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 +1,518 @@
+---
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- dataset_size:1736236
+- loss:MultipleNegativesRankingLoss
+base_model: Shuu12121/CodeModernBERT-Owl-1.0
+widget:
+- source_sentence: 'Get all categories for the item
+
+
+    Uses `<atom:category>`, `<category>` or `<dc:subject>`
+
+
+    @since Beta 3
+
+    @return SimplePie_Category[]|null List of {@see SimplePie_Category} objects'
+  sentences:
+  - "protected function user()\n    {\n        if ($this->wrappedObject->security)\
+    \ {\n            return ' this user\\'s ';\n        }\n\n        $user = $this->wrappedObject->revisionable()->withTrashed()->first(['first_name',\
+    \ 'last_name']);\n\n        return ' '.$user->first_name.' '.$user->last_name.'\\\
+    's ';\n    }"
+  - "public function hasArticlesHiddenFromRobots()\n    {\n        $app = App::getInstance();\n\
+    \n        $sql = $app['safesql']->query(\n            \"SELECT\n    COUNT(article_author.article)\n\
+    \    FROM `article_author`\n    INNER JOIN `article`\n    ON article_author.article\
+    \ = article.id\n    WHERE article_author.`author` = '%s'\n    AND article.deleted\
+    \ = 0\n    AND article_author.deleted = 0\n    AND searchable = 0\",\n       \
+    \     array(\n                $this->getUser())\n            );\n        $result\
+    \ = $app['db']->get_var($sql);\n        return ($result > 0 ? true: false);\n\
+    \    }"
+  - "public function get_categories()\n\t{\n\t\t$categories = array();\n\n\t\t$type\
+    \ = 'category';\n\t\tforeach ((array) $this->get_item_tags(SIMPLEPIE_NAMESPACE_ATOM_10,\
+    \ $type) as $category)\n\t\t{\n\t\t\t$term = null;\n\t\t\t$scheme = null;\n\t\t\
+    \t$label = null;\n\t\t\tif (isset($category['attribs']['']['term']))\n\t\t\t{\n\
+    \t\t\t\t$term = $this->sanitize($category['attribs']['']['term'], SIMPLEPIE_CONSTRUCT_HTML);\n\
+    \t\t\t}\n\t\t\tif (isset($category['attribs']['']['scheme']))\n\t\t\t{\n\t\t\t\
+    \t$scheme = $this->sanitize($category['attribs']['']['scheme'], SIMPLEPIE_CONSTRUCT_HTML);\n\
+    \t\t\t}\n\t\t\tif (isset($category['attribs']['']['label']))\n\t\t\t{\n\t\t\t\t\
+    $label = $this->sanitize($category['attribs']['']['label'], SIMPLEPIE_CONSTRUCT_HTML);\n\
+    \t\t\t}\n\t\t\t$categories[] = $this->registry->create('Category', array($term,\
+    \ $scheme, $label, $type));\n\t\t}\n\t\tforeach ((array) $this->get_item_tags(SIMPLEPIE_NAMESPACE_RSS_20,\
+    \ $type) as $category)\n\t\t{\n\t\t\t// This is really the label, but keep this\
+    \ as the term also for BC.\n\t\t\t// Label will also work on retrieving because\
+    \ that falls back to term.\n\t\t\t$term = $this->sanitize($category['data'], SIMPLEPIE_CONSTRUCT_HTML);\n\
+    \t\t\tif (isset($category['attribs']['']['domain']))\n\t\t\t{\n\t\t\t\t$scheme\
+    \ = $this->sanitize($category['attribs']['']['domain'], SIMPLEPIE_CONSTRUCT_HTML);\n\
+    \t\t\t}\n\t\t\telse\n\t\t\t{\n\t\t\t\t$scheme = null;\n\t\t\t}\n\t\t\t$categories[]\
+    \ = $this->registry->create('Category', array($term, $scheme, null, $type));\n\
+    \t\t}\n\n\t\t$type = 'subject';\n\t\tforeach ((array) $this->get_item_tags(SIMPLEPIE_NAMESPACE_DC_11,\
+    \ $type) as $category)\n\t\t{\n\t\t\t$categories[] = $this->registry->create('Category',\
+    \ array($this->sanitize($category['data'], SIMPLEPIE_CONSTRUCT_HTML), null, null,\
+    \ $type));\n\t\t}\n\t\tforeach ((array) $this->get_item_tags(SIMPLEPIE_NAMESPACE_DC_10,\
+    \ $type) as $category)\n\t\t{\n\t\t\t$categories[] = $this->registry->create('Category',\
+    \ array($this->sanitize($category['data'], SIMPLEPIE_CONSTRUCT_HTML), null, null,\
+    \ $type));\n\t\t}\n\n\t\tif (!empty($categories))\n\t\t{\n\t\t\treturn array_unique($categories);\n\
+    \t\t}\n\t\telse\n\t\t{\n\t\t\treturn null;\n\t\t}\n\t}"
+- source_sentence: 'Add a single parse mode to the route middleware
+
+    @param middle
+
+    @param mode
+
+    @param settings'
+  sentences:
+  - "public static int parseUnsignedInt(String s, int radix)\n                throws\
+    \ NumberFormatException {\n        if (s == null)  {\n            throw new NumberFormatException(\"\
+    null\");\n        }\n\n        int len = s.length();\n        if (len > 0) {\n\
+    \            char firstChar = s.charAt(0);\n            if (firstChar == '-')\
+    \ {\n                throw new\n                    NumberFormatException(String.format(\"\
+    Illegal leading minus sign \" +\n                                            \
+    \           \"on unsigned string %s.\", s));\n            } else {\n         \
+    \       if (len <= 5 || // Integer.MAX_VALUE in Character.MAX_RADIX is 6 digits\n\
+    \                    (radix == 10 && len <= 9) ) { // Integer.MAX_VALUE in base\
+    \ 10 is 10 digits\n                    return parseInt(s, radix);\n          \
+    \      } else {\n                    long ell = Long.parseLong(s, radix);\n  \
+    \                  if ((ell & 0xffff_ffff_0000_0000L) == 0) {\n              \
+    \          return (int) ell;\n                    } else {\n                 \
+    \       throw new\n                            NumberFormatException(String.format(\"\
+    String value %s exceeds \" +\n                                               \
+    \                 \"range of unsigned int.\", s));\n                    }\n  \
+    \              }\n            }\n        } else {\n            throw NumberFormatException.forInputString(s);\n\
+    \        }\n    }"
+  - "func (f *Filter) shouldNamePass(key string) bool {\n\tpass := func(f *Filter)\
+    \ bool {\n\t\tif f.namePass.Match(key) {\n\t\t\treturn true\n\t\t}\n\t\treturn\
+    \ false\n\t}\n\n\tdrop := func(f *Filter) bool {\n\t\tif f.nameDrop.Match(key)\
+    \ {\n\t\t\treturn false\n\t\t}\n\t\treturn true\n\t}\n\n\tif f.namePass != nil\
+    \ && f.nameDrop != nil {\n\t\treturn pass(f) && drop(f)\n\t} else if f.namePass\
+    \ != nil {\n\t\treturn pass(f)\n\t} else if f.nameDrop != nil {\n\t\treturn drop(f)\n\
+    \t}\n\n\treturn true\n}"
+  - "function addMode(middle, mode, settings) {\n    if (!modes.includes(mode)) throw\
+    \ `Incorrect bodyparser mode ${mode}`;\n    middle.push(bodyParser[mode](settings[mode]));\n\
+    }"
+- source_sentence: Convert Bigtable's {@link RowRange} -> guava {@link Range}.
+  sentences:
+  - "public function getMemoryUsage()\n    {\n        $size = memory_get_usage(true);\n\
+    \        $unit = array('b','kb','mb','gb','tb','pb');\n                \n    \
+    \    return @round($size/pow(1024,($i=floor(log($size,1024)))),2).' '.$unit[$i];\n\
+    \    }"
+  - "protected function _beforeDispatch(DispatcherContext $context)\n    {\n     \
+    \   // Check if the user has been explicitly authenticated for this request\n\
+    \        if (!$this->getUser()->isAuthentic(true))\n        {\n            foreach($this->__authenticator_queue\
+    \ as $authenticator)\n            {\n                if($authenticator->authenticateRequest($context)\
+    \ === true) {\n                    break;\n                }\n            }\n\
+    \        }\n\n    }"
+  - "private Range<RowKeyWrapper> rowRangeToRange(RowRange btRange) {\n    final BoundType\
+    \ startBound;\n    final ByteString startKey;\n\n    switch (btRange.getStartKeyCase())\
+    \ {\n      case START_KEY_OPEN:\n        startBound = BoundType.OPEN;\n      \
+    \  startKey = btRange.getStartKeyOpen();\n        break;\n      case START_KEY_CLOSED:\n\
+    \        startBound = BoundType.CLOSED;\n        startKey = btRange.getStartKeyClosed();\n\
+    \        break;\n      case STARTKEY_NOT_SET:\n        startBound = BoundType.CLOSED;\n\
+    \        startKey = ByteString.EMPTY;\n        break;\n      default:\n      \
+    \  throw new IllegalArgumentException(\"Unexpected start key case: \" +\n    \
+    \        btRange.getStartKeyCase());\n    }\n\n    final BoundType endBound;\n\
+    \    final ByteString endKey;\n    switch (btRange.getEndKeyCase()) {\n      case\
+    \ END_KEY_OPEN:\n        endBound = BoundType.OPEN;\n        endKey = btRange.getEndKeyOpen();\n\
+    \        break;\n      case END_KEY_CLOSED:\n        endBound = BoundType.CLOSED;\n\
+    \        endKey = btRange.getEndKeyClosed();\n        break;\n      case ENDKEY_NOT_SET:\n\
+    \        endBound = BoundType.OPEN;\n        endKey = ByteString.EMPTY;\n    \
+    \    break;\n      default:\n        throw new IllegalArgumentException(\"Unexpected\
+    \ end key case: \" + btRange.getEndKeyCase());\n    }\n\n    return boundedRange(startBound,\
+    \ startKey, endBound, endKey);\n  }"
+- source_sentence: // SetConfigurationManager sets the ConfigurationManager field's
+    value.
+  sentences:
+  - "func (s *UpdateStackInput) SetConfigurationManager(v *StackConfigurationManager)\
+    \ *UpdateStackInput {\n\ts.ConfigurationManager = v\n\treturn s\n}"
+  - "func getAllTolerationPreferNoSchedule(tolerations []v1.Toleration) (tolerationList\
+    \ []v1.Toleration) {\n\tfor _, toleration := range tolerations {\n\t\t// Empty\
+    \ effect means all effects which includes PreferNoSchedule, so we need to collect\
+    \ it as well.\n\t\tif len(toleration.Effect) == 0 || toleration.Effect == v1.TaintEffectPreferNoSchedule\
+    \ {\n\t\t\ttolerationList = append(tolerationList, toleration)\n\t\t}\n\t}\n\t\
+    return\n}"
+  - "protected function getRelationXmlHashFromDB(array $destinationContentIds)\n \
+    \   {\n        if (empty($destinationContentIds)) {\n            return array();\n\
+    \        }\n\n        $q = $this->db->createSelectQuery();\n        $q\n     \
+    \       ->select(\n                $this->db->aliasedColumn($q, 'id', 'ezcontentobject'),\n\
+    \                $this->db->aliasedColumn($q, 'remote_id', 'ezcontentobject'),\n\
+    \                $this->db->aliasedColumn($q, 'current_version', 'ezcontentobject'),\n\
+    \                $this->db->aliasedColumn($q, 'contentclass_id', 'ezcontentobject'),\n\
+    \                $this->db->aliasedColumn($q, 'node_id', 'ezcontentobject_tree'),\n\
+    \                $this->db->aliasedColumn($q, 'parent_node_id', 'ezcontentobject_tree'),\n\
+    \                $this->db->aliasedColumn($q, 'identifier', 'ezcontentclass')\n\
+    \            )\n            ->from($this->db->quoteTable('ezcontentobject'))\n\
+    \            ->leftJoin(\n                $this->db->quoteTable('ezcontentobject_tree'),\n\
+    \                $q->expr->lAnd(\n                    $q->expr->eq(\n        \
+    \                $this->db->quoteColumn('contentobject_id', 'ezcontentobject_tree'),\n\
+    \                        $this->db->quoteColumn('id', 'ezcontentobject')\n   \
+    \                 ),\n                    $q->expr->eq(\n                    \
+    \    $this->db->quoteColumn('node_id', 'ezcontentobject_tree'),\n            \
+    \            $this->db->quoteColumn('main_node_id', 'ezcontentobject_tree')\n\
+    \                    )\n                )\n            )\n            ->leftJoin(\n\
+    \                $this->db->quoteTable('ezcontentclass'),\n                $q->expr->lAnd(\n\
+    \                    $q->expr->eq(\n                        $this->db->quoteColumn('id',\
+    \ 'ezcontentclass'),\n                        $this->db->quoteColumn('contentclass_id',\
+    \ 'ezcontentobject')\n                    ),\n                    $q->expr->eq(\n\
+    \                        $this->db->quoteColumn('version', 'ezcontentclass'),\n\
+    \                        $q->bindValue(ContentType::STATUS_DEFINED, null, PDO::PARAM_INT)\n\
+    \                    )\n                )\n            )\n            ->where(\n\
+    \                $q->expr->in(\n                    $this->db->quoteColumn('id',\
+    \ 'ezcontentobject'),\n                    $destinationContentIds\n          \
+    \      )\n            );\n        $stmt = $q->prepare();\n        $stmt->execute();\n\
+    \n        return $stmt->fetchAll(PDO::FETCH_ASSOC | PDO::FETCH_GROUP);\n    }"
+- source_sentence: '******************************************************************
+
+    View helpers
+
+    *****************************************************************
+
+
+
+    Find the view for the called method.
+
+
+    @param null|string $view
+
+    @param null|string $layout
+
+
+    @return $this'
+  sentences:
+  - "public function view($view = null, $layout = null)\n    {\n        if (! is_null($layout))\
+    \ {\n            $this->layoutOptions = [\n                'default' => $layout,\n\
+    \                'ajax'    => $layout,\n            ];\n        }\n\n        //\
+    \ Set up the default view resolution\n        viewBuilder()->setUp($this->layoutOptions,\
+    \ $view);\n        $this->setupLayout();\n    }"
+  - "func (c *CognitoIdentityProvider) AdminDeleteUser(input *AdminDeleteUserInput)\
+    \ (*AdminDeleteUserOutput, error) {\n\treq, out := c.AdminDeleteUserRequest(input)\n\
+    \treturn out, req.Send()\n}"
+  - "protected function checkIfPositiveInteger(\n        $fieldName,\n        $canUseFlexforms,\n\
+    \        $sheet,\n        $explanation\n    ) {\n        $value = $this->objectToCheck->getConfValueString($fieldName,\
+    \ $sheet);\n        $this->checkIfPositiveIntegerValue(\n            $value,\n\
+    \            $fieldName,\n            $canUseFlexforms,\n            $explanation\n\
+    \        );\n    }"
+pipeline_tag: sentence-similarity
+library_name: sentence-transformers
+---
+
+# SentenceTransformer based on Shuu12121/CodeModernBERT-Owl-1.0
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [Shuu12121/CodeModernBERT-Owl-1.0](https://huggingface.co/Shuu12121/CodeModernBERT-Owl-1.0). 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-1.0](https://huggingface.co/Shuu12121/CodeModernBERT-Owl-1.0) <!-- at revision e76a6056791a4f60962d3f2ce4cc7d94bd719485 -->
+- **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 = [
+    '******************************************************************\nView helpers\n*****************************************************************\n\n\nFind the view for the called method.\n\n@param null|string $view\n@param null|string $layout\n\n@return $this',
+    "public function view($view = null, $layout = null)\n    {\n        if (! is_null($layout)) {\n            $this->layoutOptions = [\n                'default' => $layout,\n                'ajax'    => $layout,\n            ];\n        }\n\n        // Set up the default view resolution\n        viewBuilder()->setUp($this->layoutOptions, $view);\n        $this->setupLayout();\n    }",
+    'protected function checkIfPositiveInteger(\n        $fieldName,\n        $canUseFlexforms,\n        $sheet,\n        $explanation\n    ) {\n        $value = $this->objectToCheck->getConfValueString($fieldName, $sheet);\n        $this->checkIfPositiveIntegerValue(\n            $value,\n            $fieldName,\n            $canUseFlexforms,\n            $explanation\n        );\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: 1,736,236 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: 48.85 tokens</li><li>max: 1024 tokens</li></ul> | <ul><li>min: 30 tokens</li><li>mean: 171.5 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>// convDataValidationOperatior get excel data validation operator.</code>                                                 | <code>func convDataValidationOperatior(o DataValidationOperator) string {<br>	typeMap := map[DataValidationOperator]string{<br>		DataValidationOperatorBetween:            "between",<br>		DataValidationOperatorEqual:              "equal",<br>		DataValidationOperatorGreaterThan:        "greaterThan",<br>		DataValidationOperatorGreaterThanOrEqual: "greaterThanOrEqual",<br>		DataValidationOperatorLessThan:           "lessThan",<br>		DataValidationOperatorLessThanOrEqual:    "lessThanOrEqual",<br>		DataValidationOperatorNotBetween:         "notBetween",<br>		DataValidationOperatorNotEqual:           "notEqual",<br>	}<br><br>	return typeMap[o]<br><br>}</code> | <code>1.0</code> |
+  | <code>// Convert_v1_PodSecurityPolicyReview_To_security_PodSecurityPolicyReview is an autogenerated conversion function.</code> | <code>func Convert_v1_PodSecurityPolicyReview_To_security_PodSecurityPolicyReview(in *v1.PodSecurityPolicyReview, out *security.PodSecurityPolicyReview, s conversion.Scope) error {<br>	return autoConvert_v1_PodSecurityPolicyReview_To_security_PodSecurityPolicyReview(in, out, s)<br>}</code>                                                                                                                                                                                                                                                                                                                                                                                    | <code>1.0</code> |
+  | <code>// Of note, removeSegments() keeps the ordering of the results stable.</code>                                             | <code>func removeSegments(segments []Segment, toRemove []Segment) []Segment {<br>	rv := make([]Segment, 0, len(segments)-len(toRemove))<br>OUTER:<br>	for _, segment := range segments {<br>		for _, r := range toRemove {<br>			if segment == r {<br>				continue OUTER<br>			}<br>		}<br>		rv = append(rv, segment)<br>	}<br>	return rv<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`: 256
+- `per_device_eval_batch_size`: 256
+- `num_train_epochs`: 5
+- `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`: 256
+- `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`: 0.0
+- `adam_beta1`: 0.9
+- `adam_beta2`: 0.999
+- `adam_epsilon`: 1e-08
+- `max_grad_norm`: 1
+- `num_train_epochs`: 5
+- `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}
+- `tp_size`: 0
+- `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
+| Epoch  | Step | Training Loss |
+|:------:|:----:|:-------------:|
+| 0.0737 | 500  | 0.8902        |
+| 0.1474 | 1000 | 0.1132        |
+| 0.2211 | 1500 | 0.1046        |
+| 0.2949 | 2000 | 0.0988        |
+
+
+### Framework Versions
+- Python: 3.11.12
+- Sentence Transformers: 3.4.1
+- Transformers: 4.51.3
+- PyTorch: 2.6.0+cu124
+- Accelerate: 1.6.0
+- Datasets: 3.5.1
+- 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 +1,6 @@
+{
+  "</s>": 50001,
+  "<mask>": 50003,
+  "<s>": 50000,
+  "<unk>": 50002
+}

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": 0,
+  "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": "4.51.3",
+  "type_vocab_size": 2,
+  "vocab_size": 50004
+}

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.4.1",
+    "transformers": "4.51.3",
+    "pytorch": "2.6.0+cu124"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine"
+}

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": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,97 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50000": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50001": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50002": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50003": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "max_length": null,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_to_multiple_of": null,
+  "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "</s>",
+  "stride": 0,
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<unk>"
+}