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 +1,577 @@
+---
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- dataset_size:2732400
+- loss:MultipleNegativesRankingLoss
+base_model: Shuu12121/CodeModernBERT-Owl-2.0
+widget:
+- source_sentence: 'put string value.
+
+
+    @param body _.
+
+    @throws IllegalArgumentException thrown if parameters fail the validation.
+
+    @throws HttpResponseException thrown if the service returns an error.
+
+    @throws RuntimeException all other wrapped checked exceptions if the request fails
+    to be sent.'
+  sentences:
+  - "func ComposeSSHCloneURL(doer *user_model.User, ownerName, repoName string) string\
+    \ {\n\tsshUser := setting.SSH.User\n\tsshDomain := setting.SSH.Domain\n\n\tif\
+    \ sshUser == \"(DOER_USERNAME)\" {\n\t\t// Some users use SSH reverse-proxy and\
+    \ need to use the current signed-in username as the SSH user\n\t\t// to make the\
+    \ SSH reverse-proxy could prepare the user's public keys ahead.\n\t\t// For most\
+    \ cases we have the correct \"doer\", then use it as the SSH user.\n\t\t// If\
+    \ we can't get the doer, then use the built-in SSH user.\n\t\tif doer != nil {\n\
+    \t\t\tsshUser = doer.Name\n\t\t} else {\n\t\t\tsshUser = setting.SSH.BuiltinServerUser\n\
+    \t\t}\n\t}\n\n\t// non-standard port, it must use full URI\n\tif setting.SSH.Port\
+    \ != 22 {\n\t\tsshHost := net.JoinHostPort(sshDomain, strconv.Itoa(setting.SSH.Port))\n\
+    \t\treturn fmt.Sprintf(\"ssh://%s@%s/%s/%s.git\", sshUser, sshHost, url.PathEscape(ownerName),\
+    \ url.PathEscape(repoName))\n\t}\n\n\t// for standard port, it can use a shorter\
+    \ URI (without the port)\n\tsshHost := sshDomain\n\tif ip := net.ParseIP(sshHost);\
+    \ ip != nil && ip.To4() == nil {\n\t\tsshHost = \"[\" + sshHost + \"]\" // for\
+    \ IPv6 address, wrap it with brackets\n\t}\n\tif setting.Repository.UseCompatSSHURI\
+    \ {\n\t\treturn fmt.Sprintf(\"ssh://%s@%s/%s/%s.git\", sshUser, sshHost, url.PathEscape(ownerName),\
+    \ url.PathEscape(repoName))\n\t}\n\treturn fmt.Sprintf(\"%s@%s:%s/%s.git\", sshUser,\
+    \ sshHost, url.PathEscape(ownerName), url.PathEscape(repoName))\n}"
+  - "@java.lang.Override\n  public boolean hasFieldExtractionMetadata() {\n    return\
+    \ ((bitField0_ & 0x00000001) != 0);\n  }"
+  - "@Metadata(properties = { MetadataProperties.GENERATED })\n    @ServiceMethod(returns\
+    \ = ReturnType.SINGLE)\n    public void put(String body) {\n        this.serviceClient.put(body);\n\
+    \    }"
+- source_sentence: 'Optional. User specified ID for the notebook runtime.
+
+
+    Generated from protobuf field <code>string notebook_runtime_id = 4 [(.google.api.field_behavior)
+    = OPTIONAL];</code>
+
+    @return string'
+  sentences:
+  - "public function getNotebookRuntimeId()\n    {\n        return $this->notebook_runtime_id;\n\
+    \    }"
+  - "func (client *BlobContainersClient) BeginObjectLevelWorm(ctx context.Context,\
+    \ resourceGroupName string, accountName string, containerName string, options\
+    \ *BlobContainersClientBeginObjectLevelWormOptions) (*runtime.Poller[BlobContainersClientObjectLevelWormResponse],\
+    \ error) {\n\tif options == nil || options.ResumeToken == \"\" {\n\t\tresp, err\
+    \ := client.objectLevelWorm(ctx, resourceGroupName, accountName, containerName,\
+    \ options)\n\t\tif err != nil {\n\t\t\treturn nil, err\n\t\t}\n\t\tpoller, err\
+    \ := runtime.NewPoller(resp, client.internal.Pipeline(), &runtime.NewPollerOptions[BlobContainersClientObjectLevelWormResponse]{\n\
+    \t\t\tFinalStateVia: runtime.FinalStateViaLocation,\n\t\t\tTracer:        client.internal.Tracer(),\n\
+    \t\t})\n\t\treturn poller, err\n\t} else {\n\t\treturn runtime.NewPollerFromResumeToken(options.ResumeToken,\
+    \ client.internal.Pipeline(), &runtime.NewPollerFromResumeTokenOptions[BlobContainersClientObjectLevelWormResponse]{\n\
+    \t\t\tTracer: client.internal.Tracer(),\n\t\t})\n\t}\n}"
+  - "def version(self) -> Union[int, str]:\n        \n        if self._version is\
+    \ None:\n            self._version = self._get_next_version()\n        return\
+    \ self._version"
+- source_sentence: '<pre>
+
+    Output only. An email message received in reply to the case.
+
+    </pre>
+
+
+    <code>
+
+    .google.cloud.support.v2beta.EmailMessage email_message = 102 [(.google.api.field_behavior)
+    = OUTPUT_ONLY];
+
+    </code>
+
+
+    @return The emailMessage.'
+  sentences:
+  - "@java.lang.Override\n  public com.google.cloud.support.v2beta.EmailMessage getEmailMessage()\
+    \ {\n    if (eventObjectCase_ == 102) {\n      return (com.google.cloud.support.v2beta.EmailMessage)\
+    \ eventObject_;\n    }\n    return com.google.cloud.support.v2beta.EmailMessage.getDefaultInstance();\n\
+    \  }"
+  - "def df_isin(df, values):\n    \n    if is_list_like(values) and not isinstance(values,\
+    \ dict):\n        values = list(values)\n    elif not isinstance(\n        values,\
+    \ (SERIES_TYPE, DATAFRAME_TYPE, TENSOR_TYPE, INDEX_TYPE, dict)\n    ):\n     \
+    \   raise TypeError(\n            \"only list-like objects or dict are allowed\
+    \ to be passed to isin(), \"\n            f\"you passed a [{type(values)}]\"\n\
+    \        )\n    op = DataFrameIsin(values=values)\n    return op(df)"
+  - "public function getModelDeploymentMonitoringJobs()\n    {\n        return $this->model_deployment_monitoring_jobs;\n\
+    \    }"
+- source_sentence: Compute the maximum violation of KKT conditions.
+  sentences:
+  - "def with_url(self,raw_url: str) -> SearchesRequestBuilder:\n        \n      \
+    \  if raw_url is None:\n            raise TypeError(\"raw_url cannot be null.\"\
+    )\n        return SearchesRequestBuilder(self.request_adapter, raw_url)"
+  - "def get_subscription\n  # Create a client object. The client can be reused for\
+    \ multiple calls.\n  client = Google::Apps::Events::Subscriptions::V1::SubscriptionsService::Client.new\n\
+    \n  # Create a request. To set request fields, pass in keyword arguments.\n  request\
+    \ = Google::Apps::Events::Subscriptions::V1::GetSubscriptionRequest.new\n\n  #\
+    \ Call the get_subscription method.\n  result = client.get_subscription request\n\
+    \n  # The returned object is of type Google::Apps::Events::Subscriptions::V1::Subscription.\n\
+    \  p result\nend"
+  - "def compute_kkt_optimality(g, on_bound):\n    \n    g_kkt = g * on_bound\n  \
+    \  free_set = on_bound == 0\n    g_kkt[free_set] = np.abs(g[free_set])\n    return\
+    \ np.max(g_kkt)"
+- source_sentence: 'Creates a unary expression NEGATIVE
+
+
+    # Errors
+
+
+    This function errors when the argument''s type is not signed numeric'
+  sentences:
+  - "public function searchItemAction()\n    {\n        return $this->searchBase(\"\
+    ifgroupentry\", ['ifname', 'descr', 'members', 'sequence'], \"ifname\");\n   \
+    \ }"
+  - "pub fn poller(self) -> impl lro::Poller<(), crate::model::DeleteSitemapMetadata>\
+    \ {\n            type Operation =\n                lro::internal::Operation<wkt::Empty,\
+    \ crate::model::DeleteSitemapMetadata>;\n            let polling_error_policy\
+    \ = self.0.stub.get_polling_error_policy(&self.0.options);\n            let polling_backoff_policy\
+    \ = self.0.stub.get_polling_backoff_policy(&self.0.options);\n\n            let\
+    \ stub = self.0.stub.clone();\n            let mut options = self.0.options.clone();\n\
+    \            options.set_retry_policy(gax::retry_policy::NeverRetry);\n      \
+    \      let query = move |name| {\n                let stub = stub.clone();\n \
+    \               let options = options.clone();\n                async {\n    \
+    \                let op = GetOperation::new(stub)\n                        .set_name(name)\n\
+    \                        .with_options(options)\n                        .send()\n\
+    \                        .await?;\n                    Ok(Operation::new(op))\n\
+    \                }\n            };\n\n            let start = move || async {\n\
+    \                let op = self.send().await?;\n                Ok(Operation::new(op))\n\
+    \            };\n\n            lro::internal::new_unit_response_poller(\n    \
+    \            polling_error_policy,\n                polling_backoff_policy,\n\
+    \                start,\n                query,\n            )\n        }"
+  - "pub fn negative(\n    arg: Arc<dyn PhysicalExpr>,\n    input_schema: &Schema,\n\
+    ) -> Result<Arc<dyn PhysicalExpr>> {\n    let data_type = arg.data_type(input_schema)?;\n\
+    \    if !coercion::is_signed_numeric(&data_type) {\n        Err(DataFusionError::Internal(\n\
+    \            format!(\n                \"(- '{:?}') can't be evaluated because\
+    \ the expression's type is {:?}, not signed numeric\",\n                arg, data_type,\n\
+    \            ),\n        ))\n    } else {\n        Ok(Arc::new(NegativeExpr::new(arg)))\n\
+    \    }\n}"
+pipeline_tag: sentence-similarity
+library_name: sentence-transformers
+---
+
+# SentenceTransformer based on Shuu12121/CodeModernBERT-Owl-2.0
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [Shuu12121/CodeModernBERT-Owl-2.0](https://huggingface.co/Shuu12121/CodeModernBERT-Owl-2.0). 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-2.0](https://huggingface.co/Shuu12121/CodeModernBERT-Owl-2.0) <!-- at revision a6f43b644188b4e7fe211f38003c7742218607c0 -->
+- **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 = [
+    "Creates a unary expression NEGATIVE\n\n# Errors\n\nThis function errors when the argument's type is not signed numeric",
+    'pub fn negative(\n    arg: Arc<dyn PhysicalExpr>,\n    input_schema: &Schema,\n) -> Result<Arc<dyn PhysicalExpr>> {\n    let data_type = arg.data_type(input_schema)?;\n    if !coercion::is_signed_numeric(&data_type) {\n        Err(DataFusionError::Internal(\n            format!(\n                "(- \'{:?}\') can\'t be evaluated because the expression\'s type is {:?}, not signed numeric",\n                arg, data_type,\n            ),\n        ))\n    } else {\n        Ok(Arc::new(NegativeExpr::new(arg)))\n    }\n}',
+    'public function searchItemAction()\n    {\n        return $this->searchBase("ifgroupentry", [\'ifname\', \'descr\', \'members\', \'sequence\'], "ifname");\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: 2,732,400 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: 13 tokens</li><li>mean: 109.22 tokens</li><li>max: 1024 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 250.01 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>Prints the specified `pkg`.<br><br>If `is_main` is not set, nested package notation is used.</code> | <code>pub fn print_package(<br>        &mut self,<br>        resolve: &Resolve,<br>        pkg: PackageId,<br>        is_main: bool,<br>    ) -> Result<()> {<br>        let pkg = &resolve.packages[pkg];<br>        self.print_package_outer(pkg)?;<br><br>        if is_main {<br>            self.output.semicolon();<br>            self.output.newline();<br>        } else {<br>            self.output.indent_start();<br>        }<br><br>        for (name, id) in pkg.interfaces.iter() {<br>            self.print_interface_outer(resolve, *id, name)?;<br>            self.output.indent_start();<br>            self.print_interface(resolve, *id)?;<br>            self.output.indent_end();<br>            if is_main {<br>                self.output.newline();<br>            }<br>        }<br><br>        for (name, id) in pkg.worlds.iter() {<br>            self.print_docs(&resolve.worlds[*id].docs);<br>            self.print_stability(&resolve.worlds[*id].stability);<br>            self.output.keyword("world");<br>            self.output.str(" ");<br>            self.print_name_type(name, TypeKind:...</code> | <code>1.0</code> |
+  | <code><p>An alternative descriptive name for the user.</p></code>                                         | <code>pub fn nick_name(mut self, input: impl ::std::convert::Into<::std::string::String>) -> Self {<br>        self.nick_name = ::std::option::Option::Some(input.into());<br>        self<br>    }</code>                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                            | <code>1.0</code> |
+  | <code><p>Indicates whether the match is case sensitive.</p></code>                                        | <code>pub fn case_sensitive(mut self, input: bool) -> Self {<br>        self.case_sensitive = ::std::option::Option::Some(input);<br>        self<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`: 150
+- `per_device_eval_batch_size`: 150
+- `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`: 150
+- `per_device_eval_batch_size`: 150
+- `per_gpu_train_batch_size`: None
+- `per_gpu_eval_batch_size`: None
+- `gradient_accumulation_steps`: 1
+- `eval_accumulation_steps`: None
+- `torch_empty_cache_steps`: None
+- `learning_rate`: 5e-05
+- `weight_decay`: 0.0
+- `adam_beta1`: 0.9
+- `adam_beta2`: 0.999
+- `adam_epsilon`: 1e-08
+- `max_grad_norm`: 1
+- `num_train_epochs`: 3
+- `max_steps`: -1
+- `lr_scheduler_type`: linear
+- `lr_scheduler_kwargs`: {}
+- `warmup_ratio`: 0.0
+- `warmup_steps`: 0
+- `log_level`: passive
+- `log_level_replica`: warning
+- `log_on_each_node`: True
+- `logging_nan_inf_filter`: True
+- `save_safetensors`: True
+- `save_on_each_node`: False
+- `save_only_model`: False
+- `restore_callback_states_from_checkpoint`: False
+- `no_cuda`: False
+- `use_cpu`: False
+- `use_mps_device`: False
+- `seed`: 42
+- `data_seed`: None
+- `jit_mode_eval`: False
+- `use_ipex`: False
+- `bf16`: False
+- `fp16`: True
+- `fp16_opt_level`: O1
+- `half_precision_backend`: auto
+- `bf16_full_eval`: False
+- `fp16_full_eval`: False
+- `tf32`: None
+- `local_rank`: 0
+- `ddp_backend`: None
+- `tpu_num_cores`: None
+- `tpu_metrics_debug`: False
+- `debug`: []
+- `dataloader_drop_last`: False
+- `dataloader_num_workers`: 0
+- `dataloader_prefetch_factor`: None
+- `past_index`: -1
+- `disable_tqdm`: False
+- `remove_unused_columns`: True
+- `label_names`: None
+- `load_best_model_at_end`: False
+- `ignore_data_skip`: False
+- `fsdp`: []
+- `fsdp_min_num_params`: 0
+- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
+- `fsdp_transformer_layer_cls_to_wrap`: None
+- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
+- `deepspeed`: None
+- `label_smoothing_factor`: 0.0
+- `optim`: adamw_torch
+- `optim_args`: None
+- `adafactor`: False
+- `group_by_length`: False
+- `length_column_name`: length
+- `ddp_find_unused_parameters`: None
+- `ddp_bucket_cap_mb`: None
+- `ddp_broadcast_buffers`: False
+- `dataloader_pin_memory`: True
+- `dataloader_persistent_workers`: False
+- `skip_memory_metrics`: True
+- `use_legacy_prediction_loop`: False
+- `push_to_hub`: False
+- `resume_from_checkpoint`: None
+- `hub_model_id`: None
+- `hub_strategy`: every_save
+- `hub_private_repo`: None
+- `hub_always_push`: False
+- `gradient_checkpointing`: False
+- `gradient_checkpointing_kwargs`: None
+- `include_inputs_for_metrics`: False
+- `include_for_metrics`: []
+- `eval_do_concat_batches`: True
+- `fp16_backend`: auto
+- `push_to_hub_model_id`: None
+- `push_to_hub_organization`: None
+- `mp_parameters`: 
+- `auto_find_batch_size`: False
+- `full_determinism`: False
+- `torchdynamo`: None
+- `ray_scope`: last
+- `ddp_timeout`: 1800
+- `torch_compile`: False
+- `torch_compile_backend`: None
+- `torch_compile_mode`: None
+- `include_tokens_per_second`: False
+- `include_num_input_tokens_seen`: False
+- `neftune_noise_alpha`: None
+- `optim_target_modules`: None
+- `batch_eval_metrics`: False
+- `eval_on_start`: False
+- `use_liger_kernel`: False
+- `eval_use_gather_object`: False
+- `average_tokens_across_devices`: False
+- `prompts`: None
+- `batch_sampler`: batch_sampler
+- `multi_dataset_batch_sampler`: round_robin
+
+</details>
+
+### Training Logs
+<details><summary>Click to expand</summary>
+
+| Epoch  | Step  | Training Loss |
+|:------:|:-----:|:-------------:|
+| 0.0274 | 500   | 0.8232        |
+| 0.0549 | 1000  | 0.1248        |
+| 0.0823 | 1500  | 0.1102        |
+| 0.1098 | 2000  | 0.1008        |
+| 0.1372 | 2500  | 0.0962        |
+| 0.1647 | 3000  | 0.0928        |
+| 0.1921 | 3500  | 0.0878        |
+| 0.2196 | 4000  | 0.0827        |
+| 0.2470 | 4500  | 0.078         |
+| 0.2745 | 5000  | 0.0763        |
+| 0.3019 | 5500  | 0.075         |
+| 0.3294 | 6000  | 0.0716        |
+| 0.3568 | 6500  | 0.0691        |
+| 0.3843 | 7000  | 0.0673        |
+| 0.4117 | 7500  | 0.065         |
+| 0.4392 | 8000  | 0.0668        |
+| 0.4666 | 8500  | 0.0609        |
+| 0.4941 | 9000  | 0.0613        |
+| 0.5215 | 9500  | 0.0596        |
+| 0.5490 | 10000 | 0.0596        |
+| 0.5764 | 10500 | 0.058         |
+| 0.6039 | 11000 | 0.0527        |
+| 0.6313 | 11500 | 0.0521        |
+| 0.6588 | 12000 | 0.0521        |
+| 0.6862 | 12500 | 0.049         |
+| 0.7137 | 13000 | 0.0481        |
+| 0.7411 | 13500 | 0.0484        |
+| 0.7686 | 14000 | 0.049         |
+| 0.7960 | 14500 | 0.0482        |
+| 0.8235 | 15000 | 0.045         |
+| 0.8509 | 15500 | 0.0423        |
+| 0.8783 | 16000 | 0.0425        |
+| 0.9058 | 16500 | 0.04          |
+| 0.9332 | 17000 | 0.0406        |
+| 0.9607 | 17500 | 0.0374        |
+| 0.9881 | 18000 | 0.038         |
+| 1.0156 | 18500 | 0.0257        |
+| 1.0430 | 19000 | 0.0154        |
+| 1.0705 | 19500 | 0.015         |
+| 1.0979 | 20000 | 0.0157        |
+| 1.1254 | 20500 | 0.0144        |
+| 1.1528 | 21000 | 0.0148        |
+| 1.1803 | 21500 | 0.0152        |
+| 1.2077 | 22000 | 0.0154        |
+| 1.2352 | 22500 | 0.0161        |
+| 1.2626 | 23000 | 0.0155        |
+| 1.2901 | 23500 | 0.0148        |
+| 1.3175 | 24000 | 0.0152        |
+| 1.3450 | 24500 | 0.015         |
+| 1.3724 | 25000 | 0.0148        |
+| 1.3999 | 25500 | 0.0151        |
+| 1.4273 | 26000 | 0.0144        |
+| 1.4548 | 26500 | 0.0147        |
+| 1.4822 | 27000 | 0.0143        |
+| 1.5097 | 27500 | 0.0148        |
+| 1.5371 | 28000 | 0.0147        |
+| 1.5646 | 28500 | 0.0145        |
+| 1.5920 | 29000 | 0.0137        |
+| 1.6195 | 29500 | 0.0134        |
+| 1.6469 | 30000 | 0.0137        |
+| 1.6744 | 30500 | 0.0133        |
+| 1.7018 | 31000 | 0.0137        |
+| 1.7292 | 31500 | 0.0132        |
+| 1.7567 | 32000 | 0.0132        |
+| 1.7841 | 32500 | 0.0124        |
+| 1.8116 | 33000 | 0.0133        |
+| 1.8390 | 33500 | 0.0118        |
+| 1.8665 | 34000 | 0.0122        |
+| 1.8939 | 34500 | 0.0114        |
+| 1.9214 | 35000 | 0.0116        |
+| 1.9488 | 35500 | 0.0113        |
+| 1.9763 | 36000 | 0.0115        |
+| 2.0037 | 36500 | 0.0105        |
+| 2.0312 | 37000 | 0.0056        |
+| 2.0586 | 37500 | 0.0056        |
+| 2.0861 | 38000 | 0.0051        |
+| 2.1135 | 38500 | 0.0053        |
+| 2.1410 | 39000 | 0.0054        |
+| 2.1684 | 39500 | 0.0052        |
+| 2.1959 | 40000 | 0.0053        |
+| 2.2233 | 40500 | 0.0054        |
+| 2.2508 | 41000 | 0.0051        |
+| 2.2782 | 41500 | 0.0052        |
+| 2.3057 | 42000 | 0.0052        |
+| 2.3331 | 42500 | 0.0046        |
+| 2.3606 | 43000 | 0.0048        |
+| 2.3880 | 43500 | 0.0051        |
+| 2.4155 | 44000 | 0.0049        |
+| 2.4429 | 44500 | 0.0047        |
+| 2.4704 | 45000 | 0.0047        |
+| 2.4978 | 45500 | 0.0048        |
+| 2.5253 | 46000 | 0.005         |
+| 2.5527 | 46500 | 0.0049        |
+| 2.5801 | 47000 | 0.0047        |
+| 2.6076 | 47500 | 0.0046        |
+| 2.6350 | 48000 | 0.0048        |
+| 2.6625 | 48500 | 0.0045        |
+| 2.6899 | 49000 | 0.0043        |
+| 2.7174 | 49500 | 0.0047        |
+| 2.7448 | 50000 | 0.0045        |
+| 2.7723 | 50500 | 0.0046        |
+| 2.7997 | 51000 | 0.0046        |
+| 2.8272 | 51500 | 0.0044        |
+| 2.8546 | 52000 | 0.0042        |
+| 2.8821 | 52500 | 0.0045        |
+| 2.9095 | 53000 | 0.0045        |
+| 2.9370 | 53500 | 0.0043        |
+| 2.9644 | 54000 | 0.0044        |
+| 2.9919 | 54500 | 0.0043        |
+
+</details>
+
+### Framework Versions
+- Python: 3.11.12
+- Sentence Transformers: 4.1.0
+- Transformers: 4.52.3
+- PyTorch: 2.6.0+cu124
+- Accelerate: 1.6.0
+- Datasets: 3.6.0
+- Tokenizers: 0.21.1
+
+## Citation
+
+### BibTeX
+
+#### Sentence Transformers
+```bibtex
+@inproceedings{reimers-2019-sentence-bert,
+    title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
+    author = "Reimers, Nils and Gurevych, Iryna",
+    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
+    month = "11",
+    year = "2019",
+    publisher = "Association for Computational Linguistics",
+    url = "https://arxiv.org/abs/1908.10084",
+}
+```
+
+#### MultipleNegativesRankingLoss
+```bibtex
+@misc{henderson2017efficient,
+    title={Efficient Natural Language Response Suggestion for Smart Reply},
+    author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil},
+    year={2017},
+    eprint={1705.00652},
+    archivePrefix={arXiv},
+    primaryClass={cs.CL}
+}
+```
+
+<!--
+## Glossary
+
+*Clearly define terms in order to be accessible across audiences.*
+-->
+
+<!--
+## Model Card Authors
+
+*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
+-->
+
+<!--
+## Model Card Contact
+
+*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
+-->

added_tokens.json

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

config.json

@@ -0,0 +1,48 @@
+{
+  "architectures": [
+    "ModernBertModel"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 50000,
+  "classifier_activation": "gelu",
+  "classifier_bias": false,
+  "classifier_dropout": 0.0,
+  "classifier_pooling": "cls",
+  "cls_token_id": 50281,
+  "decoder_bias": true,
+  "deterministic_flash_attn": false,
+  "embedding_dropout": 0.0,
+  "eos_token_id": 50001,
+  "global_attn_every_n_layers": 3,
+  "global_rope_theta": 160000.0,
+  "hidden_activation": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_cutoff_factor": 2.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "local_attention": 128,
+  "local_attention_rope_theta": 10000,
+  "local_attention_window": 128,
+  "local_rope_theta": 10000.0,
+  "max_position_embeddings": 8192,
+  "mlp_bias": false,
+  "mlp_dropout": 0.0,
+  "model_type": "modernbert",
+  "norm_bias": false,
+  "norm_eps": 1e-05,
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "repad_logits_with_grad": false,
+  "rope_theta": 160000,
+  "sep_token_id": 50282,
+  "sparse_pred_ignore_index": -100,
+  "sparse_prediction": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.52.3",
+  "type_vocab_size": 2,
+  "vocab_size": 50004
+}

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "4.1.0",
+    "transformers": "4.52.3",
+    "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:f8d709d4b2dfc3f5debe0bde61197d37aee5b0ce909442ad9cb3649403b47f8a
+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": 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]"
+}