--- tags: - sentence-transformers - sentence-similarity - feature-extraction - dense - generated_from_trainer - dataset_size:39122 - loss:MultipleNegativesRankingLoss base_model: google/embeddinggemma-300m widget: - source_sentence: 组件即将出现时加载收藏商家数据 sentences: - "static async delete(key: string, preferenceName: string = defaultPreferenceName)\ \ {\n let preferences = await this.getPreferences(preferenceName)\n return\ \ await preferences.delete(key)\n }" - "async aboutToAppear(): Promise {\n await this.loadFavoriteMerchants();\n\ \ }" - 'Copyright (c) 2022 Huawei Device Co., Ltd. Licensed under the Apache License,Version 2.0 (the "License"); you may not use this file except in compliance with the License. You may obtain a copy of the License at http://www.apache.org/licenses/LICENSE-2.0 Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the specific language governing permissions and limitations under the License.' - source_sentence: "@Builder\n buildBottomNavigation() {\n Tabs({ index: this.currentTabIndex\ \ }) {\n TabContent() {\n // 首页内容在主区域显示\n }\n .tabBar(this.buildTabBarItem('首页',\ \ $r('app.media.ic_home'), 0))\n \n TabContent() {\n // 联系人内容在主区域显示\n\ \ }\n .tabBar(this.buildTabBarItem('联系人', $r('app.media.ic_contacts'),\ \ 1))\n \n TabContent() {\n // 日历内容在主区域显示\n }\n .tabBar(this.buildTabBarItem('日历',\ \ $r('app.media.ic_calendar'), 2))\n \n TabContent() {\n // 祝福语内容在主区域显示\n\ \ }\n .tabBar(this.buildTabBarItem('祝福语', $r('app.media.ic_greetings'),\ \ 3))\n \n TabContent() {\n // 设置内容在主区域显示\n }\n .tabBar(this.buildTabBarItem('设置',\ \ $r('app.media.ic_settings'), 4))\n }\n .onChange((index: number) => {\n\ \ this.onTabChange(index);\n })\n .barPosition(BarPosition.End)\n \ \ .barBackgroundColor('#ffffff')\n .barHeight(60)\n }" sentences: - 定义List的builder方法 - 错误相关常量 - 构建底部导航栏 - source_sentence: 插入数据库 sentences: - "static dateToTimestamp(date: Date): number {\n return date.getTime();\n }" - "public async insertData(context: common.Context, Contact: Contact): Promise\ \ {\n logger.info(TAG, 'insert begin');\n if (!context) {\n logger.info(TAG,\ \ 'context is null or undefined');\n }\n\n const predicates = new rdb.RdbPredicates(TABLE_NAME);\n\ \ if (predicates === null || predicates === undefined) {\n logger.info(TAG,\ \ 'predicates is null or undefined');\n }\n\n this.rdbStore = await rdb.getRdbStore(context,\ \ STORE_CONFIG);\n\n let value1 = Contact.name;\n let value2 = Contact.phone;\n\ \ let value3 = Contact.email;\n let value4 = Contact.address;\n let value5\ \ = Contact.avatar;\n let value6 = Contact.category;\n\n const valueBucket:\ \ ValuesBucket = {\n 'name': value1,\n 'phone': value2,\n 'email':\ \ value3,\n 'address': value4,\n 'avatar': value5,\n 'category':\ \ value6\n }\n\n if (this.rdbStore != undefined) {\n this.rdbStore.insert(TABLE_NAME,\ \ valueBucket, rdb.ConflictResolution.ON_CONFLICT_REPLACE,\n (err: BusinessError,\ \ rows: number) => {\n if (err) {\n logger.info(TAG, \"Insert\ \ failed, err: \" + err)\n return\n }\n logger.info(TAG,\ \ `insert done:${rows}`);\n promptAction.showToast({\n message:\ \ $r('app.string.operate_rdb_in_taskpool_add_prompt_text', Contact.name),\n \ \ duration: CommonConstants.PROMPT_DURATION_TIME\n });\n \ \ })\n }\n }" - 日历日期的代办事项 - source_sentence: "private recordOperation(\n type: 'create' | 'update' | 'delete'\ \ | 'complete' | 'cancel',\n todoId: string,\n changes?: ChangeRecord,\n\ \ description?: string\n ): void {\n try {\n const record: TodoOperationRecord\ \ = {\n id: this.generateId(),\n type,\n todoId,\n \ \ changes,\n timestamp: new Date().toISOString(),\n description\n\ \ };\n\n this.operationRecords.unshift(record);\n \n // 只保留最近100条记录\n\ \ if (this.operationRecords.length > 100) {\n this.operationRecords\ \ = this.operationRecords.slice(0, 100);\n }\n\n hilog.info(LogConstants.DOMAIN_APP,\ \ LogConstants.TAG_APP, `Recorded operation: ${type} for todo ${todoId}`);\n \ \ } catch (error) {\n hilog.error(LogConstants.DOMAIN_APP, LogConstants.TAG_APP,\ \ `Failed to record operation: ${error}`);\n }\n }" sentences: - 记录操作 - "export interface DataConfig {\n autoBackup: AutoBackupConfig;\n dataRetention:\ \ DataRetentionConfig;\n syncConfig: SyncConfig;\n}" - "@Builder\n ExamSwitchModule() {\n Row() {\n Text('切换题库：')\n .fontSize(14)\n\ \ Text( this.guideService.guideData.licenseType !== undefined?licenseTypeName[this.guideService.guideData.licenseType]:'')\n\ \ .fontSize(14)\n .fontColor('#64BB5C')\n Image($r('app.media.right_triangle'))\n\ \ .width(16)\n .height(16)\n .fillColor('rgba(0,0,0,0.9)')\n\ \ }\n .width('100%')\n .justifyContent(FlexAlign.Start)\n .onClick(()\ \ => {\n this.vm.navStack.pushPathByName('guidePage', true)\n })\n }" - source_sentence: 'resize(size: number): void;' sentences: - "Resize the bitVector's length.\n\n@param { number } size - The new size for bitVector.\ \ If count is greater than the current size of bitVector,\nthe additional bit\ \ elements are set to 0.\n@throws { BusinessError } 401 - Parameter error. Possible\ \ causes:\n1.Mandatory parameters are left unspecified.\n2.Incorrect parameter\ \ types.\n@throws { BusinessError } 10200011 - The resize method cannot be bound.\n\ @throws { BusinessError } 10200201 - Concurrent modification error.\n@syscap SystemCapability.Utils.Lang\n\ @atomicservice\n@since 12\n \nResize the bitVector's length.\n\n@param { number\ \ } size - The new size for bitVector. If count is greater than the current size\ \ of bitVector,\nthe additional bit elements are set to 0.\n@throws { BusinessError\ \ } 401 - Parameter error. Possible causes:\n1.Mandatory parameters are left unspecified.\n\ 2.Incorrect parameter types.\n@throws { BusinessError } 10200011 - The resize\ \ method cannot be bound.\n@throws { BusinessError } 10200201 - Concurrent modification\ \ error.\n@syscap SystemCapability.Utils.Lang\n@crossplatform\n@atomicservice\n\ @since 18" - "makeNode(uiContext: UIContext): FrameNode {\n this.rootNode = new FrameNode(uiContext);\n\ \ if (this.rootNode !== null) {\n this.rootRenderNode = this.rootNode.getRenderNode();\n\ \ }\n return this.rootNode;\n }" - "export interface OnlineLunarYear {\n year: number;\n zodiac: string;\n ganzhi:\ \ string;\n leapMonth: number;\n isLeapYear: boolean;\n leapMonthDays?: number;\n\ \ solarTerms: SolarTermInfo[];\n festivals: LunarFestival[];\n}" pipeline_tag: sentence-similarity library_name: sentence-transformers --- # SentenceTransformer based on google/embeddinggemma-300m This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [google/embeddinggemma-300m](https://huggingface.co/google/embeddinggemma-300m). 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:** [google/embeddinggemma-300m](https://huggingface.co/google/embeddinggemma-300m) - **Maximum Sequence Length:** 512 tokens - **Output Dimensionality:** 768 dimensions - **Similarity Function:** Cosine Similarity ### Model Sources - **Documentation:** [Sentence Transformers Documentation](https://sbert.net) - **Repository:** [Sentence Transformers on GitHub](https://github.com/huggingface/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': 512, 'do_lower_case': False, 'architecture': 'Gemma3TextModel'}) (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True}) (2): Dense({'in_features': 768, 'out_features': 3072, 'bias': False, 'activation_function': 'torch.nn.modules.linear.Identity'}) (3): Dense({'in_features': 3072, 'out_features': 768, 'bias': False, 'activation_function': 'torch.nn.modules.linear.Identity'}) (4): Normalize() ) ``` ## 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("hreyulog/embedinggemma_arkts") # Run inference queries = [ "Transform an array of points with all matrices. VERY IMPORTANT: Keep\nmatrix order \"value-touch-offset\" when transforming.\n\n@param pts", ] documents = [ "public pointValuesToPixel(pts: number[]) {\n this.mMatrixValueToPx.mapPoints(pts);\n this.mViewPortHandler.getMatrixTouch().mapPoints(pts);\n this.mMatrixOffset.mapPoints(pts);\n }", 'makeNode(uiContext: UIContext): FrameNode {\n this.rootNode = new FrameNode(uiContext);\n if (this.rootNode !== null) {\n this.rootRenderNode = this.rootNode.getRenderNode();\n }\n return this.rootNode;\n }', 'export interface OnlineLunarYear {\n year: number;\n zodiac: string;\n ganzhi: string;\n leapMonth: number;\n isLeapYear: boolean;\n leapMonthDays?: number;\n solarTerms: SolarTermInfo[];\n festivals: LunarFestival[];\n}', ] query_embeddings = model.encode_query(queries) document_embeddings = model.encode_document(documents) print(query_embeddings.shape, document_embeddings.shape) # [1, 768] [3, 768] # Get the similarity scores for the embeddings similarities = model.similarity(query_embeddings, document_embeddings) print(similarities) # tensor([[ 0.8923, 0.0264, -0.0212]]) ``` ## Evaluation Results On arkts-code-docstring dataset split test | Model | Params | MRR | NDCG@5 | Recall@1 | Recall@5 | |------|--------|-----|--------|----------|----------| | **embedinggemma_arkts** | 308M | **0.7788** | **0.8034** | **0.7142** | **0.8769** | | QWEN3-Embedding-0.6B | 596M | 0.6776 | 0.7015 | 0.6141 | 0.7723 | | embeddinggemma-300m | 308M | 0.6399 | 0.6654 | 0.5740 | 0.7416 | | BGE-M3 | 567M | 0.5283 | 0.5603 | 0.4464 | 0.6558 | | BGE-base-zh-v1.5 | 110M | 0.3598 | 0.3903 | 0.2841 | 0.4816 | | BGE-base-en-v1.5 | 110M | 0.3439 | 0.3637 | 0.2935 | 0.4227 | | E5-base-v2 | 110M | 0.3073 | 0.3261 | 0.2596 | 0.3823 | | BM25 (jieba) | – | 0.2043 | 0.2204 | 0.1643 | 0.2690 | ## Training Details ### Training Dataset Dataset: [hreyulog/arkts-code-docstring](https://huggingface.co/datasets/hreyulog/arkts-code-docstring) * Size: 39,122 training samples * Columns: sentence_0 and sentence_1 * Approximate statistics based on the first 1000 samples: | | sentence_0 | sentence_1 | |:--------|:-----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------| | type | string | string | | details | | | * Samples: | sentence_0 | sentence_1 | |:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| | 移除登录状态监听 | public removeLoginStateListener(listener: (isLoggedIn: boolean) => void) {\n const index = this.loginStateListeners.indexOf(listener);\n if (index !== -1) {\n this.loginStateListeners.splice(index, 1);\n }\n } | | PUT请求 | static put(url: string, data?: Object, config: RequestConfig = {}): Promise> {
const putConfig: RequestConfig = {
method: http.RequestMethod.PUT,
headers: config.headers,
timeout: config.timeout,
data: data
};
return HttpUtil.request(url, putConfig);
} | | Transform an array of points with all matrices. VERY IMPORTANT: Keep\nmatrix order \"value-touch-offset\" when transforming.\n\n@param pts | public pointValuesToPixel(pts: number[]) {\n this.mMatrixValueToPx.mapPoints(pts);\n this.mViewPortHandler.getMatrixTouch().mapPoints(pts);\n this.mMatrixOffset.mapPoints(pts);\n } | * Loss: [MultipleNegativesRankingLoss](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters: ```json { "scale": 20.0, "similarity_fct": "cos_sim", "gather_across_devices": false } ``` ### Training Hyperparameters #### Non-Default Hyperparameters - `per_device_train_batch_size`: 32 - `per_device_eval_batch_size`: 32 - `num_train_epochs`: 2 - `multi_dataset_batch_sampler`: round_robin #### All Hyperparameters
Click to expand - `do_predict`: False - `eval_strategy`: no - `prediction_loss_only`: True - `per_device_train_batch_size`: 32 - `per_device_eval_batch_size`: 32 - `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`: 2 - `max_steps`: -1 - `lr_scheduler_type`: linear - `lr_scheduler_kwargs`: None - `warmup_ratio`: None - `warmup_steps`: 0 - `log_level`: passive - `log_level_replica`: warning - `log_on_each_node`: True - `logging_nan_inf_filter`: True - `enable_jit_checkpoint`: False - `save_on_each_node`: False - `save_only_model`: False - `restore_callback_states_from_checkpoint`: False - `use_cpu`: False - `seed`: 42 - `data_seed`: None - `bf16`: False - `fp16`: False - `bf16_full_eval`: False - `fp16_full_eval`: False - `tf32`: None - `local_rank`: -1 - `ddp_backend`: None - `debug`: [] - `dataloader_drop_last`: False - `dataloader_num_workers`: 0 - `dataloader_prefetch_factor`: None - `disable_tqdm`: False - `remove_unused_columns`: True - `label_names`: None - `load_best_model_at_end`: False - `ignore_data_skip`: False - `fsdp`: [] - `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False} - `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None} - `parallelism_config`: None - `deepspeed`: None - `label_smoothing_factor`: 0.0 - `optim`: adamw_torch_fused - `optim_args`: None - `group_by_length`: False - `length_column_name`: length - `project`: huggingface - `trackio_space_id`: trackio - `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 - `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_for_metrics`: [] - `eval_do_concat_batches`: True - `auto_find_batch_size`: False - `full_determinism`: False - `ddp_timeout`: 1800 - `torch_compile`: False - `torch_compile_backend`: None - `torch_compile_mode`: None - `include_num_input_tokens_seen`: no - `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`: True - `use_cache`: False - `prompts`: None - `batch_sampler`: batch_sampler - `multi_dataset_batch_sampler`: round_robin - `router_mapping`: {} - `learning_rate_mapping`: {}
### Training Logs | Epoch | Step | Training Loss | |:------:|:----:|:-------------:| | 0.4088 | 500 | 0.3798 | | 0.8177 | 1000 | 0.2489 | | 1.2265 | 1500 | 0.1308 | | 1.6353 | 2000 | 0.0877 | ### Framework Versions - Python: 3.10.19 - Sentence Transformers: 5.2.2 - Transformers: 5.0.0 - PyTorch: 2.9.1 - Accelerate: 1.12.0 - Datasets: 4.5.0 - Tokenizers: 0.22.2 ## Citation ### BibTeX #### ArkTS-CodeSearch ```bibtex @misc{he2026arktscodesearchopensourcearktsdataset, title={ArkTS-CodeSearch: A Open-Source ArkTS Dataset for Code Retrieval}, author={Yulong He and Artem Ermakov and Sergey Kovalchuk and Artem Aliev and Dmitry Shalymov}, year={2026}, eprint={2602.05550}, archivePrefix={arXiv}, primaryClass={cs.SE}, url={https://arxiv.org/abs/2602.05550}, } ```