Hugging Face's logo

AI4free
/
JARVIS-tool-search-v1

Sentence Similarity
sentence-transformers
Safetensors
feature-extraction
Generated from Trainer
dataset_size:421264
loss:MultipleNegativesRankingLoss
Model card Files
xet
 Community

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
  • Maximum Sequence Length: inf tokens
  • Output Dimensionality: 256 dimensions
  • Similarity Function: Cosine Similarity
  • Supported Modality: Text

Model Sources

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]])

Training Details

Training Dataset

Unnamed Dataset

  • Size: 421,264 training samples
  • Columns: anchor and positive
  • Approximate statistics based on the first 100 samples:
    anchor positive
    type string string
    modality text text
    details
    • min: 29 characters
    • mean: 238.62 characters
    • max: 2706 characters
    • min: 63 characters
    • mean: 533.32 characters
    • max: 1573 characters
  • Samples:
    anchor positive
    Find go code: // SetPriority sets the Priority field's value. go function SetPriority:
    func (s *UpdateMaintenanceWindowTaskInput) SetPriority(v int64) *UpdateMaintenanceWindowTaskInput {
    s.Priority = &v
    return s
    }
    Find php code: Prepare a has-one-deep or has-many-deep relationship from an existing has-many-through relationship.

    @param \Illuminate\Database\Eloquent\Relations\HasManyThrough $relation
    @param \Illuminate\Database\Eloquent\Model[] $through
    @param array $foreignKeys
    @param array $localKeys
    @return array    		 php function ConcatenatesRelationships.hasOneOrManyDeepFromHasManyThrough:
    protected function hasOneOrManyDeepFromHasManyThrough(HasManyThrough $relation, array $through, array $foreignKeys, array $localKeys)
    {
    $through[] = get_class($relation->getParent());

    $foreignKeys[] = $relation->getFirstKeyName();
    $foreignKeys[] = $relation->getForeignKeyName();

    $localKeys[] = $relation->getLocalKeyName();
    $localKeys[] = $relation->getSecondLocalKeyName();

    return [$through, $foreignKeys, $localKeys];
    }
    Find go code: // GetServiceInstances returns back a list of managed Service Instances based
    // off of the provided filters.    		 go function GetServiceInstances:
    func (client *Client) GetServiceInstances(filters ...Filter) ([]ServiceInstance, Warnings, error) {
    request, err := client.newHTTPRequest(requestOptions{
    RequestName: internal.GetServiceInstancesRequest,
    Query: ConvertFilterParameters(filters),
    })
    if err != nil {
    return nil, nil, err
    }

    var fullInstancesList []ServiceInstance
    warnings, err := client.paginate(request, ServiceInstance{}, func(item interface{}) error {
    if instance, ok := item.(ServiceInstance); ok {
    fullInstancesList = append(fullInstancesList, instance)
    } else {
    return ccerror.UnknownObjectInListError{
    Expected: ServiceInstance{},
    Unexpected: item,
    }
    }
    return nil
    })

    return fullInstancesList, warnings, err
    }
  • Loss: MultipleNegativesRankingLoss 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: anchor and positive
  • Approximate statistics based on the first 100 samples:
    anchor positive
    type string string
    modality text text
    details
    • min: 28 characters
    • mean: 206.54 characters
    • max: 1078 characters
    • min: 76 characters
    • mean: 713.74 characters
    • max: 1556 characters
  • Samples:
    anchor positive
    Find php code: {@inheritDoc} php function BuildConfigsPass.process:
    public function process(ContainerBuilder $container)
    {
    $configs = $this->processTagData($container->findTaggedServiceIds('payum.action'), 'payum.action.', 'payum.prepend_actions');
    $configs = array_replace_recursive(
    $configs,
    $this->processTagData($container->findTaggedServiceIds('payum.api'), 'payum.api.', 'payum.prepend_apis')
    );
    $configs = array_replace_recursive(
    $configs,
    $this->processTagData($container->findTaggedServiceIds('payum.extension'), 'payum.extension.', 'payum.prepend_extensions')
    );

    $builder = $container->getDefinition('payum.builder');
    if ($container->hasDefinition('twig')) {
    $config = ['twig.env' => '@twig'];

    $builder->addMethodCall('addCoreGatewayFactoryConfig', [$config]);
    }

    if (false == empty($configs[0])) {
    $builder->addMethodCall('addCoreGatewayFactoryConfig',...
    Code search (javascript): This function returns the index where we need to split the menu javascript code:
    function calculateNumberOfItemsInMenu(menuWidth, items, moreMenuItem){


    var itemsWidth = 0;

    var itemsWidthGrowth = [];

    var splitMenuAt;

    items.each(function(i){

    var item = jQuery(this);

    if (item.is(':visible')) {

    itemsWidth += item.children('a').outerWidth();

    } else {

    item.show();

    itemsWidth += item.children('a').outerWidth();

    item.hide();

    }

    if (i > 0) {

    itemsWidth -= 6;

    }

    itemsWidthGrowth[i] = itemsWidth;

    });


    //Test if there is room without more-btn

    if((menuWidth - moreMenuItem.outerWidth(true)) > itemsWidthGrowth[items.length - 1] && moreMenuItem.is(":visible")){

    ...
    Find javascript code: get ast of template
    @param {String} [name] xtemplate name
    @param {String} tplContent
    @return {Object}    		 javascript function ``:
    function (tplContent, name) {
    if (tplContent) {
    var ret;
    try {
    ret = parser.parse(tplContent, name);
    } catch (err) {
    var e;
    if (err instanceof Error) {
    e = err;
    } else {
    e = new Error(err);
    }
    var errorStr = 'XTemplate error ';
    e.stack = errorStr + e.stack;
    e.message = errorStr + e.message;
    throw e;
    }
    return ret;
    } else {
    return {
    statements: []
    };
    }
    }
  • Loss: MultipleNegativesRankingLoss 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

Click to expand
  • 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: adamw_torch_fused
  • 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: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': 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: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_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: {}

Training Logs

Click to expand
Epoch Step Training Loss Validation Loss
0.0012 1 2.1556 -
0.0304 25 2.2146 -
0.0608 50 2.1920 -
0.0912 75 2.1143 -
0.1217 100 1.9792 -
0.1521 125 1.9022 -
0.1825 150 1.7480 -
0.2129 175 1.5972 -
0.2433 200 1.5071 -
0.2737 225 1.4351 -
0.3041 250 1.3025 -
0.3345 275 1.2240 -
0.3650 300 1.1487 -
0.3954 325 1.0857 -
0.4258 350 1.0583 -
0.4562 375 0.9984 -
0.4866 400 0.9691 -
0.5170 425 0.9302 -
0.5474 450 0.9005 -
0.5779 475 0.8575 -
0.6083 500 0.8184 -
0.6387 525 0.8095 -
0.6691 550 0.7817 -
0.6995 575 0.7805 -
0.7299 600 0.7413 -
0.7603 625 0.7297 -
0.7908 650 0.7325 -
0.8212 675 0.6821 -
0.8516 700 0.6786 -
0.8820 725 0.6831 -
0.9124 750 0.6480 -
0.9428 775 0.6537 -
0.9732 800 0.6342 -
0.9842 809 - 0.6233
1.0195 825 0.5972 -
1.0499 850 0.5548 -
1.0803 875 0.5521 -
1.1107 900 0.5461 -
1.1411 925 0.5315 -
1.1715 950 0.5343 -
1.2019 975 0.5251 -
1.2324 1000 0.5331 -
1.2628 1025 0.5055 -
1.2932 1050 0.5199 -
1.3236 1075 0.4942 -
1.3540 1100 0.5070 -
1.3844 1125 0.4927 -
1.4148 1150 0.5014 -
1.4453 1175 0.4886 -
1.4757 1200 0.4829 -
1.5061 1225 0.4727 -
1.5365 1250 0.4537 -
1.5669 1275 0.4675 -
1.5973 1300 0.4592 -
1.6277 1325 0.4599 -
1.6582 1350 0.4711 -
1.6886 1375 0.4466 -
1.7190 1400 0.4511 -
1.7494 1425 0.4581 -
1.7798 1450 0.4685 -
1.8102 1475 0.4434 -
1.8406 1500 0.4398 -
1.8710 1525 0.4422 -
1.9015 1550 0.4420 -
1.9319 1575 0.4460 -
1.9623 1600 0.4354 -
1.9842 1618 - 0.4567
2.0085 1625 0.4073 -
2.0389 1650 0.3666 -
2.0693 1675 0.3497 -
2.0998 1700 0.3531 -
2.1302 1725 0.3478 -
2.1606 1750 0.3558 -
2.1910 1775 0.3483 -
2.2214 1800 0.3477 -
2.2518 1825 0.3511 -
2.2822 1850 0.3368 -
2.3127 1875 0.3519 -
2.3431 1900 0.3546 -
2.3735 1925 0.3613 -
2.4039 1950 0.3486 -
2.4343 1975 0.3394 -
2.4647 2000 0.3523 -
2.4951 2025 0.3384 -
2.5255 2050 0.3408 -
2.5560 2075 0.3459 -
2.5864 2100 0.3444 -
2.6168 2125 0.3359 -
2.6472 2150 0.3588 -
2.6776 2175 0.3336 -
2.7080 2200 0.3366 -
2.7384 2225 0.3362 -
2.7689 2250 0.3364 -
2.7993 2275 0.3368 -
2.8297 2300 0.3322 -
2.8601 2325 0.3442 -
2.8905 2350 0.3210 -
2.9209 2375 0.3311 -
2.9513 2400 0.3449 -
2.9818 2425 0.3242 -
2.9842 2427 - 0.4100
3.0280 2450 0.2820 -
3.0584 2475 0.2689 -
3.0888 2500 0.2688 -
3.1192 2525 0.2739 -
3.1496 2550 0.2676 -
3.1800 2575 0.2774 -
3.2105 2600 0.2794 -
3.2409 2625 0.2712 -
3.2713 2650 0.2759 -
3.3017 2675 0.2633 -
3.3321 2700 0.2808 -
3.3625 2725 0.2787 -
3.3929 2750 0.2752 -
3.4234 2775 0.2882 -
3.4538 2800 0.2836 -
3.4842 2825 0.2744 -
3.5146 2850 0.2745 -
3.5450 2875 0.2642 -
3.5754 2900 0.2685 -
3.6058 2925 0.2663 -
3.6363 2950 0.2817 -
3.6667 2975 0.2752 -
3.6971 3000 0.2721 -
3.7275 3025 0.2657 -
3.7579 3050 0.2807 -
3.7883 3075 0.2771 -
3.8187 3100 0.2742 -
3.8491 3125 0.2759 -
3.8796 3150 0.2845 -
3.9100 3175 0.2788 -
3.9404 3200 0.2763 -
3.9708 3225 0.2744 -
3.9842 3236 - 0.3850
4.0170 3250 0.2507 -
4.0474 3275 0.2222 -
4.0779 3300 0.2286 -
4.1083 3325 0.2232 -
4.1387 3350 0.2302 -
4.1691 3375 0.2297 -
4.1995 3400 0.2364 -
4.2299 3425 0.2301 -
4.2603 3450 0.2277 -
4.2908 3475 0.2307 -
4.3212 3500 0.2327 -
4.3516 3525 0.2286 -
4.3820 3550 0.2364 -
4.4124 3575 0.2453 -
4.4428 3600 0.2295 -
4.4732 3625 0.2351 -
4.5036 3650 0.2305 -
4.5341 3675 0.2366 -
4.5645 3700 0.2385 -
4.5949 3725 0.2285 -
4.6253 3750 0.2358 -
4.6557 3775 0.2446 -
4.6861 3800 0.2348 -
4.7165 3825 0.2346 -
4.7470 3850 0.2317 -
4.7774 3875 0.2305 -
4.8078 3900 0.2333 -
4.8382 3925 0.2439 -
4.8686 3950 0.2411 -
4.8990 3975 0.2348 -
4.9294 4000 0.2300 -
4.9599 4025 0.2339 -
4.9842 4045 - 0.3736
5.0061 4050 0.2394 -
5.0365 4075 0.2063 -
5.0669 4100 0.1971 -
5.0973 4125 0.1967 -
5.1277 4150 0.1989 -
5.1582 4175 0.1960 -
5.1886 4200 0.2003 -
5.2190 4225 0.2000 -
5.2494 4250 0.2040 -
5.2798 4275 0.2102 -
5.3102 4300 0.2077 -
5.3406 4325 0.2016 -
5.3710 4350 0.2127 -
5.4015 4375 0.2028 -
5.4319 4400 0.1995 -
5.4623 4425 0.2021 -
5.4927 4450 0.2109 -
5.5231 4475 0.2014 -
5.5535 4500 0.2105 -
5.5839 4525 0.2045 -
5.6144 4550 0.2076 -
5.6448 4575 0.2138 -
5.6752 4600 0.2070 -
5.7056 4625 0.2013 -
5.7360 4650 0.1973 -
5.7664 4675 0.2038 -
5.7968 4700 0.2197 -
5.8273 4725 0.2078 -
5.8577 4750 0.1980 -
5.8881 4775 0.2080 -
5.9185 4800 0.2066 -
5.9489 4825 0.2045 -
5.9793 4850 0.1992 -
5.9842 4854 - 0.3701
6.0255 4875 0.1887 -
6.0560 4900 0.1894 -
6.0864 4925 0.1906 -
6.1168 4950 0.1789 -
6.1472 4975 0.1870 -
6.1776 5000 0.1852 -
6.2080 5025 0.1829 -
6.2384 5050 0.1800 -
6.2689 5075 0.1879 -
6.2993 5100 0.1847 -
6.3297 5125 0.1810 -
6.3601 5150 0.1820 -
6.3905 5175 0.1855 -
6.4209 5200 0.1825 -
6.4513 5225 0.1839 -
6.4818 5250 0.1798 -
6.5122 5275 0.1817 -
6.5426 5300 0.1778 -
6.5730 5325 0.1865 -
6.6034 5350 0.1861 -
6.6338 5375 0.1874 -
6.6642 5400 0.1899 -
6.6946 5425 0.1816 -
6.7251 5450 0.1881 -
6.7555 5475 0.1955 -
6.7859 5500 0.1883 -
6.8163 5525 0.1859 -
6.8467 5550 0.1834 -
6.8771 5575 0.1937 -
6.9075 5600 0.1900 -
6.9380 5625 0.1874 -
6.9684 5650 0.1911 -
6.9842 5663 - 0.3659
7.0146 5675 0.1842 -
7.0450 5700 0.1664 -
7.0754 5725 0.1670 -
7.1058 5750 0.1692 -
7.1363 5775 0.1748 -
7.1667 5800 0.1679 -
7.1971 5825 0.1726 -
7.2275 5850 0.1654 -
7.2579 5875 0.1717 -
7.2883 5900 0.1759 -
7.3187 5925 0.1681 -
7.3491 5950 0.1805 -
7.3796 5975 0.1720 -
7.4100 6000 0.1785 -
7.4404 6025 0.1785 -
7.4708 6050 0.1722 -
7.5012 6075 0.1727 -
7.5316 6100 0.1762 -
7.5620 6125 0.1753 -
7.5925 6150 0.1713 -
7.6229 6175 0.1732 -
7.6533 6200 0.1692 -
7.6837 6225 0.1771 -
7.7141 6250 0.1830 -
7.7445 6275 0.1715 -
7.7749 6300 0.1682 -
7.8054 6325 0.1783 -
7.8358 6350 0.1725 -
7.8662 6375 0.1715 -
7.8966 6400 0.1763 -
7.9270 6425 0.1653 -
7.9574 6450 0.1704 -
7.9842 6472 - 0.3639
8.0036 6475 0.1780 -
8.0341 6500 0.1593 -
8.0645 6525 0.1630 -
8.0949 6550 0.1559 -
8.1253 6575 0.1677 -
8.1557 6600 0.1565 -
8.1861 6625 0.1640 -
8.2165 6650 0.1665 -
8.2470 6675 0.1651 -
8.2774 6700 0.1655 -
8.3078 6725 0.1699 -
8.3382 6750 0.1682 -
8.3686 6775 0.1615 -
8.3990 6800 0.1702 -
8.4294 6825 0.1638 -
8.4599 6850 0.1700 -
8.4903 6875 0.1701 -
8.5207 6900 0.1627 -
8.5511 6925 0.1630 -
8.5815 6950 0.1674 -
8.6119 6975 0.1652 -
8.6423 7000 0.1667 -
8.6727 7025 0.1633 -
8.7032 7050 0.1744 -
8.7336 7075 0.1635 -
8.7640 7100 0.1670 -
8.7944 7125 0.1680 -
8.8248 7150 0.1681 -
8.8552 7175 0.1640 -
8.8856 7200 0.1697 -
8.9161 7225 0.1716 -
8.9465 7250 0.1662 -
8.9769 7275 0.1655 -
8.9842 7281 - 0.3631
9.0231 7300 0.1672 -
9.0535 7325 0.1592 -
9.0839 7350 0.1555 -
9.1144 7375 0.1582 -
9.1448 7400 0.1565 -
9.1752 7425 0.1541 -
9.2056 7450 0.1571 -
9.2360 7475 0.1652 -
9.2664 7500 0.1693 -
9.2968 7525 0.1599 -
9.3273 7550 0.1642 -
9.3577 7575 0.1614 -
9.3881 7600 0.1595 -
9.4185 7625 0.1548 -
9.4489 7650 0.1705 -
9.4793 7675 0.1644 -
9.5097 7700 0.1623 -
9.5401 7725 0.1621 -
9.5706 7750 0.1629 -
9.6010 7775 0.1620 -
9.6314 7800 0.1668 -
9.6618 7825 0.1618 -
9.6922 7850 0.1589 -
9.7226 7875 0.1595 -
9.7530 7900 0.1641 -
9.7835 7925 0.1669 -
9.8139 7950 0.1699 -
9.8443 7975 0.1671 -
9.8747 8000 0.1627 -
9.9051 8025 0.1614 -
9.9355 8050 0.1635 -
9.9659 8075 0.1586 -
9.9842 8090 - 0.3629
  • The bold row denotes the saved checkpoint.

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},
}
Downloads last month

-

Downloads are not tracked for this model. How to track
Safetensors
Model size
7.56M params
Tensor type
F32
·
Inference Providers NEW
Sentence Similarity
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for AI4free/JARVIS-tool-search-v1

Base model

minishlab/potion-base-8M
Finetuned
(5)
this model
Finetunes
1 model

Papers for AI4free/JARVIS-tool-search-v1