).replace('-', '')[:8]))\n  else:\n    # Return\
+    \ as String, yyyy-mm-dd\n    for d in all_days:\n      output.append(str(d)[:10])\n\
+    \  return output"
+  - "public void setColSize3(Integer newColSize3) {\n\t\tInteger oldColSize3 = colSize3;\n\
+    \t\tcolSize3 = newColSize3;\n\t\tif (eNotificationRequired())\n\t\t\teNotify(new\
+    \ ENotificationImpl(this, Notification.SET, AfplibPackage.COLOR_SPECIFICATION__COL_SIZE3,\
+    \ oldColSize3, colSize3));\n\t}"
+  - "public function deleteCompanyBusinessUnitStoreAddress(CompanyBusinessUnitStoreAddressTransfer\
+    \ $companyBusinessUnitStoreAddressTransfer): void\n    {\n        $this->getFactory()\n\
+    \            ->createFosCompanyBusinessUnitStoreAddressQuery()\n            ->findOneByIdCompanyBusinessUnitStoreAddress($companyBusinessUnitStoreAddressTransfer->getIdCompanyBusinessUnitStoreAddress())\n\
+    \            ->delete();\n    }"
+- source_sentence: 'Returns array of basket oxarticle objects
+
+
+    @return array'
+  sentences:
+  - "public function visit(NodeVisitorInterface $visitor)\n    {\n        foreach\
+    \ ($this->children as $child)\n        {\n            $child->visit($visitor);\n\
+    \        }\n    }"
+  - "func GetColDefaultValue(ctx sessionctx.Context, col *model.ColumnInfo) (types.Datum,\
+    \ error) {\n\treturn getColDefaultValue(ctx, col, col.GetDefaultValue())\n}"
+  - "public function getBasketArticles()\n    {\n        $aBasketArticles = [];\n\
+    \        /** @var \\oxBasketItem $oBasketItem */\n        foreach ($this->_aBasketContents\
+    \ as $sItemKey => $oBasketItem) {\n            try {\n                $oProduct\
+    \ = $oBasketItem->getArticle(true);\n\n                if (\\OxidEsales\\Eshop\\\
+    Core\\Registry::getConfig()->getConfigParam('bl_perfLoadSelectLists')) {\n   \
+    \                 // marking chosen select list\n                    $aSelList\
+    \ = $oBasketItem->getSelList();\n                    if (is_array($aSelList) &&\
+    \ ($aSelectlist = $oProduct->getSelectLists($sItemKey))) {\n                 \
+    \       reset($aSelList);\n                        foreach ($aSelList as $conkey\
+    \ => $iSel) {\n                            $aSelectlist[$conkey][$iSel]->selected\
+    \ = 1;\n                        }\n                        $oProduct->setSelectlist($aSelectlist);\n\
+    \                    }\n                }\n            } catch (\\OxidEsales\\\
+    Eshop\\Core\\Exception\\NoArticleException $oEx) {\n                \\OxidEsales\\\
+    Eshop\\Core\\Registry::getUtilsView()->addErrorToDisplay($oEx);\n            \
+    \    $this->removeItem($sItemKey);\n                $this->calculateBasket(true);\n\
+    \                continue;\n            } catch (\\OxidEsales\\Eshop\\Core\\Exception\\\
+    ArticleInputException $oEx) {\n                \\OxidEsales\\Eshop\\Core\\Registry::getUtilsView()->addErrorToDisplay($oEx);\n\
+    \                $this->removeItem($sItemKey);\n                $this->calculateBasket(true);\n\
+    \                continue;\n            }\n\n            $aBasketArticles[$sItemKey]\
+    \ = $oProduct;\n        }\n\n        return $aBasketArticles;\n    }"
+- source_sentence: get test root
+  sentences:
+  - "@CheckReturnValue\n    @SchedulerSupport(SchedulerSupport.NONE)\n    public final\
+    \ Maybe<T> doOnDispose(Action onDispose) {\n        return RxJavaPlugins.onAssembly(new\
+    \ MaybePeek<T>(this,\n                Functions.emptyConsumer(), // onSubscribe\n\
+    \                Functions.emptyConsumer(), // onSuccess\n                Functions.emptyConsumer(),\
+    \ // onError\n                Functions.EMPTY_ACTION,    // onComplete\n     \
+    \           Functions.EMPTY_ACTION,    // (onSuccess | onError | onComplete) after\n\
+    \                ObjectHelper.requireNonNull(onDispose, \"onDispose is null\"\
+    )\n        ));\n    }"
+  - "protected Object parseKeyElement(Element keyEle, BeanDefinition bd, String defaultKeyTypeName)\
+    \ {\n    NodeList nl = keyEle.getChildNodes();\n    Element subElement = null;\n\
+    \    for (int i = 0; i < nl.getLength(); i++) {\n      Node node = nl.item(i);\n\
+    \      if (node instanceof Element) {\n        // Child element is what we're\
+    \ looking for.\n        if (subElement != null)\n          error(\"<key> element\
+    \ must not contain more than one value sub-element\", keyEle);\n        else subElement\
+    \ = (Element) node;\n      }\n    }\n    return parsePropertySubElement(subElement,\
+    \ bd, defaultKeyTypeName);\n  }"
+  - "function getRootPath(){\n    var rootPath = path.resolve('.');\n    while(rootPath){\n\
+    \        if(fs.existsSync(rootPath + '/config.json')){\n            break;\n \
+    \       }\n        rootPath = rootPath.substring(0, rootPath.lastIndexOf(path.sep));\n\
+    \    }\n    return rootPath;\n}"
+pipeline_tag: sentence-similarity
+library_name: sentence-transformers
+---
+
+# SentenceTransformer based on Shuu12121/CodeModernBERT-Owl-3.0
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [Shuu12121/CodeModernBERT-Owl-3.0](https://huggingface.co/Shuu12121/CodeModernBERT-Owl-3.0). 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:** [Shuu12121/CodeModernBERT-Owl-3.0](https://huggingface.co/Shuu12121/CodeModernBERT-Owl-3.0) <!-- at revision a6beebbd776ae122f34f875dfa731557a1f70d8f -->
+- **Maximum Sequence Length:** 1024 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': 1024, 'do_lower_case': False}) with Transformer model: ModernBertModel 
+  (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})
+)
+```
+
+## 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 = [
+    'get test root',
+    "function getRootPath(){\n    var rootPath = path.resolve('.');\n    while(rootPath){\n        if(fs.existsSync(rootPath + '/config.json')){\n            break;\n        }\n        rootPath = rootPath.substring(0, rootPath.lastIndexOf(path.sep));\n    }\n    return rootPath;\n}",
+    'protected Object parseKeyElement(Element keyEle, BeanDefinition bd, String defaultKeyTypeName) {\n    NodeList nl = keyEle.getChildNodes();\n    Element subElement = null;\n    for (int i = 0; i < nl.getLength(); i++) {\n      Node node = nl.item(i);\n      if (node instanceof Element) {\n        // Child element is what we\'re looking for.\n        if (subElement != null)\n          error("<key> element must not contain more than one value sub-element", keyEle);\n        else subElement = (Element) node;\n      }\n    }\n    return parsePropertySubElement(subElement, bd, defaultKeyTypeName);\n  }',
+]
+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.*
+-->
+
+<!--
+## 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: 7,059,200 training samples
+* Columns: <code>sentence_0</code>, <code>sentence_1</code>, and <code>label</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | sentence_0                                                                         | sentence_1                                                                            | label                                                         |
+  |:--------|:-----------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------|:--------------------------------------------------------------|
+  | type    | string                                                                             | string                                                                                | float                                                         |
+  | details | <ul><li>min: 3 tokens</li><li>mean: 51.42 tokens</li><li>max: 974 tokens</li></ul> | <ul><li>min: 29 tokens</li><li>mean: 162.71 tokens</li><li>max: 1024 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>// SetDefaultVersionId sets the DefaultVersionId field's value.</code>           | <code>func (s *Policy) SetDefaultVersionId(v string) *Policy {<br>	s.DefaultVersionId = &v<br>	return s<br>}</code>                                       | <code>1.0</code> |
+  | <code>// SetNextPageToken sets the NextPageToken field's value.</code>                 | <code>func (s *ListBudgetsForResourceOutput) SetNextPageToken(v string) *ListBudgetsForResourceOutput {<br>	s.NextPageToken = &v<br>	return s<br>}</code> | <code>1.0</code> |
+  | <code>// SetHealthyThresholdCount sets the HealthyThresholdCount field's value.</code> | <code>func (s *TargetGroup) SetHealthyThresholdCount(v int64) *TargetGroup {<br>	s.HealthyThresholdCount = &v<br>	return s<br>}</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"
+  }
+  ```
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `per_device_train_batch_size`: 200
+- `per_device_eval_batch_size`: 200
+- `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`: no
+- `prediction_loss_only`: True
+- `per_device_train_batch_size`: 200
+- `per_device_eval_batch_size`: 200
+- `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`: 3
+- `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}
+- `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`: batch_sampler
+- `multi_dataset_batch_sampler`: round_robin
+
+</details>
+
+### Training Logs
+<details><summary>Click to expand</summary>
+
+| Epoch  | Step   | Training Loss |
+|:------:|:------:|:-------------:|
+| 0.0142 | 500    | 1.1661        |
+| 0.0283 | 1000   | 0.1176        |
+| 0.0425 | 1500   | 0.1096        |
+| 0.0567 | 2000   | 0.1013        |
+| 0.0708 | 2500   | 0.0967        |
+| 0.0850 | 3000   | 0.0912        |
+| 0.0992 | 3500   | 0.0886        |
+| 0.1133 | 4000   | 0.0799        |
+| 0.1275 | 4500   | 0.0776        |
+| 0.1417 | 5000   | 0.0757        |
+| 0.1558 | 5500   | 0.0751        |
+| 0.1700 | 6000   | 0.0714        |
+| 0.1842 | 6500   | 0.0703        |
+| 0.1983 | 7000   | 0.0667        |
+| 0.2125 | 7500   | 0.0674        |
+| 0.2267 | 8000   | 0.0625        |
+| 0.2408 | 8500   | 0.0598        |
+| 0.2550 | 9000   | 0.0597        |
+| 0.2692 | 9500   | 0.0585        |
+| 0.2833 | 10000  | 0.0568        |
+| 0.2975 | 10500  | 0.055         |
+| 0.3117 | 11000  | 0.0554        |
+| 0.3258 | 11500  | 0.0529        |
+| 0.3400 | 12000  | 0.0516        |
+| 0.3541 | 12500  | 0.0506        |
+| 0.3683 | 13000  | 0.05          |
+| 0.3825 | 13500  | 0.0484        |
+| 0.3966 | 14000  | 0.0472        |
+| 0.4108 | 14500  | 0.0468        |
+| 0.4250 | 15000  | 0.045         |
+| 0.4391 | 15500  | 0.046         |
+| 0.4533 | 16000  | 0.0452        |
+| 0.4675 | 16500  | 0.0428        |
+| 0.4816 | 17000  | 0.0424        |
+| 0.4958 | 17500  | 0.04          |
+| 0.5100 | 18000  | 0.0402        |
+| 0.5241 | 18500  | 0.0391        |
+| 0.5383 | 19000  | 0.0389        |
+| 0.5525 | 19500  | 0.0385        |
+| 0.5666 | 20000  | 0.0357        |
+| 0.5808 | 20500  | 0.0362        |
+| 0.5950 | 21000  | 0.0369        |
+| 0.6091 | 21500  | 0.0372        |
+| 0.6233 | 22000  | 0.0351        |
+| 0.6375 | 22500  | 0.034         |
+| 0.6516 | 23000  | 0.0364        |
+| 0.6658 | 23500  | 0.033         |
+| 0.6800 | 24000  | 0.0336        |
+| 0.6941 | 24500  | 0.0302        |
+| 0.7083 | 25000  | 0.0309        |
+| 0.7225 | 25500  | 0.0306        |
+| 0.7366 | 26000  | 0.0316        |
+| 0.7508 | 26500  | 0.0306        |
+| 0.7650 | 27000  | 0.0307        |
+| 0.7791 | 27500  | 0.0303        |
+| 0.7933 | 28000  | 0.028         |
+| 0.8075 | 28500  | 0.0289        |
+| 0.8216 | 29000  | 0.0297        |
+| 0.8358 | 29500  | 0.0281        |
+| 0.8500 | 30000  | 0.029         |
+| 0.8641 | 30500  | 0.027         |
+| 0.8783 | 31000  | 0.0282        |
+| 0.8925 | 31500  | 0.0264        |
+| 0.9066 | 32000  | 0.027         |
+| 0.9208 | 32500  | 0.0259        |
+| 0.9350 | 33000  | 0.0272        |
+| 0.9491 | 33500  | 0.0275        |
+| 0.9633 | 34000  | 0.0244        |
+| 0.9774 | 34500  | 0.0254        |
+| 0.9916 | 35000  | 0.0261        |
+| 1.0058 | 35500  | 0.0189        |
+| 1.0199 | 36000  | 0.0118        |
+| 1.0341 | 36500  | 0.012         |
+| 1.0483 | 37000  | 0.0118        |
+| 1.0624 | 37500  | 0.0109        |
+| 1.0766 | 38000  | 0.0123        |
+| 1.0908 | 38500  | 0.0122        |
+| 1.1049 | 39000  | 0.0122        |
+| 1.1191 | 39500  | 0.0123        |
+| 1.1333 | 40000  | 0.0117        |
+| 1.1474 | 40500  | 0.0115        |
+| 1.1616 | 41000  | 0.0122        |
+| 1.1758 | 41500  | 0.0117        |
+| 1.1899 | 42000  | 0.0119        |
+| 1.2041 | 42500  | 0.0112        |
+| 1.2183 | 43000  | 0.0122        |
+| 1.2324 | 43500  | 0.0116        |
+| 1.2466 | 44000  | 0.0107        |
+| 1.2608 | 44500  | 0.0126        |
+| 1.2749 | 45000  | 0.0114        |
+| 1.2891 | 45500  | 0.011         |
+| 1.3033 | 46000  | 0.0116        |
+| 1.3174 | 46500  | 0.0114        |
+| 1.3316 | 47000  | 0.0111        |
+| 1.3458 | 47500  | 0.0112        |
+| 1.3599 | 48000  | 0.0112        |
+| 1.3741 | 48500  | 0.0115        |
+| 1.3883 | 49000  | 0.0104        |
+| 1.4024 | 49500  | 0.0109        |
+| 1.4166 | 50000  | 0.0113        |
+| 1.4308 | 50500  | 0.0115        |
+| 1.4449 | 51000  | 0.0103        |
+| 1.4591 | 51500  | 0.0114        |
+| 1.4733 | 52000  | 0.0104        |
+| 1.4874 | 52500  | 0.0106        |
+| 1.5016 | 53000  | 0.0103        |
+| 1.5158 | 53500  | 0.0102        |
+| 1.5299 | 54000  | 0.0101        |
+| 1.5441 | 54500  | 0.0104        |
+| 1.5583 | 55000  | 0.011         |
+| 1.5724 | 55500  | 0.0107        |
+| 1.5866 | 56000  | 0.0097        |
+| 1.6007 | 56500  | 0.0099        |
+| 1.6149 | 57000  | 0.0102        |
+| 1.6291 | 57500  | 0.0098        |
+| 1.6432 | 58000  | 0.01          |
+| 1.6574 | 58500  | 0.0096        |
+| 1.6716 | 59000  | 0.0099        |
+| 1.6857 | 59500  | 0.0103        |
+| 1.6999 | 60000  | 0.0098        |
+| 1.7141 | 60500  | 0.0097        |
+| 1.7282 | 61000  | 0.0094        |
+| 1.7424 | 61500  | 0.0093        |
+| 1.7566 | 62000  | 0.0102        |
+| 1.7707 | 62500  | 0.0099        |
+| 1.7849 | 63000  | 0.0098        |
+| 1.7991 | 63500  | 0.009         |
+| 1.8132 | 64000  | 0.0097        |
+| 1.8274 | 64500  | 0.009         |
+| 1.8416 | 65000  | 0.0093        |
+| 1.8557 | 65500  | 0.0092        |
+| 1.8699 | 66000  | 0.0095        |
+| 1.8841 | 66500  | 0.0093        |
+| 1.8982 | 67000  | 0.0094        |
+| 1.9124 | 67500  | 0.0089        |
+| 1.9266 | 68000  | 0.0091        |
+| 1.9407 | 68500  | 0.0089        |
+| 1.9549 | 69000  | 0.0084        |
+| 1.9691 | 69500  | 0.0087        |
+| 1.9832 | 70000  | 0.0094        |
+| 1.9974 | 70500  | 0.0085        |
+| 2.0116 | 71000  | 0.0049        |
+| 2.0257 | 71500  | 0.0041        |
+| 2.0399 | 72000  | 0.0039        |
+| 2.0541 | 72500  | 0.0038        |
+| 2.0682 | 73000  | 0.004         |
+| 2.0824 | 73500  | 0.0039        |
+| 2.0966 | 74000  | 0.0038        |
+| 2.1107 | 74500  | 0.0041        |
+| 2.1249 | 75000  | 0.0037        |
+| 2.1391 | 75500  | 0.0038        |
+| 2.1532 | 76000  | 0.0041        |
+| 2.1674 | 76500  | 0.0036        |
+| 2.1816 | 77000  | 0.0039        |
+| 2.1957 | 77500  | 0.0039        |
+| 2.2099 | 78000  | 0.0038        |
+| 2.2240 | 78500  | 0.0038        |
+| 2.2382 | 79000  | 0.0037        |
+| 2.2524 | 79500  | 0.0037        |
+| 2.2665 | 80000  | 0.0036        |
+| 2.2807 | 80500  | 0.0038        |
+| 2.2949 | 81000  | 0.0037        |
+| 2.3090 | 81500  | 0.0036        |
+| 2.3232 | 82000  | 0.0036        |
+| 2.3374 | 82500  | 0.0038        |
+| 2.3515 | 83000  | 0.0037        |
+| 2.3657 | 83500  | 0.0037        |
+| 2.3799 | 84000  | 0.0038        |
+| 2.3940 | 84500  | 0.0037        |
+| 2.4082 | 85000  | 0.0036        |
+| 2.4224 | 85500  | 0.0034        |
+| 2.4365 | 86000  | 0.0035        |
+| 2.4507 | 86500  | 0.0033        |
+| 2.4649 | 87000  | 0.0036        |
+| 2.4790 | 87500  | 0.0035        |
+| 2.4932 | 88000  | 0.0034        |
+| 2.5074 | 88500  | 0.0034        |
+| 2.5215 | 89000  | 0.0034        |
+| 2.5357 | 89500  | 0.0031        |
+| 2.5499 | 90000  | 0.0033        |
+| 2.5640 | 90500  | 0.0033        |
+| 2.5782 | 91000  | 0.0035        |
+| 2.5924 | 91500  | 0.0033        |
+| 2.6065 | 92000  | 0.0032        |
+| 2.6207 | 92500  | 0.0034        |
+| 2.6349 | 93000  | 0.0031        |
+| 2.6490 | 93500  | 0.0032        |
+| 2.6632 | 94000  | 0.0032        |
+| 2.6774 | 94500  | 0.0033        |
+| 2.6915 | 95000  | 0.0032        |
+| 2.7057 | 95500  | 0.003         |
+| 2.7199 | 96000  | 0.0032        |
+| 2.7340 | 96500  | 0.0032        |
+| 2.7482 | 97000  | 0.003         |
+| 2.7624 | 97500  | 0.0032        |
+| 2.7765 | 98000  | 0.0033        |
+| 2.7907 | 98500  | 0.003         |
+| 2.8049 | 99000  | 0.003         |
+| 2.8190 | 99500  | 0.0031        |
+| 2.8332 | 100000 | 0.0031        |
+| 2.8473 | 100500 | 0.003         |
+| 2.8615 | 101000 | 0.003         |
+| 2.8757 | 101500 | 0.003         |
+| 2.8898 | 102000 | 0.003         |
+| 2.9040 | 102500 | 0.003         |
+| 2.9182 | 103000 | 0.003         |
+| 2.9323 | 103500 | 0.003         |
+| 2.9465 | 104000 | 0.0033        |
+| 2.9607 | 104500 | 0.0029        |
+| 2.9748 | 105000 | 0.003         |
+| 2.9890 | 105500 | 0.0028        |
+
+</details>
+
+### Framework Versions
+- Python: 3.11.13
+- Sentence Transformers: 4.1.0
+- Transformers: 4.52.4
+- PyTorch: 2.6.0+cu124
+- 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",
+}
+```
+
+#### 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.*
+-->

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "</s>": 50001,
+  "<s>": 50000
+}

config.json

@@ -0,0 +1,48 @@
+{
+  "architectures": [
+    "ModernBertModel"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 50000,
+  "classifier_activation": "gelu",
+  "classifier_bias": false,
+  "classifier_dropout": 0.0,
+  "classifier_pooling": "cls",
+  "cls_token_id": 50281,
+  "decoder_bias": true,
+  "deterministic_flash_attn": false,
+  "embedding_dropout": 0.0,
+  "eos_token_id": 50001,
+  "global_attn_every_n_layers": 3,
+  "global_rope_theta": 160000.0,
+  "hidden_activation": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_cutoff_factor": 2.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "local_attention": 128,
+  "local_attention_rope_theta": 10000,
+  "local_attention_window": 128,
+  "local_rope_theta": 10000.0,
+  "max_position_embeddings": 8192,
+  "mlp_bias": false,
+  "mlp_dropout": 0.0,
+  "model_type": "modernbert",
+  "norm_bias": false,
+  "norm_eps": 1e-05,
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "repad_logits_with_grad": false,
+  "rope_theta": 160000,
+  "sep_token_id": 50282,
+  "sparse_pred_ignore_index": -100,
+  "sparse_prediction": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.52.4",
+  "type_vocab_size": 2,
+  "vocab_size": 50005
+}

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "4.1.0",
+    "transformers": "4.52.4",
+    "pytorch": "2.6.0+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:fddee72b9599d5ff528951f5cb0affb9988f2ed784612a01fe2790a2690ef131
+size 606684184

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": 1024,
+  "do_lower_case": false
+}

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "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": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,74 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[MASK]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50000": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50001": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "[CLS]",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "[UNK]"
+}