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 +1,657 @@
+---
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- dataset_size:6960000
+- loss:MultipleNegativesRankingLoss
+base_model: Shuu12121/CodeModernBERT-Owl-4.1
+widget:
+- source_sentence: Create a function to call with simple and hard types This is done
+    so simple types don't need to check for hard types
+  sentences:
+  - "function copyHead(headHtml, doc) {\n        var head = doc.getElementsByTagName('head')[0];\n\
+    \n        if (head.innerHTML == headHtml) {\n            // the content is already\
+    \ correct\n            return;\n        }\n\n        jQuery.init(head).empty();\n\
+    \n        appendHTML(headHtml, head);\n    }"
+  - "func compress(value float64) int16 {\n\ti := int16(precision*math.Log(1.0+math.Abs(value))\
+    \ + 0.5)\n\tif value < 0 {\n\t\treturn -1 * i\n\t}\n\treturn i\n}"
+  - "function (types, hard) {\n            for (var t in types) {\n              \
+    \  if (types.hasOwnProperty(t)) {\n                    (function (prop) {\n  \
+    \                      Object.defineProperty(props, prop, {\n                \
+    \            get: function () {\n                                for (var i =\
+    \ 0; i < inputs.length; ++i) {\n                                    if (!checkType(prop,\
+    \ inputs[i], hard)) {\n                                        return false;\n\
+    \                                    }\n                                }\n  \
+    \                              return true;\n                            }\n \
+    \                       });\n                    }(t));\n                }\n \
+    \           }\n        }"
+- source_sentence: 'Takes an array of promises and returns a promise that is fulfilled
+    once all
+
+    the promises in the array are fulfilled
+
+
+    @param {Array} array The array of promises
+
+    @return {Promise} the promise that is fulfilled when all the array is fulfilled,
+    resolved to the array of results'
+  sentences:
+  - "public static List<DockerImage> getDockerImagesFromAgents(final int buildInfoId,\
+    \ TaskListener listener) throws IOException, InterruptedException {\n        List<DockerImage>\
+    \ dockerImages = new ArrayList<DockerImage>();\n\n        // Collect images from\
+    \ the master:\n        dockerImages.addAll(getAndDiscardImagesByBuildId(buildInfoId));\n\
+    \n        // Collect images from all the agents:\n        List<Node> nodes = Jenkins.getInstance().getNodes();\n\
+    \        for (Node node : nodes) {\n            if (node == null || node.getChannel()\
+    \ == null) {\n                continue;\n            }\n            try {\n  \
+    \              List<DockerImage> partialDockerImages = node.getChannel().call(new\
+    \ MasterToSlaveCallable<List<DockerImage>, IOException>() {\n                \
+    \    public List<DockerImage> call() throws IOException {\n                  \
+    \      List<DockerImage> dockerImages = new ArrayList<DockerImage>();\n      \
+    \                  dockerImages.addAll(getAndDiscardImagesByBuildId(buildInfoId));\n\
+    \                        return dockerImages;\n                    }\n       \
+    \         });\n                dockerImages.addAll(partialDockerImages);\n   \
+    \         } catch (Exception e) {\n                listener.getLogger().println(\"\
+    Could not collect docker images from Jenkins node '\" + node.getDisplayName()\
+    \ + \"' due to: \" + e.getMessage());\n            }\n        }\n        return\
+    \ dockerImages;\n    }"
+  - "public function findUnitByStart(Token $token) {\n\t\tforeach ($this->collection\
+    \ as $unit) {\n\t\t\tif ($unit->start === $token) {\n\t\t\t\treturn $unit;\n\t\
+    \t\t}\n\t\t}\n\n\t\treturn null;\n\t}"
+  - "function (array) {\n            var self = this,\n                deferred =\
+    \ new Deferred(),\n                fulfilled = 0,\n                length,\n \
+    \               results = [],\n                hasError = false;\n\n         \
+    \   if (!isArray(array)) {\n                array = slice.call(arguments);\n \
+    \           }\n            length = array.length;\n\n            if (length ===\
+    \ 0) {\n                deferred.emitSuccess(results);\n            } else {\n\
+    \                array.forEach(function (promise, index) {\n\n               \
+    \     self.when(promise,\n                        //Success\n                \
+    \        function (value) {\n                            results[index] = value;\n\
+    \                            fulfilled += 1;\n                            if (fulfilled\
+    \ === length) {\n\n                                if (hasError) {\n         \
+    \                           deferred.emitError(results);\n                   \
+    \             } else {\n                                    deferred.emitSuccess(results);\n\
+    \                                }\n                            }\n          \
+    \              },\n                        //Error\n                        function\
+    \ (error) {\n                            results[index] = error;\n           \
+    \                 hasError = true;\n                            fulfilled += 1;\n\
+    \                            if (fulfilled === length) {\n                   \
+    \             deferred.emitError(results);\n                            }\n  \
+    \                      }\n                    );\n                });\n      \
+    \      }\n            return deferred.getPromise();\n        }"
+- source_sentence: 'Create and return a MBeanInfo instance for the supplied object.
+
+
+    @param object             Supplied object to inspect.
+
+    @param classIntrospector  ClassIntrospector to use.
+
+
+    @return a MBeanInfo instance for the supplied object.
+
+
+    @throws IntrospectionException    If failed to create Info object
+
+    @throws IllegalArgumentException'
+  sentences:
+  - "function toggleShepherdModalClass(currentElement) {\n  const shepherdModal =\
+    \ document.querySelector(`${classNames.modalTarget}`);\n\n  if (shepherdModal)\
+    \ {\n    shepherdModal.classList.remove(classNames.modalTarget);\n  }\n\n  currentElement.classList.add(classNames.modalTarget);\n\
+    }"
+  - "public function handle(): void\n    {\n        $directory = $this->argument('directory');\n\
+    \n        if (!is_dir($directory)) {\n            $this->error(\n            \
+    \    sprintf('The directory \"%1$s\" does not exist. Run `resume make --output=%1$s`.',\
+    \ $directory)\n            );\n\n            exit(1);\n        }\n\n        chdir($directory);\n\
+    \n        $this->info(\n            sprintf('Resume preview started: http://%s:%s',\
+    \ $this->host(), $this->port())\n        );\n        $this->info('Stop the server\
+    \ with CTRL+C.');\n\n        passthru($this->command($this->host(), $this->port()),\
+    \ $exitCode);\n\n        exit($exitCode);\n    }"
+  - "private MBeanInfo getInfo(Object object, ClassIntrospector classIntrospector)\
+    \ throws IntrospectionException {\n        JmxBean jmxBean = AnnotationUtils.getAnnotation(object.getClass(),\
+    \ JmxBean.class);\n       \n        MBeanInfo beanInfo = new MBeanInfo(object.getClass().getName(),\
+    \ \n                                           jmxBean.description(), \n     \
+    \                                      getAttributes(classIntrospector), \n  \
+    \                                         getConstructors(classIntrospector),\
+    \ \n                                           getOperations(classIntrospector),\
+    \ \n                                           getNotifications(object));\n  \
+    \      return beanInfo;\n    }"
+- source_sentence: 'Adds a collaborator to this folder.
+
+
+    @param collaborator the collaborator to add.
+
+    @param role         the role of the collaborator.
+
+    @return info about the new collaboration.'
+  sentences:
+  - "final public function readUInt32()\n    {\n        if (PHP_INT_SIZE < 8) {\n\
+    \            // @codeCoverageIgnoreStart\n            if ($this->isLittleEndian())\
+    \ {\n                list(, $lo, $hi) = unpack('S*', $this->read(4));\n      \
+    \      } else {\n                list(, $hi, $lo) = unpack('S*', $this->read(4));\n\
+    \            }\n            return $hi * (0xffff+1) + $lo; // eq $hi << 16 | $lo\n\
+    \            // @codeCoverageIgnoreEnd\n        } else {\n            list(, $int)\
+    \ = unpack('L*', $this->read(4)) + array(0, 0);\n            return $int;\n  \
+    \      }\n    }"
+  - "public function add_on_empty($attribute, $msg)\n\t{\n\t\tif (empty($msg))\n\t\
+    \t\t$msg = self::$DEFAULT_ERROR_MESSAGES['empty'];\n\n\t\tif (empty($this->model->$attribute))\n\
+    \t\t\t$this->add($attribute, $msg);\n\t}"
+  - "public BoxCollaboration.Info collaborate(BoxCollaborator collaborator, BoxCollaboration.Role\
+    \ role) {\n        JsonObject accessibleByField = new JsonObject();\n        accessibleByField.add(\"\
+    id\", collaborator.getID());\n\n        if (collaborator instanceof BoxUser) {\n\
+    \            accessibleByField.add(\"type\", \"user\");\n        } else if (collaborator\
+    \ instanceof BoxGroup) {\n            accessibleByField.add(\"type\", \"group\"\
+    );\n        } else {\n            throw new IllegalArgumentException(\"The given\
+    \ collaborator is of an unknown type.\");\n        }\n\n        return this.collaborate(accessibleByField,\
+    \ role, null, null);\n    }"
+- source_sentence: 'Register the router instance.
+
+
+    @return void'
+  sentences:
+  - "protected function registerRouter()\n\t{\n\t\t$this->app['router'] = $this->app->share(function($app)\n\
+    \t\t{\n\t\t\treturn new Router($app['events'], $app);\n\t\t});\n\t}"
+  - "@Override\n    @Nullable\n    public Long apply(@Nonnull Long partialAccountNumber)\
+    \ {\n        checkNotNull(partialAccountNumber, \"partialAccountNumber can't be\
+    \ null\");\n        boolean isEven = true;\n        int total = 0;\n        Long\
+    \ temp = partialAccountNumber;\n\n        while (temp > 0) {\n            long\
+    \ digit = temp % 10;\n            if (isEven) {\n                long multipliedDigit\
+    \ = digit * 2;\n                total += isTwoDigit(multipliedDigit) ? sumUpDigits(multipliedDigit)\
+    \ : multipliedDigit;\n            } else {\n                total += digit;\n\
+    \            }\n            temp /= 10;\n            isEven = !isEven;\n     \
+    \   }\n\n        int check = total * 9 % 10;\n\n        return partialAccountNumber\
+    \ * 10 + check;\n    }"
+  - "func (d *Driver) DiffSize(id string, idMappings *idtools.IDMappings, parent string,\
+    \ parentMappings *idtools.IDMappings, mountLabel string) (size int64, err error)\
+    \ {\n\tif d.useNaiveDiff() || !d.isParent(id, parent) {\n\t\treturn d.naiveDiff.DiffSize(id,\
+    \ idMappings, parent, parentMappings, mountLabel)\n\t}\n\treturn directory.Size(d.getDiffPath(id))\n\
+    }"
+pipeline_tag: sentence-similarity
+library_name: sentence-transformers
+---
+
+# SentenceTransformer based on Shuu12121/CodeModernBERT-Owl-4.1
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [Shuu12121/CodeModernBERT-Owl-4.1](https://huggingface.co/Shuu12121/CodeModernBERT-Owl-4.1). 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-4.1](https://huggingface.co/Shuu12121/CodeModernBERT-Owl-4.1) <!-- at revision 1daade193254e92a8593c9fe97fc80e2cb742df4 -->
+- **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 = [
+    'Register the router instance.\n\n@return void',
+    "protected function registerRouter()\n\t{\n\t\t$this->app['router'] = $this->app->share(function($app)\n\t\t{\n\t\t\treturn new Router($app['events'], $app);\n\t\t});\n\t}",
+    'func (d *Driver) DiffSize(id string, idMappings *idtools.IDMappings, parent string, parentMappings *idtools.IDMappings, mountLabel string) (size int64, err error) {\n\tif d.useNaiveDiff() || !d.isParent(id, parent) {\n\t\treturn d.naiveDiff.DiffSize(id, idMappings, parent, parentMappings, mountLabel)\n\t}\n\treturn directory.Size(d.getDiffPath(id))\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: 6,960,000 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: 50.31 tokens</li><li>max: 1024 tokens</li></ul> | <ul><li>min: 28 tokens</li><li>mean: 164.73 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>// GetNodeID returns the NodeID field if it's non-nil, zero value otherwise.</code>                                      | <code>func (a *App) GetNodeID() string {<br>	if a == nil || a.NodeID == nil {<br>		return ""<br>	}<br>	return *a.NodeID<br>}</code>                                                                                                                                                                                                                                                                                                                                                                                                                                                            | <code>1.0</code> |
+  | <code>// SignVote signs a canonical representation of the vote, along with the<br>// chainID. Implements PrivValidator.</code> | <code>func (pv *FilePV) SignVote(chainID string, vote *types.Vote) error {<br>	if err := pv.signVote(chainID, vote); err != nil {<br>		return fmt.Errorf("error signing vote: %v", err)<br>	}<br>	return nil<br>}</code>                                                                                                                                                                                                                                                                                                                                                                       | <code>1.0</code> |
+  | <code>//GetQyAccessToken 获取access_token</code>                                                                                 | <code>func (ctx *Context) GetQyAccessToken() (accessToken string, err error) {<br>	ctx.accessTokenLock.Lock()<br>	defer ctx.accessTokenLock.Unlock()<br><br>	accessTokenCacheKey := fmt.Sprintf("qy_access_token_%s", ctx.AppID)<br>	val := ctx.Cache.Get(accessTokenCacheKey)<br>	if val != nil {<br>		accessToken = val.(string)<br>		return<br>	}<br><br>	//从微信服务器获取<br>	var resQyAccessToken ResQyAccessToken<br>	resQyAccessToken, err = ctx.GetQyAccessTokenFromServer()<br>	if err != nil {<br>		return<br>	}<br><br>	accessToken = resQyAccessToken.AccessToken<br>	return<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`: 250
+- `per_device_eval_batch_size`: 250
+- `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`: 250
+- `per_device_eval_batch_size`: 250
+- `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
+- `hub_revision`: None
+- `gradient_checkpointing`: False
+- `gradient_checkpointing_kwargs`: None
+- `include_inputs_for_metrics`: False
+- `include_for_metrics`: []
+- `eval_do_concat_batches`: True
+- `fp16_backend`: auto
+- `push_to_hub_model_id`: None
+- `push_to_hub_organization`: None
+- `mp_parameters`: 
+- `auto_find_batch_size`: False
+- `full_determinism`: False
+- `torchdynamo`: None
+- `ray_scope`: last
+- `ddp_timeout`: 1800
+- `torch_compile`: False
+- `torch_compile_backend`: None
+- `torch_compile_mode`: None
+- `include_tokens_per_second`: False
+- `include_num_input_tokens_seen`: False
+- `neftune_noise_alpha`: None
+- `optim_target_modules`: None
+- `batch_eval_metrics`: False
+- `eval_on_start`: False
+- `use_liger_kernel`: False
+- `liger_kernel_config`: None
+- `eval_use_gather_object`: False
+- `average_tokens_across_devices`: False
+- `prompts`: None
+- `batch_sampler`: batch_sampler
+- `multi_dataset_batch_sampler`: round_robin
+
+</details>
+
+### Training Logs
+<details><summary>Click to expand</summary>
+
+| Epoch  | Step  | Training Loss |
+|:------:|:-----:|:-------------:|
+| 0.0180 | 500   | 0.9746        |
+| 0.0359 | 1000  | 0.1636        |
+| 0.0539 | 1500  | 0.1502        |
+| 0.0718 | 2000  | 0.1374        |
+| 0.0898 | 2500  | 0.1314        |
+| 0.1078 | 3000  | 0.1241        |
+| 0.1257 | 3500  | 0.1152        |
+| 0.1437 | 4000  | 0.1146        |
+| 0.1616 | 4500  | 0.1065        |
+| 0.1796 | 5000  | 0.1014        |
+| 0.1976 | 5500  | 0.0983        |
+| 0.2155 | 6000  | 0.0987        |
+| 0.2335 | 6500  | 0.0917        |
+| 0.2514 | 7000  | 0.0912        |
+| 0.2694 | 7500  | 0.0896        |
+| 0.2874 | 8000  | 0.086         |
+| 0.3053 | 8500  | 0.0811        |
+| 0.3233 | 9000  | 0.0813        |
+| 0.3412 | 9500  | 0.082         |
+| 0.3592 | 10000 | 0.0759        |
+| 0.3772 | 10500 | 0.0753        |
+| 0.3951 | 11000 | 0.0722        |
+| 0.4131 | 11500 | 0.0707        |
+| 0.4310 | 12000 | 0.0699        |
+| 0.4490 | 12500 | 0.0698        |
+| 0.4670 | 13000 | 0.0679        |
+| 0.4849 | 13500 | 0.0653        |
+| 0.5029 | 14000 | 0.0641        |
+| 0.5208 | 14500 | 0.063         |
+| 0.5388 | 15000 | 0.0621        |
+| 0.5568 | 15500 | 0.061         |
+| 0.5747 | 16000 | 0.0581        |
+| 0.5927 | 16500 | 0.0555        |
+| 0.6106 | 17000 | 0.0552        |
+| 0.6286 | 17500 | 0.0551        |
+| 0.6466 | 18000 | 0.0533        |
+| 0.6645 | 18500 | 0.0521        |
+| 0.6825 | 19000 | 0.051         |
+| 0.7004 | 19500 | 0.0509        |
+| 0.7184 | 20000 | 0.0499        |
+| 0.7364 | 20500 | 0.0468        |
+| 0.7543 | 21000 | 0.0484        |
+| 0.7723 | 21500 | 0.0466        |
+| 0.7902 | 22000 | 0.0446        |
+| 0.8082 | 22500 | 0.0453        |
+| 0.8261 | 23000 | 0.0442        |
+| 0.8441 | 23500 | 0.0424        |
+| 0.8621 | 24000 | 0.0434        |
+| 0.8800 | 24500 | 0.0416        |
+| 0.8980 | 25000 | 0.0406        |
+| 0.9159 | 25500 | 0.0404        |
+| 0.9339 | 26000 | 0.0398        |
+| 0.9519 | 26500 | 0.0406        |
+| 0.9698 | 27000 | 0.0387        |
+| 0.9878 | 27500 | 0.0386        |
+| 1.0057 | 28000 | 0.0311        |
+| 1.0237 | 28500 | 0.0193        |
+| 1.0417 | 29000 | 0.0197        |
+| 1.0596 | 29500 | 0.0186        |
+| 1.0776 | 30000 | 0.0192        |
+| 1.0955 | 30500 | 0.0194        |
+| 1.1135 | 31000 | 0.0196        |
+| 1.1315 | 31500 | 0.0198        |
+| 1.1494 | 32000 | 0.0203        |
+| 1.1674 | 32500 | 0.02          |
+| 1.1853 | 33000 | 0.0184        |
+| 1.2033 | 33500 | 0.0181        |
+| 1.2213 | 34000 | 0.0195        |
+| 1.2392 | 34500 | 0.0186        |
+| 1.2572 | 35000 | 0.0184        |
+| 1.2751 | 35500 | 0.0184        |
+| 1.2931 | 36000 | 0.0194        |
+| 1.3111 | 36500 | 0.0191        |
+| 1.3290 | 37000 | 0.0183        |
+| 1.3470 | 37500 | 0.0179        |
+| 1.3649 | 38000 | 0.0179        |
+| 1.3829 | 38500 | 0.0178        |
+| 1.4009 | 39000 | 0.018         |
+| 1.4188 | 39500 | 0.0182        |
+| 1.4368 | 40000 | 0.0188        |
+| 1.4547 | 40500 | 0.0172        |
+| 1.4727 | 41000 | 0.0169        |
+| 1.4907 | 41500 | 0.0173        |
+| 1.5086 | 42000 | 0.0166        |
+| 1.5266 | 42500 | 0.0157        |
+| 1.5445 | 43000 | 0.0168        |
+| 1.5625 | 43500 | 0.0158        |
+| 1.5805 | 44000 | 0.016         |
+| 1.5984 | 44500 | 0.0166        |
+| 1.6164 | 45000 | 0.0168        |
+| 1.6343 | 45500 | 0.0162        |
+| 1.6523 | 46000 | 0.0153        |
+| 1.6703 | 46500 | 0.0149        |
+| 1.6882 | 47000 | 0.0158        |
+| 1.7062 | 47500 | 0.0152        |
+| 1.7241 | 48000 | 0.0147        |
+| 1.7421 | 48500 | 0.0146        |
+| 1.7601 | 49000 | 0.0145        |
+| 1.7780 | 49500 | 0.0148        |
+| 1.7960 | 50000 | 0.015         |
+| 1.8139 | 50500 | 0.0145        |
+| 1.8319 | 51000 | 0.0142        |
+| 1.8499 | 51500 | 0.014         |
+| 1.8678 | 52000 | 0.0139        |
+| 1.8858 | 52500 | 0.0133        |
+| 1.9037 | 53000 | 0.0135        |
+| 1.9217 | 53500 | 0.0131        |
+| 1.9397 | 54000 | 0.0134        |
+| 1.9576 | 54500 | 0.013         |
+| 1.9756 | 55000 | 0.0132        |
+| 1.9935 | 55500 | 0.0122        |
+| 2.0115 | 56000 | 0.0089        |
+| 2.0295 | 56500 | 0.0061        |
+| 2.0474 | 57000 | 0.0061        |
+| 2.0654 | 57500 | 0.006         |
+| 2.0833 | 58000 | 0.0062        |
+| 2.1013 | 58500 | 0.0058        |
+| 2.1193 | 59000 | 0.0059        |
+| 2.1372 | 59500 | 0.0059        |
+| 2.1552 | 60000 | 0.0059        |
+| 2.1731 | 60500 | 0.0058        |
+| 2.1911 | 61000 | 0.0059        |
+| 2.2091 | 61500 | 0.0058        |
+| 2.2270 | 62000 | 0.0059        |
+| 2.2450 | 62500 | 0.0058        |
+| 2.2629 | 63000 | 0.0057        |
+| 2.2809 | 63500 | 0.0055        |
+| 2.2989 | 64000 | 0.0056        |
+| 2.3168 | 64500 | 0.0056        |
+| 2.3348 | 65000 | 0.0056        |
+| 2.3527 | 65500 | 0.0057        |
+| 2.3707 | 66000 | 0.0055        |
+| 2.3886 | 66500 | 0.0056        |
+| 2.4066 | 67000 | 0.0054        |
+| 2.4246 | 67500 | 0.0055        |
+| 2.4425 | 68000 | 0.0052        |
+| 2.4605 | 68500 | 0.0053        |
+| 2.4784 | 69000 | 0.0052        |
+| 2.4964 | 69500 | 0.0053        |
+| 2.5144 | 70000 | 0.0052        |
+| 2.5323 | 70500 | 0.0052        |
+| 2.5503 | 71000 | 0.0051        |
+| 2.5682 | 71500 | 0.0049        |
+| 2.5862 | 72000 | 0.005         |
+| 2.6042 | 72500 | 0.0047        |
+| 2.6221 | 73000 | 0.0048        |
+| 2.6401 | 73500 | 0.0047        |
+| 2.6580 | 74000 | 0.0048        |
+| 2.6760 | 74500 | 0.0048        |
+| 2.6940 | 75000 | 0.0048        |
+| 2.7119 | 75500 | 0.0047        |
+| 2.7299 | 76000 | 0.0047        |
+| 2.7478 | 76500 | 0.0046        |
+| 2.7658 | 77000 | 0.0046        |
+| 2.7838 | 77500 | 0.0044        |
+| 2.8017 | 78000 | 0.0046        |
+| 2.8197 | 78500 | 0.0047        |
+| 2.8376 | 79000 | 0.0045        |
+| 2.8556 | 79500 | 0.0043        |
+| 2.8736 | 80000 | 0.0045        |
+| 2.8915 | 80500 | 0.0044        |
+| 2.9095 | 81000 | 0.0045        |
+| 2.9274 | 81500 | 0.0045        |
+| 2.9454 | 82000 | 0.0043        |
+| 2.9634 | 82500 | 0.0042        |
+| 2.9813 | 83000 | 0.0041        |
+| 2.9993 | 83500 | 0.0044        |
+
+</details>
+
+### Framework Versions
+- Python: 3.11.13
+- Sentence Transformers: 4.1.0
+- Transformers: 4.53.0
+- PyTorch: 2.6.0+cu124
+- Accelerate: 1.8.1
+- Datasets: 3.6.0
+- Tokenizers: 0.21.2
+
+## 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": "4.53.0",
+  "type_vocab_size": 2,
+  "vocab_size": 50005
+}

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "4.1.0",
+    "transformers": "4.53.0",
+    "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:dfa9e6096d18fe6a5dff8337873d833e0e6a59c836dee08b57683f885c9270a0
+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 +1,78 @@
+{
+  "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]",
+  "max_length": 256,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "stride": 0,
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
+}