AI4free/JARVIS-tool-search-v1

SentenceTransformer based on minishlab/potion-base-8M

This is a sentence-transformers model finetuned from minishlab/potion-base-8M. It maps sentences & paragraphs to a 256-dimensional dense vector space and can be used for retrieval.

Model Details

Model Description

• —Model Type: Sentence Transformer
• —Base model: minishlab/potion-base-8M <!-- at revision bf8b056651a2c21b8d2565580b8569da283cab23 -->
• —Maximum Sequence Length: inf tokens
• —Output Dimensionality: 256 dimensions
• —Similarity Function: Cosine Similarity
• —Supported Modality: Text <!-- - Training Dataset: Unknown --> <!-- - Language: Unknown --> <!-- - License: Unknown -->

Model Sources

• —Documentation: Sentence Transformers Documentation
• —Repository: Sentence Transformers on GitHub
• —Hugging Face: Sentence Transformers on Hugging Face

Full Model Architecture

SentenceTransformer(
  (0): StaticEmbedding({})
)

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 = [
    'Find python code: Convert the SDP relaxation to a human-readable format.\n\n    :param sdp: The SDP relaxation to write.\n    :type sdp: :class:`ncpol2sdpa.sdp`.\n    :returns: tuple of the objective function in a string and a matrix of\n              strings as the symbolic representation of the moment matrix',
    'python function `convert_to_human_readable`:\ndef convert_to_human_readable(sdp):\n    """Convert the SDP relaxation to a human-readable format.\n\n    :param sdp: The SDP relaxation to write.\n    :type sdp: :class:`ncpol2sdpa.sdp`.\n    :returns: tuple of the objective function in a string and a matrix of\n              strings as the symbolic representation of the moment matrix\n    """\n\n    objective = ""\n    indices_in_objective = []\n    for i, tmp in enumerate(sdp.obj_facvar):\n        candidates = [key for key, v in\n                      sdp.monomial_index.items() if v == i+1]\n        if len(candidates) > 0:\n            monomial = convert_monomial_to_string(candidates[0])\n        else:\n            monomial = ""\n        if tmp > 0:\n            objective += "+"+str(tmp)+monomial\n            indices_in_objective.append(i)\n        elif tmp < 0:\n            objective += str(tmp)+monomial\n            indices_in_objective.append(i)\n\n    matrix_size = 0\n    cumulative_sum = 0\n    row_offsets = [0]\n    block_offset = [0]\n    for bs in sdp.block_struct:\n        matrix_size += abs(bs)\n        cumulative_sum += bs ** 2\n        row_offsets.append(cumulative_sum)\n        block_offset.append(matrix_size)\n\n    matrix = []\n    for i in range(matrix_size):\n        matrix_line = ["0"] * matrix_size\n        matrix.append(matrix_line)\n\n    for row in range(len(sdp.F.rows)):\n        if len(sdp.F.rows[row]) > 0:\n            col_index = 0\n            for k in sdp.F.rows[row]:\n                value = sdp.F.data[row][col_index]\n                col',
    'Solution (swift):\nCustom Collection View Layout Class:\n```swift\nimport UIKit\n\nclass CustomCollectionViewLayout: UICollectionViewLayout {\n    let sectionInset = UIEdgeInsets(top: 20, left: 2, bottom: 20, right: 2)\n    var itemSize: CGFloat = 50 // Replace with the desired item size\n\n    override func prepare() {\n        // Implement layout preparation logic here\n    }\n\n    override var collectionViewContentSize: CGSize {\n        // Calculate and return the total content size of the collection view\n        return CGSize.zero\n    }\n\n    override func layoutAttributesForElements(in rect: CGRect) -> [UICollectionViewLayoutAttributes]? {\n        // Calculate and return the layout attributes for the items that intersect with the given rect\n        return nil\n    }\n}\n```\n\nView Controller:\n```swift\nimport UIKit\n\nclass MedicalRecordsViewController: UIViewController {\n    let collectionView = UICollectionView(frame: .zero, collectionViewLayout: CustomCollectionViewLayout())\n    let patient = Patient() // Assume Patient class is defined elsewhere\n\n    override func viewDidLoad() {\n        super.viewDidLoad()\n        let layout = collectionView.collectionViewLayout as! CustomCollectionViewLayout\n        layout.sectionInset = UIEdgeInsets(top: 20, left: 2, bottom: 20, right: 2)\n        layout.itemSize = CGSize(width: layout.itemSize, height: layout.itemSize)\n        layout.minimumInteritemSpacing = 5\n        layout.minimumLineSpacing = 5\n        self.collectionView.collectionViewLayout = layout\n    }\n\n    o',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 256]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities)
# tensor([[ 1.0000,  0.6170, -0.1287],
#         [ 0.6170,  1.0000, -0.0954],
#         [-0.1287, -0.0954,  1.0000]])

<!--

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: 421,264 training samples
• —Columns: <code>anchor</code> and <code>positive</code>
• —Approximate statistics based on the first 100 samples: | | anchor | positive | |:---------|:--------------------------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------------------| | type | string | string | | modality | text | text | | details | <ul><li>min: 29 characters</li><li>mean: 238.62 characters</li><li>max: 2706 characters</li></ul> | <ul><li>min: 63 characters</li><li>mean: 533.32 characters</li><li>max: 1573 characters</li></ul> |
• —Samples: | anchor | positive | |:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| | <code>Find go code: // SetPriority sets the Priority field's value.</code> | <code>go function SetPriority:<br>func (s UpdateMaintenanceWindowTaskInput) SetPriority(v int64) UpdateMaintenanceWindowTaskInput {<br> s.Priority = &v<br> return s<br>}</code> | | <code>Find php code: Prepare a has-one-deep or has-many-deep relationship from an existing has-many-through relationship.<br><br>@param \Illuminate\Database\Eloquent\Relations\HasManyThrough $relation<br>@param \Illuminate\Database\Eloquent\Model[] $through<br>@param array $foreignKeys<br>@param array $localKeys<br>@return array</code> | <code>php function ConcatenatesRelationships.hasOneOrManyDeepFromHasManyThrough:<br>protected function hasOneOrManyDeepFromHasManyThrough(HasManyThrough $relation, array $through, array $foreignKeys, array $localKeys)<br> {<br> $through[] = get_class($relation->getParent());<br><br> $foreignKeys[] = $relation->getFirstKeyName();<br> $foreignKeys[] = $relation->getForeignKeyName();<br><br> $localKeys[] = $relation->getLocalKeyName();<br> $localKeys[] = $relation->getSecondLocalKeyName();<br><br> return [$through, $foreignKeys, $localKeys];<br> }</code> | | <code>Find go code: // GetServiceInstances returns back a list of managed Service Instances based<br>// off of the provided filters.</code> | <code>go function GetServiceInstances:<br>func (client *Client) GetServiceInstances(filters ...Filter) ([]ServiceInstance, Warnings, error) {<br> request, err := client.newHTTPRequest(requestOptions{<br> RequestName: internal.GetServiceInstancesRequest,<br> Query: ConvertFilterParameters(filters),<br> })<br> if err != nil {<br> return nil, nil, err<br> }<br><br> var fullInstancesList []ServiceInstance<br> warnings, err := client.paginate(request, ServiceInstance{}, func(item interface{}) error {<br> if instance, ok := item.(ServiceInstance); ok {<br> fullInstancesList = append(fullInstancesList, instance)<br> } else {<br> return ccerror.UnknownObjectInListError{<br> Expected: ServiceInstance{},<br> Unexpected: item,<br> }<br> }<br> return nil<br> })<br><br> return fullInstancesList, warnings, err<br>}</code> |
• —Loss: <code>MultipleNegativesRankingLoss</code> with these parameters:

  {
      "scale": 20.0,
      "similarity_fct": "cos_sim",
      "gather_across_devices": false,
      "directions": [
          "query_to_doc"
      ],
      "partition_mode": "joint",
      "hardness_mode": null,
      "hardness_strength": 0.0
  }

Evaluation Dataset

Unnamed Dataset

• —Size: 2,000 evaluation samples
• —Columns: <code>anchor</code> and <code>positive</code>
• —Approximate statistics based on the first 100 samples: | | anchor | positive | |:---------|:--------------------------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------------------| | type | string | string | | modality | text | text | | details | <ul><li>min: 28 characters</li><li>mean: 206.54 characters</li><li>max: 1078 characters</li></ul> | <ul><li>min: 76 characters</li><li>mean: 713.74 characters</li><li>max: 1556 characters</li></ul> |
• —Samples: | anchor | positive | |:--------------------------------------------------------------------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| | <code>Find php code: {@inheritDoc}</code> | <code>php function BuildConfigsPass.process:<br>public function process(ContainerBuilder $container)<br> {<br> $configs = $this->processTagData($container->findTaggedServiceIds('payum.action'), 'payum.action.', 'payum.prependactions');<br> $configs = arrayreplacerecursive(<br> $configs,<br> $this->processTagData($container->findTaggedServiceIds('payum.api'), 'payum.api.', 'payum.prependapis')<br> );<br> $configs = arrayreplacerecursive(<br> $configs,<br> $this->processTagData($container->findTaggedServiceIds('payum.extension'), 'payum.extension.', 'payum.prepend_extensions')<br> );<br><br> $builder = $container->getDefinition('payum.builder');<br> if ($container->hasDefinition('twig')) {<br> $config = ['twig.env' => '@twig'];<br><br> $builder->addMethodCall('addCoreGatewayFactoryConfig', [$config]);<br> }<br><br> if (false == empty($configs[0])) {<br> $builder->addMethodCall('addCoreGatewayFactoryConfig',...</code> | | <code>Code search (javascript): This function returns the index where we need to split the menu</code> | <code>javascript code:<br>function calculateNumberOfItemsInMenu(menuWidth, items, moreMenuItem){ <br> <br> var itemsWidth = 0; <br> var itemsWidthGrowth = []; <br> var splitMenuAt; <br> items.each(function(i){ <br> var item = jQuery(this); <br> if (item.is(':visible')) { <br> itemsWidth += item.children('a').outerWidth(); <br> } else { <br> item.show(); <br> itemsWidth += item.children('a').outerWidth(); <br> item.hide(); <br> } <br> if (i > 0) { <br> itemsWidth -= 6; <br> } <br> itemsWidthGrowth[i] = itemsWidth; <br> }); <br> <br> //Test if there is room without more-btn <br> if((menuWidth - moreMenuItem.outerWidth(true)) > itemsWidthGrowth[items.length - 1] && moreMenuItem.is(":visible")){ <br> ...</code> | | <code>Find javascript code: get ast of template<br>@param {String} [name] xtemplate name<br>@param {String} tplContent<br>@return {Object}</code> | <code>javascript function ``:<br>function (tplContent, name) {<br> if (tplContent) {<br> var ret;<br> try {<br> ret = parser.parse(tplContent, name);<br> } catch (err) {<br> var e;<br> if (err instanceof Error) {<br> e = err;<br> } else {<br> e = new Error(err);<br> }<br> var errorStr = 'XTemplate error ';<br> e.stack = errorStr + e.stack;<br> e.message = errorStr + e.message;<br> throw e;<br> }<br> return ret;<br> } else {<br> return {<br> statements: []<br> };<br> }<br> }</code> |
• —Loss: <code>MultipleNegativesRankingLoss</code> with these parameters:

  {
      "scale": 20.0,
      "similarity_fct": "cos_sim",
      "gather_across_devices": false,
      "directions": [
          "query_to_doc"
      ],
      "partition_mode": "joint",
      "hardness_mode": null,
      "hardness_strength": 0.0
  }

Training Hyperparameters

Non-Default Hyperparameters

• —per_device_train_batch_size: 512
• —num_train_epochs: 10
• —learning_rate: 0.03
• —lr_scheduler_type: cosine
• —warmup_steps: 0.1
• —disable_tqdm: True
• —per_device_eval_batch_size: 512
• —load_best_model_at_end: True
• —dataloader_drop_last: True
• —batch_sampler: no_duplicates

All Hyperparameters

<details><summary>Click to expand</summary>

• —per_device_train_batch_size: 512
• —num_train_epochs: 10
• —max_steps: -1
• —learning_rate: 0.03
• —lr_scheduler_type: cosine
• —lr_scheduler_kwargs: None
• —warmup_steps: 0.1
• —optim: adamwtorchfused
• —optim_args: None
• —weight_decay: 0.0
• —adam_beta1: 0.9
• —adam_beta2: 0.999
• —adam_epsilon: 1e-08
• —optim_target_modules: None
• —gradient_accumulation_steps: 1
• —average_tokens_across_devices: True
• —max_grad_norm: 1.0
• —label_smoothing_factor: 0.0
• —bf16: False
• —fp16: False
• —bf16_full_eval: False
• —fp16_full_eval: False
• —tf32: None
• —gradient_checkpointing: False
• —gradient_checkpointing_kwargs: None
• —torch_compile: False
• —torch_compile_backend: None
• —torch_compile_mode: None
• —use_liger_kernel: False
• —liger_kernel_config: None
• —use_cache: False
• —neftune_noise_alpha: None
• —torch_empty_cache_steps: None
• —auto_find_batch_size: False
• —log_on_each_node: True
• —logging_nan_inf_filter: True
• —include_num_input_tokens_seen: no
• —log_level: passive
• —log_level_replica: warning
• —disable_tqdm: True
• —project: huggingface
• —trackio_space_id: None
• —trackio_bucket_id: None
• —trackio_static_space_id: None
• —per_device_eval_batch_size: 512
• —prediction_loss_only: True
• —eval_on_start: False
• —eval_do_concat_batches: True
• —eval_use_gather_object: False
• —eval_accumulation_steps: None
• —include_for_metrics: []
• —batch_eval_metrics: False
• —save_only_model: False
• —save_on_each_node: False
• —enable_jit_checkpoint: False
• —push_to_hub: False
• —hub_private_repo: None
• —hub_model_id: None
• —hub_strategy: every_save
• —hub_always_push: False
• —hub_revision: None
• —load_best_model_at_end: True
• —ignore_data_skip: False
• —restore_callback_states_from_checkpoint: False
• —full_determinism: False
• —seed: 42
• —data_seed: None
• —use_cpu: False
• —accelerator_config: {'splitbatches': False, 'dispatchbatches': None, 'evenbatches': True, 'useseedablesampler': True, 'nonblocking': False, 'gradientaccumulationkwargs': None}
• —parallelism_config: None
• —dataloader_drop_last: True
• —dataloader_num_workers: 0
• —dataloader_pin_memory: True
• —dataloader_persistent_workers: False
• —dataloader_prefetch_factor: None
• —remove_unused_columns: True
• —label_names: None
• —train_sampling_strategy: random
• —length_column_name: length
• —ddp_find_unused_parameters: None
• —ddp_bucket_cap_mb: None
• —ddp_broadcast_buffers: False
• —ddp_static_graph: None
• —ddp_backend: None
• —ddp_timeout: 1800
• —fsdp: []
• —fsdp_config: {'minnumparams': 0, 'xla': False, 'xlafsdpv2': False, 'xlafsdpgrad_ckpt': False}
• —deepspeed: None
• —debug: []
• —skip_memory_metrics: True
• —do_predict: False
• —resume_from_checkpoint: None
• —warmup_ratio: None
• —local_rank: -1
• —prompts: None
• —batch_sampler: no_duplicates
• —multi_dataset_batch_sampler: proportional
• —router_mapping: {}
• —learning_rate_mapping: {}

</details>

Training Logs

<details><summary>Click to expand</summary>

• —The bold row denotes the saved checkpoint. </details>

Training Time

• —Training: 6.5 hours
• —Evaluation: 21.0 seconds
• —Total: 6.5 hours

Framework Versions

• —Python: 3.13.13
• —Sentence Transformers: 5.5.1
• —Transformers: 5.9.0
• —PyTorch: 2.12.0+cu130
• —Accelerate: 1.13.0
• —Datasets: 4.8.5
• —Tokenizers: 0.22.2

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{oord2019representationlearningcontrastivepredictive,
      title={Representation Learning with Contrastive Predictive Coding},
      author={Aaron van den Oord and Yazhe Li and Oriol Vinyals},
      year={2019},
      eprint={1807.03748},
      archivePrefix={arXiv},
      primaryClass={cs.LG},
      url={https://arxiv.org/abs/1807.03748},
}

<!--

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. -->