Hugging Face's logo

Shuu12121
/
CodeSearch-ModernBERT-Owl-3.0-Plus

Sentence Similarity
sentence-transformers
Safetensors
English
modernbert
feature-extraction
Generated from Trainer
dataset_size:7059200
loss:MultipleNegativesRankingLoss
text-embeddings-inference
Model card Files
xet
Community
CodeSearch-ModernBERT-Owl-3.0-Plus / README.md
Shuu12121's picture
Shuu12121
Upload ModernBERT model
e35b241 verified
preview code
|
raw
history blame
27.8 kB
metadata
tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - generated_from_trainer
  - dataset_size:7059200
  - loss:MultipleNegativesRankingLoss
base_model: Shuu12121/CodeModernBERT-Owl-3.0
widget:
  - source_sentence: >-
      The maximum value of the slider. (default 0) <P>

      @return Returns the value of the attribute, or 0, if it hasn't been set by
      the JSF file.
    sentences:
      - |-
        @Override
            public UpdateSmsChannelResult updateSmsChannel(UpdateSmsChannelRequest request) {
                request = beforeClientExecution(request);
                return executeUpdateSmsChannel(request);
            }
      - |-
        async function isValidOrigin(origin, sourceOrigin) {
            // This will fetch the caches from https://cdn.ampproject.org/caches.json the first time it's
            // called. Subsequent calls will receive a cached version.
            const officialCacheList = await caches.list();
            // Calculate the cache specific origin
            const cacheSubdomain = `https://${await createCacheSubdomain(sourceOrigin)}.`;
            // Check all caches listed on ampproject.org
            for (const cache of officialCacheList) {
              const cachedOrigin = cacheSubdomain + cache.cacheDomain;
              if (origin === cachedOrigin) {
                return true;
              }
            }
            return false;
          }
      - "public java.lang.Object getMin() {\n\t\treturn (java.lang.Object) getStateHelper().eval(PropertyKeys.min, 0);\n\t}"
  - source_sentence: >-
      The Method from the Date.getMinutes is deprecated. This is a
      helper-Method.


      @param date

      The Date-object to get the minutes.

      @return The minutes from the Date-object.
    sentences:
      - "public static int getMinutes(final Date date)\n\t{\n\t\tfinal Calendar calendar = Calendar.getInstance();\n\t\tcalendar.setTime(date);\n\t\treturn calendar.get(Calendar.MINUTE);\n\t}"
      - "func (opts BeeOptions) Bind(name string, dst interface{}) error {\n\tv := opts.Value(name)\n\tif v == nil {\n\t\treturn errors.New(\"Option with name \" + name + \" not found\")\n\t}\n\n\treturn ConvertValue(v, dst)\n}"
      - >-
        public function createFor(Customer $customer, array $options = [], array
        $filters = [])
            {
                $this->parentId = $customer->id;

                return parent::rest_create($options, $filters);
            }
  - source_sentence: |-
      Return a list of all dates from 11/12/2015 to the present.

        Args:
          boo: if true, list contains Numbers (20151230); if false, list contains Strings ("2015-12-30")
        Returns:
          list of either Numbers or Strings
    sentences:
      - |-
        def all_days(boo):
          
          earliest = datetime.strptime(('2015-11-12').replace('-', ' '), '%Y %m %d')
          latest = datetime.strptime(datetime.today().date().isoformat().replace('-', ' '), '%Y %m %d')
          num_days = (latest - earliest).days + 1
          all_days = [latest - timedelta(days=x) for x in range(num_days)]
          all_days.reverse()

          output = []

          if boo:
            # Return as Integer, yyyymmdd
            for d in all_days:
              output.append(int(str(d).replace('-', '')[:8]))
          else:
            # Return as String, yyyy-mm-dd
            for d in all_days:
              output.append(str(d)[:10])
          return output
      - "public void setColSize3(Integer newColSize3) {\n\t\tInteger oldColSize3 = colSize3;\n\t\tcolSize3 = newColSize3;\n\t\tif (eNotificationRequired())\n\t\t\teNotify(new ENotificationImpl(this, Notification.SET, AfplibPackage.COLOR_SPECIFICATION__COL_SIZE3, oldColSize3, colSize3));\n\t}"
      - >-
        public function
        deleteCompanyBusinessUnitStoreAddress(CompanyBusinessUnitStoreAddressTransfer
        $companyBusinessUnitStoreAddressTransfer): void
            {
                $this->getFactory()
                    ->createFosCompanyBusinessUnitStoreAddressQuery()
                    ->findOneByIdCompanyBusinessUnitStoreAddress($companyBusinessUnitStoreAddressTransfer->getIdCompanyBusinessUnitStoreAddress())
                    ->delete();
            }
  - source_sentence: |-
      Returns array of basket oxarticle objects

      @return array
    sentences:
      - |-
        public function visit(NodeVisitorInterface $visitor)
            {
                foreach ($this->children as $child)
                {
                    $child->visit($visitor);
                }
            }
      - "func GetColDefaultValue(ctx sessionctx.Context, col *model.ColumnInfo) (types.Datum, error) {\n\treturn getColDefaultValue(ctx, col, col.GetDefaultValue())\n}"
      - |-
        public function getBasketArticles()
            {
                $aBasketArticles = [];
                /** @var \oxBasketItem $oBasketItem */
                foreach ($this->_aBasketContents as $sItemKey => $oBasketItem) {
                    try {
                        $oProduct = $oBasketItem->getArticle(true);

                        if (\OxidEsales\Eshop\Core\Registry::getConfig()->getConfigParam('bl_perfLoadSelectLists')) {
                            // marking chosen select list
                            $aSelList = $oBasketItem->getSelList();
                            if (is_array($aSelList) && ($aSelectlist = $oProduct->getSelectLists($sItemKey))) {
                                reset($aSelList);
                                foreach ($aSelList as $conkey => $iSel) {
                                    $aSelectlist[$conkey][$iSel]->selected = 1;
                                }
                                $oProduct->setSelectlist($aSelectlist);
                            }
                        }
                    } catch (\OxidEsales\Eshop\Core\Exception\NoArticleException $oEx) {
                        \OxidEsales\Eshop\Core\Registry::getUtilsView()->addErrorToDisplay($oEx);
                        $this->removeItem($sItemKey);
                        $this->calculateBasket(true);
                        continue;
                    } catch (\OxidEsales\Eshop\Core\Exception\ArticleInputException $oEx) {
                        \OxidEsales\Eshop\Core\Registry::getUtilsView()->addErrorToDisplay($oEx);
                        $this->removeItem($sItemKey);
                        $this->calculateBasket(true);
                        continue;
                    }

                    $aBasketArticles[$sItemKey] = $oProduct;
                }

                return $aBasketArticles;
            }
  - source_sentence: get test root
    sentences:
      - |-
        @CheckReturnValue
            @SchedulerSupport(SchedulerSupport.NONE)
            public final Maybe<T> doOnDispose(Action onDispose) {
                return RxJavaPlugins.onAssembly(new MaybePeek<T>(this,
                        Functions.emptyConsumer(), // onSubscribe
                        Functions.emptyConsumer(), // onSuccess
                        Functions.emptyConsumer(), // onError
                        Functions.EMPTY_ACTION,    // onComplete
                        Functions.EMPTY_ACTION,    // (onSuccess | onError | onComplete) after
                        ObjectHelper.requireNonNull(onDispose, "onDispose is null")
                ));
            }
      - >-
        protected Object parseKeyElement(Element keyEle, BeanDefinition bd,
        String defaultKeyTypeName) {
            NodeList nl = keyEle.getChildNodes();
            Element subElement = null;
            for (int i = 0; i < nl.getLength(); i++) {
              Node node = nl.item(i);
              if (node instanceof Element) {
                // Child element is what we're looking for.
                if (subElement != null)
                  error("<key> element must not contain more than one value sub-element", keyEle);
                else subElement = (Element) node;
              }
            }
            return parsePropertySubElement(subElement, bd, defaultKeyTypeName);
          }
      - |-
        function getRootPath(){
            var rootPath = path.resolve('.');
            while(rootPath){
                if(fs.existsSync(rootPath + '/config.json')){
                    break;
                }
                rootPath = rootPath.substring(0, rootPath.lastIndexOf(path.sep));
            }
            return rootPath;
        }
pipeline_tag: sentence-similarity
library_name: sentence-transformers

SentenceTransformer based on Shuu12121/CodeModernBERT-Owl-3.0

This is a sentence-transformers model finetuned from Shuu12121/CodeModernBERT-Owl-3.0. 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-3.0
  • Maximum Sequence Length: 1024 tokens
  • Output Dimensionality: 768 dimensions
  • Similarity Function: Cosine Similarity

Model Sources

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:

pip install -U sentence-transformers

Then you can load this model and run inference.

from sentence_transformers import SentenceTransformer

# Download from the 🤗 Hub
model = SentenceTransformer("sentence_transformers_model_id")
# Run inference
sentences = [
    'get test root',
    "function getRootPath(){\n    var rootPath = path.resolve('.');\n    while(rootPath){\n        if(fs.existsSync(rootPath + '/config.json')){\n            break;\n        }\n        rootPath = rootPath.substring(0, rootPath.lastIndexOf(path.sep));\n    }\n    return rootPath;\n}",
    'protected Object parseKeyElement(Element keyEle, BeanDefinition bd, String defaultKeyTypeName) {\n    NodeList nl = keyEle.getChildNodes();\n    Element subElement = null;\n    for (int i = 0; i < nl.getLength(); i++) {\n      Node node = nl.item(i);\n      if (node instanceof Element) {\n        // Child element is what we\'re looking for.\n        if (subElement != null)\n          error("<key> element must not contain more than one value sub-element", keyEle);\n        else subElement = (Element) node;\n      }\n    }\n    return parsePropertySubElement(subElement, bd, defaultKeyTypeName);\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]

Training Details

Training Dataset

Unnamed Dataset

  • Size: 7,059,200 training samples
  • Columns: sentence_0, sentence_1, and label
  • Approximate statistics based on the first 1000 samples:
    sentence_0 sentence_1 label
    type string string float
    details
    • min: 3 tokens
    • mean: 51.42 tokens
    • max: 974 tokens
    • min: 29 tokens
    • mean: 162.71 tokens
    • max: 1024 tokens
    • min: 1.0
    • mean: 1.0
    • max: 1.0
  • Samples:
    sentence_0 sentence_1 label
    // SetDefaultVersionId sets the DefaultVersionId field's value. func (s *Policy) SetDefaultVersionId(v string) *Policy {
    s.DefaultVersionId = &v
    return s
    }    		 1.0
    // SetNextPageToken sets the NextPageToken field's value. func (s *ListBudgetsForResourceOutput) SetNextPageToken(v string) *ListBudgetsForResourceOutput {
    s.NextPageToken = &v
    return s
    }    		 1.0
    // SetHealthyThresholdCount sets the HealthyThresholdCount field's value. func (s *TargetGroup) SetHealthyThresholdCount(v int64) *TargetGroup {
    s.HealthyThresholdCount = &v
    return s
    }    		 1.0
  • Loss: MultipleNegativesRankingLoss with these parameters:
    {
    "scale": 20.0,
    "similarity_fct": "cos_sim"
}

Training Hyperparameters

Non-Default Hyperparameters

  • per_device_train_batch_size: 200
  • per_device_eval_batch_size: 200
  • fp16: True
  • multi_dataset_batch_sampler: round_robin

All Hyperparameters

Click to expand
  • overwrite_output_dir: False
  • do_predict: False
  • eval_strategy: no
  • prediction_loss_only: True
  • per_device_train_batch_size: 200
  • per_device_eval_batch_size: 200
  • 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

Training Logs

Click to expand
Epoch Step Training Loss
0.0142 500 1.1661
0.0283 1000 0.1176
0.0425 1500 0.1096
0.0567 2000 0.1013
0.0708 2500 0.0967
0.0850 3000 0.0912
0.0992 3500 0.0886
0.1133 4000 0.0799
0.1275 4500 0.0776
0.1417 5000 0.0757
0.1558 5500 0.0751
0.1700 6000 0.0714
0.1842 6500 0.0703
0.1983 7000 0.0667
0.2125 7500 0.0674
0.2267 8000 0.0625
0.2408 8500 0.0598
0.2550 9000 0.0597
0.2692 9500 0.0585
0.2833 10000 0.0568
0.2975 10500 0.055
0.3117 11000 0.0554
0.3258 11500 0.0529
0.3400 12000 0.0516
0.3541 12500 0.0506
0.3683 13000 0.05
0.3825 13500 0.0484
0.3966 14000 0.0472
0.4108 14500 0.0468
0.4250 15000 0.045
0.4391 15500 0.046
0.4533 16000 0.0452
0.4675 16500 0.0428
0.4816 17000 0.0424
0.4958 17500 0.04
0.5100 18000 0.0402
0.5241 18500 0.0391
0.5383 19000 0.0389
0.5525 19500 0.0385
0.5666 20000 0.0357
0.5808 20500 0.0362
0.5950 21000 0.0369
0.6091 21500 0.0372
0.6233 22000 0.0351
0.6375 22500 0.034
0.6516 23000 0.0364
0.6658 23500 0.033
0.6800 24000 0.0336
0.6941 24500 0.0302
0.7083 25000 0.0309
0.7225 25500 0.0306
0.7366 26000 0.0316
0.7508 26500 0.0306
0.7650 27000 0.0307
0.7791 27500 0.0303
0.7933 28000 0.028
0.8075 28500 0.0289
0.8216 29000 0.0297
0.8358 29500 0.0281
0.8500 30000 0.029
0.8641 30500 0.027
0.8783 31000 0.0282
0.8925 31500 0.0264
0.9066 32000 0.027
0.9208 32500 0.0259
0.9350 33000 0.0272
0.9491 33500 0.0275
0.9633 34000 0.0244
0.9774 34500 0.0254
0.9916 35000 0.0261
1.0058 35500 0.0189
1.0199 36000 0.0118
1.0341 36500 0.012
1.0483 37000 0.0118
1.0624 37500 0.0109
1.0766 38000 0.0123
1.0908 38500 0.0122
1.1049 39000 0.0122
1.1191 39500 0.0123
1.1333 40000 0.0117
1.1474 40500 0.0115
1.1616 41000 0.0122
1.1758 41500 0.0117
1.1899 42000 0.0119
1.2041 42500 0.0112
1.2183 43000 0.0122
1.2324 43500 0.0116
1.2466 44000 0.0107
1.2608 44500 0.0126
1.2749 45000 0.0114
1.2891 45500 0.011
1.3033 46000 0.0116
1.3174 46500 0.0114
1.3316 47000 0.0111
1.3458 47500 0.0112
1.3599 48000 0.0112
1.3741 48500 0.0115
1.3883 49000 0.0104
1.4024 49500 0.0109
1.4166 50000 0.0113
1.4308 50500 0.0115
1.4449 51000 0.0103
1.4591 51500 0.0114
1.4733 52000 0.0104
1.4874 52500 0.0106
1.5016 53000 0.0103
1.5158 53500 0.0102
1.5299 54000 0.0101
1.5441 54500 0.0104
1.5583 55000 0.011
1.5724 55500 0.0107
1.5866 56000 0.0097
1.6007 56500 0.0099
1.6149 57000 0.0102
1.6291 57500 0.0098
1.6432 58000 0.01
1.6574 58500 0.0096
1.6716 59000 0.0099
1.6857 59500 0.0103
1.6999 60000 0.0098
1.7141 60500 0.0097
1.7282 61000 0.0094
1.7424 61500 0.0093
1.7566 62000 0.0102
1.7707 62500 0.0099
1.7849 63000 0.0098
1.7991 63500 0.009
1.8132 64000 0.0097
1.8274 64500 0.009
1.8416 65000 0.0093
1.8557 65500 0.0092
1.8699 66000 0.0095
1.8841 66500 0.0093
1.8982 67000 0.0094
1.9124 67500 0.0089
1.9266 68000 0.0091
1.9407 68500 0.0089
1.9549 69000 0.0084
1.9691 69500 0.0087
1.9832 70000 0.0094
1.9974 70500 0.0085
2.0116 71000 0.0049
2.0257 71500 0.0041
2.0399 72000 0.0039
2.0541 72500 0.0038
2.0682 73000 0.004
2.0824 73500 0.0039
2.0966 74000 0.0038
2.1107 74500 0.0041
2.1249 75000 0.0037
2.1391 75500 0.0038
2.1532 76000 0.0041
2.1674 76500 0.0036
2.1816 77000 0.0039
2.1957 77500 0.0039
2.2099 78000 0.0038
2.2240 78500 0.0038
2.2382 79000 0.0037
2.2524 79500 0.0037
2.2665 80000 0.0036
2.2807 80500 0.0038
2.2949 81000 0.0037
2.3090 81500 0.0036
2.3232 82000 0.0036
2.3374 82500 0.0038
2.3515 83000 0.0037
2.3657 83500 0.0037
2.3799 84000 0.0038
2.3940 84500 0.0037
2.4082 85000 0.0036
2.4224 85500 0.0034
2.4365 86000 0.0035
2.4507 86500 0.0033
2.4649 87000 0.0036
2.4790 87500 0.0035
2.4932 88000 0.0034
2.5074 88500 0.0034
2.5215 89000 0.0034
2.5357 89500 0.0031
2.5499 90000 0.0033
2.5640 90500 0.0033
2.5782 91000 0.0035
2.5924 91500 0.0033
2.6065 92000 0.0032
2.6207 92500 0.0034
2.6349 93000 0.0031
2.6490 93500 0.0032
2.6632 94000 0.0032
2.6774 94500 0.0033
2.6915 95000 0.0032
2.7057 95500 0.003
2.7199 96000 0.0032
2.7340 96500 0.0032
2.7482 97000 0.003
2.7624 97500 0.0032
2.7765 98000 0.0033
2.7907 98500 0.003
2.8049 99000 0.003
2.8190 99500 0.0031
2.8332 100000 0.0031
2.8473 100500 0.003
2.8615 101000 0.003
2.8757 101500 0.003
2.8898 102000 0.003
2.9040 102500 0.003
2.9182 103000 0.003
2.9323 103500 0.003
2.9465 104000 0.0033
2.9607 104500 0.0029
2.9748 105000 0.003
2.9890 105500 0.0028

Framework Versions

  • Python: 3.11.13
  • Sentence Transformers: 4.1.0
  • Transformers: 4.52.4
  • PyTorch: 2.6.0+cu124
  • Accelerate: 1.7.0
  • Datasets: 3.6.0
  • Tokenizers: 0.21.1

Citation

BibTeX

Sentence Transformers 

@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 

@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}
}