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 +1,633 @@
+---
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- dataset_size:1761493
+- loss:MultipleNegativesRankingLoss
+base_model: Shuu12121/CodeModernBERT-Crow
+widget:
+- source_sentence: 'getAttachment
+
+    Return an attachment from a SharePoint list item
+
+
+    @param $list_name Name of list
+
+    @param $list_item_id ID of record item is attached to
+
+    @return Array of attachment urls'
+  sentences:
+  - "private function getOrderDirection(): string\n    {\n        $result = !empty($this->searchData['sort_by_order'])\
+    \ ?\n            $this->searchData['sort_by_order'] :\n            Options::DEFAULT_SORT_BY_ORDER;\n\
+    \n        return $result;\n    }"
+  - "function(property, value) {\n        var values = [];\n        for (var i in\
+    \ this._nodes) {\n            if (this._nodes.hasOwnProperty(i)) {\n         \
+    \       var n = this._nodes[i];\n                if ((property in n && n[property]\
+    \ == value) || (n.data && value == n.data[property])) {\n                    values.push(n);\n\
+    \                }\n            }\n        }\n\n        return (values.length)\
+    \ ? values : null;\n    }"
+  - "public function getAttachments ($list_name, $list_item_id) {\n\t\t// Wrap in\
+    \ CAML\n\t\t$CAML = '\n\t\t<GetAttachmentCollection xmlns=\"http://schemas.microsoft.com/sharepoint/soap/\"\
+    >\n\t\t\t<listName>' . $list_name . '</listName>\n\t\t\t<listItemID>' . $list_item_id\
+    \ . '</listItemID>\n\t\t</GetAttachmentCollection>';\n\n\t\t$xmlvar = new \\SoapVar($CAML,\
+    \ XSD_ANYXML);\n\n\t\t// Attempt to run operation\n\t\ttry {\n\t\t\t$rawXml =\
+    \ $this->soapClient->GetAttachmentCollection($xmlvar)->GetAttachmentCollectionResult->any;\n\
+    \t\t} catch (\\SoapFault $fault) {\n\t\t\t$this->onError($fault);\n\t\t}\n\n\t\
+    \t// Load XML in to DOM document and grab all list items.\n\t\t$nodes = $this->getArrayFromElementsByTagName($rawXml,\
+    \ 'Attachment');\n\n\t\t$attachments = array();\n\n\t\t// Format data in to array\
+    \ or object\n\t\tforeach ($nodes as $counter => $node) {\n\t\t\t$attachments[]\
+    \ = $node->textContent;\n\t\t}\n\n\t\t// Return Array of attachment URLs\n\t\t\
+    return $attachments;\n\t}"
+- source_sentence: 'Load the services into the module if they have
+
+    not loaded already
+
+    @param \OtherCode\FController\Components\Services $services
+
+    @param \OtherCode\FController\Components\Registry $storage
+
+    @param \OtherCode\FController\Components\Messages $messages'
+  sentences:
+  - "public function connect(\\OtherCode\\FController\\Components\\Services $services,\
+    \ \\OtherCode\\FController\\Components\\Registry $storage, \\OtherCode\\FController\\\
+    Components\\Messages $messages)\n    {\n        if (!isset($this->services)) {\n\
+    \            $this->services = $services;\n        }\n\n        if (!isset($this->storage))\
+    \ {\n            $this->storage = $storage;\n        }\n\n        if (!isset($this->messages))\
+    \ {\n            $this->messages = $messages;\n        }\n    }"
+  - "function(element) {\n    var that = this;\n    this.element = element;\n    this.signalTap\
+    \ = new Listeners();\n    this.signalLong = new Listeners();\n    this.signalTouchstart\
+    \ = new Listeners();\n    this.signalTouchend = new Listeners();\n    this.signalMove\
+    \ = windowMove;\n    this._touch = 0; // 0 = Nothing,  1 = Mouse, 2 = Touch.\n\
+    \    this._onMouseDown = function(evt) {\n        if (that._touch) return;\n \
+    \       currentTouchListener = that;\n        that._touch = 1;\n        evt.preventDefault();\n\
+    \        evt.stopPropagation();\n        var rect = that.element.getBoundingClientRect();\n\
+    \        var arg = {\n            x: evt.pageX - rect.left,\n            y: evt.pageY\
+    \ - rect.top,\n            rect: rect\n        };\n        console.info(\"[tfw.touch-event]\
+    \ arg=...\", arg);\n        that.signalTouchstart.fire(arg);\n    };\n    this._onTouchstart\
+    \ = function(evt) {\n        if (that._touch) return;\n        currentTouchListener\
+    \ = that;\n        that._touch = 2;\n        evt.preventDefault();\n        evt.stopPropagation();\n\
+    \        var rect = that.element.getBoundingClientRect();\n        var arg = {\n\
+    \            x: evt.pageX - rect.left,\n            y: evt.pageY - rect.top,\n\
+    \            rect: rect\n        };\n        console.info(\"[tfw.touch-event]\
+    \ arg=...\", arg);\n        that.signalTouchstart.fire(arg);\n    };\n    element.addEventListener(\"\
+    mousedown\", this._onMouseDown, false);\n}"
+  - "func (cfg *TransportConfig) WithBasePath(basePath string) *TransportConfig {\n\
+    \tcfg.BasePath = basePath\n\treturn cfg\n}"
+- source_sentence: '// DirectoryValidator ensures the input is a valid and **existing**
+    directory
+
+    // Returns modified extended path'
+  sentences:
+  - "func DirectoryValidator(input string) (interface{}, error) {\n\tif input == \"\
+    \" {\n\t\treturn \"\", nil\n\t}\n\n\tpath, err := PathValidator(input)\n\tif err\
+    \ != nil {\n\t\treturn nil, err\n\t}\n\tpathStr := path.(string)\n\n\tinfo, err\
+    \ := os.Stat(pathStr)\n\tif err != nil {\n\t\treturn nil, err\n\t}\n\n\tif !info.IsDir()\
+    \ {\n\t\treturn nil, fmt.Errorf(\"%s is not a directory\", pathStr)\n\t}\n\n\t\
+    return pathStr, nil\n}"
+  - "public void addGivenVendor(String source, String name, String value, boolean\
+    \ regex, Confidence confidence) {\n        givenVendor.add(new EvidenceMatcher(source,\
+    \ name, value, regex, confidence));\n    }"
+  - "func (a *EnableArgs) SetMaxScriptsCacheSize(maxScriptsCacheSize float64) *EnableArgs\
+    \ {\n\ta.MaxScriptsCacheSize = &maxScriptsCacheSize\n\treturn a\n}"
+- source_sentence: https://url.spec.whatwg.org/#url-miscellaneous
+  sentences:
+  - "public boolean isDescendent(TarEntry desc) {\r\n        return desc.header.name.toString().startsWith(this.header.name.toString());\r\
+    \n    }"
+  - "public String displayErrors(String pathPrefix) {\n\n        if (pathPrefix ==\
+    \ null) {\n            pathPrefix = \"\";\n        }\n        StringBuffer html\
+    \ = new StringBuffer(512);\n        html.append(\"<table border='0' cellpadding='5'\
+    \ cellspacing='0' style='width: 100%; height: 100%;'>\");\n        html.append(\"\
+    \\t<tr>\");\n        html.append(\"\\t\\t<td style='vertical-align: middle; height:\
+    \ 100%;'>\");\n        html.append(getHtmlPart(\"C_BLOCK_START\", \"Error\"));\n\
+    \        html.append(\"\\t\\t\\t<table border='0' cellpadding='0' cellspacing='0'\
+    \ style='width: 100%;'>\");\n        html.append(\"\\t\\t\\t\\t<tr>\");\n    \
+    \    html.append(\"\\t\\t\\t\\t\\t<td><img src='\").append(pathPrefix).append(\"\
+    resources/error.png' border='0'></td>\");\n        html.append(\"\\t\\t\\t\\t\\\
+    t<td>&nbsp;&nbsp;</td>\");\n        html.append(\"\\t\\t\\t\\t\\t<td style='width:\
+    \ 100%;'>\");\n\n        Iterator<String> iter = getErrors().iterator();\n   \
+    \     while (iter.hasNext()) {\n            String msg = iter.next();\n      \
+    \      html.append(\"\\t\\t\\t\\t\\t\\t\");\n            html.append(msg);\n \
+    \           html.append(\"<br/>\");\n        }\n\n        html.append(\"\\t\\\
+    t\\t\\t\\t</td>\");\n        html.append(\"\\t\\t\\t\\t</tr>\");\n        html.append(\"\
+    \\t\\t\\t</table>\");\n        html.append(getHtmlPart(\"C_BLOCK_END\"));\n  \
+    \      html.append(\"\\t\\t</td>\");\n        html.append(\"\\t</tr>\");\n   \
+    \     html.append(\"</table>\");\n        return html.toString();\n    }"
+  - "function getDefaultPortFromScheme( scheme ) {\n  var port = null;\n  if ( scheme\
+    \ === 'ftp') {\n    port = 21;\n  }\n  else if ( scheme === 'gopher' ) {\n   \
+    \ port = 70;\n  }\n  else if ( scheme === 'http' || scheme === 'ws' ) {\n    port\
+    \ = 80;\n  }\n  else if ( scheme === 'https' || scheme === 'wss' ) {\n    port\
+    \ = 443;\n  }\n  return port;\n}"
+- source_sentence: syntactic sugar
+  sentences:
+  - "@Override\n    public void sawOpcode(int seen) {\n        int groupId = -1;\n\
+    \n        try {\n            stack.precomputation(this);\n\n            if (seen\
+    \ == Const.INVOKEINTERFACE) {\n                String className = getClassConstantOperand();\n\
+    \                String methodName = getNameConstantOperand();\n             \
+    \   String signature = getSigConstantOperand();\n                QMethod methodInfo\
+    \ = new QMethod(methodName, signature);\n\n                if (isCollection(className))\
+    \ {\n                    if (collectionMethods.contains(methodInfo) || ITERATOR.equals(methodInfo))\
+    \ {\n                        if (stack.getStackDepth() > 0) {\n              \
+    \              OpcodeStack.Item itm = stack.getStackItem(0);\n               \
+    \             groupId = findCollectionGroup(itm, true);\n                    \
+    \    }\n                    } else if (REMOVE.equals(methodInfo)) {\n        \
+    \                if (stack.getStackDepth() > 1) {\n                          \
+    \  OpcodeStack.Item itm = stack.getStackItem(1);\n                           \
+    \ int id = findCollectionGroup(itm, true);\n                            if ((id\
+    \ >= 0) && collectionGroups.get(id).isStandardCollection()) {\n              \
+    \                  Integer it = groupToIterator.get(Integer.valueOf(id));\n  \
+    \                              Loop loop = loops.get(it);\n                  \
+    \              if (loop != null) {\n                                    int pc\
+    \ = getPC();\n                                    if (loop.hasPC(pc)) {\n    \
+    \                                    boolean needPop = !Values.SIG_VOID.equals(SignatureUtils.getReturnSignature(signature));\n\
+    \n                                        if (!breakFollows(loop, needPop) &&\
+    \ !returnFollows(needPop)) {\n                                            bugReporter.reportBug(new\
+    \ BugInstance(this, BugType.DWI_DELETING_WHILE_ITERATING.name(), NORMAL_PRIORITY)\n\
+    \                                                    .addClass(this).addMethod(this).addSourceLine(this));\n\
+    \                                        }\n                                 \
+    \   }\n                                }\n                            }\n    \
+    \                    }\n                    } else {\n                       \
+    \ Integer numArgs = modifyingMethods.get(methodInfo);\n                      \
+    \  if ((numArgs != null) && (stack.getStackDepth() > numArgs.intValue())) {\n\
+    \                            OpcodeStack.Item itm = stack.getStackItem(numArgs.intValue());\n\
+    \                            int id = findCollectionGroup(itm, true);\n      \
+    \                      if (id >= 0) {\n                                Integer\
+    \ it = groupToIterator.get(Integer.valueOf(id));\n                           \
+    \     if (it != null) {\n                                    Loop loop = loops.get(it);\n\
+    \                                    if (loop != null) {\n                   \
+    \                     int pc = getPC();\n                                    \
+    \    if (loop.hasPC(pc)) {\n                                            boolean\
+    \ needPop = !Values.SIG_VOID.equals(SignatureUtils.getReturnSignature(signature));\n\
+    \                                            boolean breakFollows = breakFollows(loop,\
+    \ needPop);\n                                            boolean returnFollows\
+    \ = !breakFollows && returnFollows(needPop);\n\n                             \
+    \               if (!breakFollows && !returnFollows) {\n                     \
+    \                           bugReporter.reportBug(new BugInstance(this, BugType.DWI_MODIFYING_WHILE_ITERATING.name(),\
+    \ NORMAL_PRIORITY)\n                                                        .addClass(this).addMethod(this).addSourceLine(this));\n\
+    \                                            }\n                             \
+    \           }\n                                    }\n                       \
+    \         }\n                            }\n                        }\n      \
+    \              }\n                } else if (\"java/util/Iterator\".equals(className)\
+    \ && HASNEXT.equals(methodInfo) && (stack.getStackDepth() > 0)) {\n          \
+    \          OpcodeStack.Item itm = stack.getStackItem(0);\n                   \
+    \ Integer id = (Integer) itm.getUserValue();\n                    if (id != null)\
+    \ {\n                        groupId = id.intValue();\n                    }\n\
+    \                }\n            } else if ((seen == Const.PUTFIELD) || (seen ==\
+    \ Const.PUTSTATIC)) {\n                if (stack.getStackDepth() > 1) {\n    \
+    \                OpcodeStack.Item itm = stack.getStackItem(0);\n\n           \
+    \         Integer id = (Integer) itm.getUserValue();\n                    if (id\
+    \ == null) {\n                        FieldAnnotation fa = FieldAnnotation\n \
+    \                               .fromFieldDescriptor(new FieldDescriptor(getClassConstantOperand(),\
+    \ getNameConstantOperand(), getSigConstantOperand(), false));\n              \
+    \          itm = new OpcodeStack.Item(itm.getSignature(), fa, stack.getStackItem(1).getRegisterNumber());\n\
+    \                        removeFromCollectionGroup(itm);\n                   \
+    \     groupId = findCollectionGroup(itm, true);\n                    }\n     \
+    \           }\n            } else if (OpcodeUtils.isAStore(seen)) {\n        \
+    \        if (stack.getStackDepth() > 0) {\n                    OpcodeStack.Item\
+    \ itm = stack.getStackItem(0);\n                    Integer id = (Integer) itm.getUserValue();\n\
+    \                    if (id != null) {\n                        int reg = RegisterUtils.getAStoreReg(this,\
+    \ seen);\n\n                        try {\n                            JavaClass\
+    \ cls = itm.getJavaClass();\n                            if ((cls != null) &&\
+    \ cls.implementationOf(iteratorClass)) {\n                                Integer\
+    \ regIt = Integer.valueOf(reg);\n                                Iterator<Integer>\
+    \ curIt = groupToIterator.values().iterator();\n                             \
+    \   while (curIt.hasNext()) {\n                                    if (curIt.next().equals(regIt))\
+    \ {\n                                        curIt.remove();\n               \
+    \                     }\n                                }\n                 \
+    \               groupToIterator.put(id, regIt);\n                            }\n\
+    \n                            GroupPair pair = collectionGroups.get(id.intValue());\n\
+    \                            if (pair != null) {\n                           \
+    \     pair.addMember(Integer.valueOf(reg));\n                            }\n \
+    \                       } catch (ClassNotFoundException cnfe) {\n            \
+    \                bugReporter.reportMissingClass(cnfe);\n                     \
+    \   }\n                    } else {\n                        String cls = itm.getSignature();\n\
+    \                        if ((cls != null) && cls.startsWith(Values.SIG_QUALIFIED_CLASS_PREFIX))\
+    \ {\n                            cls = SignatureUtils.trimSignature(cls);\n  \
+    \                          if (isCollection(cls) || \"java/util/Iterator\".equals(cls))\
+    \ {\n                                int reg = RegisterUtils.getAStoreReg(this,\
+    \ seen);\n                                removeFromCollectionGroup(new OpcodeStack.Item(itm,\
+    \ reg));\n                                Iterator<Integer> it = groupToIterator.values().iterator();\n\
+    \                                while (it.hasNext()) {\n                    \
+    \                if (it.next().intValue() == reg) {\n                        \
+    \                it.remove();\n                                        break;\n\
+    \                                    }\n                                }\n  \
+    \                          }\n                        }\n                    }\n\
+    \                }\n            } else if (OpcodeUtils.isALoad(seen)) {\n    \
+    \            int reg = RegisterUtils.getALoadReg(this, seen);\n              \
+    \  OpcodeStack.Item itm = new OpcodeStack.Item(new OpcodeStack.Item(), reg);\n\
+    \                groupId = findCollectionGroup(itm, false);\n            } else\
+    \ if ((seen == Const.IFEQ) && (stack.getStackDepth() > 0)) {\n               \
+    \ OpcodeStack.Item itm = stack.getStackItem(0);\n                Integer id =\
+    \ (Integer) itm.getUserValue();\n                if (id != null) {\n         \
+    \           int target = getBranchTarget();\n                    int gotoAddr\
+    \ = target - 3;\n                    int ins = getCode().getCode()[gotoAddr];\n\
+    \                    if (ins < 0) {\n                        ins = 256 + ins;\n\
+    \                    }\n                    if ((ins == Const.GOTO) || (ins ==\
+    \ Const.GOTO_W)) {\n                        Integer reg = groupToIterator.get(id);\n\
+    \                        if (reg != null) {\n                            loops.put(reg,\
+    \ new Loop(getPC(), gotoAddr));\n                        }\n                 \
+    \   }\n                }\n            }\n        } finally {\n            TernaryPatcher.pre(stack,\
+    \ seen);\n            stack.sawOpcode(this, seen);\n            TernaryPatcher.post(stack,\
+    \ seen);\n            if ((groupId >= 0) && (stack.getStackDepth() > 0)) {\n \
+    \               OpcodeStack.Item itm = stack.getStackItem(0);\n              \
+    \  itm.setUserValue(Integer.valueOf(groupId));\n            }\n\n            processEndOfScopes(Integer.valueOf(getPC()));\n\
+    \        }\n    }"
+  - "function Concept(concept) {\n  if (!(concept.prefLabel && concept.id && concept.type\
+    \ === 'Concept')) {\n    throw new Error('Invalid concept: \"' + concept.id +\
+    \ '\"');\n  }\n  this.id = concept.id;\n  this.prefLabel = concept.prefLabel;\n\
+    \  this.altLabel = concept.altLabel;\n  this.hiddenLabel = concept.hiddenLabel;\n\
+    \  this.definition = concept.definition;\n  this._topConceptOf = concept.topConceptOf;\n\
+    \  this._partOfScheme = false;\n  this._originalConcept = concept;\n  this._broaderConcepts\
+    \ = [];\n  this._narrowerConcepts = [];\n  this._relatedConcepts = [];\n}"
+  - "public MessageDestinationComponent addDestination() { //3\r\n      MessageDestinationComponent\
+    \ t = new MessageDestinationComponent();\r\n      if (this.destination == null)\r\
+    \n        this.destination = new ArrayList<MessageDestinationComponent>();\r\n\
+    \      this.destination.add(t);\r\n      return t;\r\n    }"
+pipeline_tag: sentence-similarity
+library_name: sentence-transformers
+---
+
+# SentenceTransformer based on Shuu12121/CodeModernBERT-Crow
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [Shuu12121/CodeModernBERT-Crow](https://huggingface.co/Shuu12121/CodeModernBERT-Crow). 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-Crow](https://huggingface.co/Shuu12121/CodeModernBERT-Crow) <!-- at revision 69dc7bd7a418b18011047cf48670e7eb0b499651 -->
+- **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 = [
+    'syntactic sugar',
+    'public MessageDestinationComponent addDestination() { //3\r\n      MessageDestinationComponent t = new MessageDestinationComponent();\r\n      if (this.destination == null)\r\n        this.destination = new ArrayList<MessageDestinationComponent>();\r\n      this.destination.add(t);\r\n      return t;\r\n    }',
+    'function Concept(concept) {\n  if (!(concept.prefLabel && concept.id && concept.type === \'Concept\')) {\n    throw new Error(\'Invalid concept: "\' + concept.id + \'"\');\n  }\n  this.id = concept.id;\n  this.prefLabel = concept.prefLabel;\n  this.altLabel = concept.altLabel;\n  this.hiddenLabel = concept.hiddenLabel;\n  this.definition = concept.definition;\n  this._topConceptOf = concept.topConceptOf;\n  this._partOfScheme = false;\n  this._originalConcept = concept;\n  this._broaderConcepts = [];\n  this._narrowerConcepts = [];\n  this._relatedConcepts = [];\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: 1,761,493 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: 48.06 tokens</li><li>max: 914 tokens</li></ul> | <ul><li>min: 28 tokens</li><li>mean: 183.37 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>// NewMockUnit creates a new mock instance</code>                | <code>func NewMockUnit(ctrl *gomock.Controller) *MockUnit {<br>	mock := &MockUnit{ctrl: ctrl}<br>	mock.recorder = &MockUnitMockRecorder{mock}<br>	return mock<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>// addHandler adds a handler for a puType/event.</code>          | <code>func (r *registerer) addHandler(puType common.PUType, event common.Event, handler common.EventHandler) {<br>	r.handlers[puType][event] = handler<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 |
+|:------:|:-----:|:-------------:|
+| 0.0727 | 500   | 0.7681        |
+| 0.1453 | 1000  | 0.1157        |
+| 0.2180 | 1500  | 0.1068        |
+| 0.2907 | 2000  | 0.0979        |
+| 0.3633 | 2500  | 0.0969        |
+| 0.4360 | 3000  | 0.0945        |
+| 0.5086 | 3500  | 0.0918        |
+| 0.5813 | 4000  | 0.0905        |
+| 0.6540 | 4500  | 0.088         |
+| 0.7266 | 5000  | 0.0854        |
+| 0.7993 | 5500  | 0.0855        |
+| 0.8720 | 6000  | 0.0873        |
+| 0.9446 | 6500  | 0.082         |
+| 1.0173 | 7000  | 0.0728        |
+| 1.0900 | 7500  | 0.0427        |
+| 1.1626 | 8000  | 0.0435        |
+| 1.2353 | 8500  | 0.0441        |
+| 1.3079 | 9000  | 0.045         |
+| 1.3806 | 9500  | 0.0444        |
+| 1.4533 | 10000 | 0.0433        |
+| 1.5259 | 10500 | 0.0447        |
+| 1.5986 | 11000 | 0.0443        |
+| 1.6713 | 11500 | 0.0439        |
+| 1.7439 | 12000 | 0.0449        |
+| 1.8166 | 12500 | 0.0441        |
+| 1.8893 | 13000 | 0.0443        |
+| 1.9619 | 13500 | 0.0461        |
+| 2.0346 | 14000 | 0.0335        |
+| 2.1073 | 14500 | 0.0192        |
+| 2.1799 | 15000 | 0.0199        |
+| 2.2526 | 15500 | 0.0197        |
+| 2.3252 | 16000 | 0.0199        |
+| 2.3979 | 16500 | 0.02          |
+| 2.4706 | 17000 | 0.0206        |
+| 2.5432 | 17500 | 0.0204        |
+| 2.6159 | 18000 | 0.0202        |
+| 2.6886 | 18500 | 0.0206        |
+| 2.7612 | 19000 | 0.0209        |
+| 2.8339 | 19500 | 0.0211        |
+| 2.9066 | 20000 | 0.0207        |
+| 2.9792 | 20500 | 0.0202        |
+| 3.0519 | 21000 | 0.014         |
+| 3.1245 | 21500 | 0.0112        |
+| 3.1972 | 22000 | 0.0111        |
+| 3.2699 | 22500 | 0.0113        |
+| 3.3425 | 23000 | 0.0117        |
+| 3.4152 | 23500 | 0.0116        |
+| 3.4879 | 24000 | 0.0118        |
+| 3.5605 | 24500 | 0.0114        |
+| 3.6332 | 25000 | 0.0114        |
+| 3.7059 | 25500 | 0.011         |
+| 3.7785 | 26000 | 0.0109        |
+| 3.8512 | 26500 | 0.0113        |
+| 3.9238 | 27000 | 0.0113        |
+| 3.9965 | 27500 | 0.0111        |
+| 4.0692 | 28000 | 0.0085        |
+| 4.1418 | 28500 | 0.0081        |
+| 4.2145 | 29000 | 0.0082        |
+| 4.2872 | 29500 | 0.0083        |
+| 4.3598 | 30000 | 0.0085        |
+| 4.4325 | 30500 | 0.0086        |
+| 4.5052 | 31000 | 0.0082        |
+| 4.5778 | 31500 | 0.0083        |
+| 4.6505 | 32000 | 0.0084        |
+| 4.7232 | 32500 | 0.0085        |
+| 4.7958 | 33000 | 0.0083        |
+| 4.8685 | 33500 | 0.0082        |
+| 4.9411 | 34000 | 0.0081        |
+
+
+### Framework Versions
+- Python: 3.11.12
+- Sentence Transformers: 3.4.1
+- Transformers: 4.51.3
+- PyTorch: 2.6.0+cu124
+- Accelerate: 1.5.2
+- Datasets: 3.5.0
+- 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 +1,6 @@
+{
+  "</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"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:801a2a2608009baa7e661ca6a6206734f39954cf8a4af85409ffc70705094c68
+size 606681112

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>"
+}