benjamintli
/

modernbert-codesearchnet

+{
+    "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
+}

README.md ADDED Viewed

	@@ -0,0 +1,972 @@

+---
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- dense
+- generated_from_trainer
+- dataset_size:369762
+- loss:CachedMultipleNegativesRankingLoss
+base_model: benjamintli/modernbert-cosqa
+widget:
+- source_sentence: Return a Python AST node for `recur` occurring inside a `loop`.
+  sentences:
+  - "def _reset(self, name=None):\n        \"\"\"Revert specified property to default\
+    \ value\n\n        If no property is specified, all properties are returned to\
+    \ default.\n        \"\"\"\n        if name is None:\n            for key in self._props:\n\
+    \                if isinstance(self._props[key], basic.Property):\n          \
+    \          self._reset(key)\n            return\n        if name not in self._props:\n\
+    \            raise AttributeError(\"Input name '{}' is not a known \"\n      \
+    \                           \"property or attribute\".format(name))\n        if\
+    \ not isinstance(self._props[name], basic.Property):\n            raise AttributeError(\"\
+    Cannot reset GettableProperty \"\n                                 \"'{}'\".format(name))\n\
+    \        if name in self._defaults:\n            val = self._defaults[name]\n\
+    \        else:\n            val = self._props[name].default\n        if callable(val):\n\
+    \            val = val()\n        setattr(self, name, val)"
+  - "def cancel(self):\n        '''\n        Cancel a running workflow.\n\n      \
+    \  Args:\n            None\n\n        Returns:\n            None\n        '''\n\
+    \        if not self.id:\n            raise WorkflowError('Workflow is not running.\
+    \  Cannot cancel.')\n\n        if self.batch_values:\n            self.workflow.batch_workflow_cancel(self.id)\n\
+    \        else:\n            self.workflow.cancel(self.id)"
+  - "def __loop_recur_to_py_ast(ctx: GeneratorContext, node: Recur) -> GeneratedPyAST:\n\
+    \    \"\"\"Return a Python AST node for `recur` occurring inside a `loop`.\"\"\
+    \"\n    assert node.op == NodeOp.RECUR\n\n    recur_deps: List[ast.AST] = []\n\
+    \    recur_targets: List[ast.Name] = []\n    recur_exprs: List[ast.AST] = []\n\
+    \    for name, expr in zip(ctx.recur_point.binding_names, node.exprs):\n     \
+    \   expr_ast = gen_py_ast(ctx, expr)\n        recur_deps.extend(expr_ast.dependencies)\n\
+    \        recur_targets.append(ast.Name(id=name, ctx=ast.Store()))\n        recur_exprs.append(expr_ast.node)\n\
+    \n    if len(recur_targets) == 1:\n        assert len(recur_exprs) == 1\n    \
+    \    recur_deps.append(ast.Assign(targets=recur_targets, value=recur_exprs[0]))\n\
+    \    else:\n        recur_deps.append(\n            ast.Assign(\n            \
+    \    targets=[ast.Tuple(elts=recur_targets, ctx=ast.Store())],\n             \
+    \   value=ast.Tuple(elts=recur_exprs, ctx=ast.Load()),\n            )\n      \
+    \  )\n    recur_deps.append(ast.Continue())\n\n    return GeneratedPyAST(node=ast.NameConstant(None),\
+    \ dependencies=recur_deps)"
+- source_sentence: "Create a :class:`~turicreate.linear_regression.LinearRegression`\
+    \ to\n    predict a scalar target variable as a linear function of one or more\n\
+    \    features. In addition to standard numeric and categorical types, features\n\
+    \    can also be extracted automatically from list- or dictionary-type SFrame\n\
+    \    columns.\n\n    The linear regression module can be used for ridge regression,\
+    \ Lasso, and\n    elastic net regression (see References for more detail on these\
+    \ methods). By\n    default, this model has an l2 regularization weight of 0.01.\n\
+    \n    Parameters\n    ----------\n    dataset : SFrame\n        The dataset to\
+    \ use for training the model.\n\n    target : string\n        Name of the column\
+    \ containing the target variable.\n\n    features : list[string], optional\n \
+    \       Names of the columns containing features. 'None' (the default) indicates\n\
+    \        that all columns except the target variable should be used as features.\n\
+    \n        The features are columns in the input SFrame that can be of the\n  \
+    \      following types:\n\n        - *Numeric*: values of numeric type integer\
+    \ or float.\n\n        - *Categorical*: values of type string.\n\n        - *Array*:\
+    \ list of numeric (integer or float) values. Each list element\n          is treated\
+    \ as a separate feature in the model.\n\n        - *Dictionary*: key-value pairs\
+    \ with numeric (integer or float) values\n          Each key of a dictionary is\
+    \ treated as a separate feature and the\n          value in the dictionary corresponds\
+    \ to the value of the feature.\n          Dictionaries are ideal for representing\
+    \ sparse data.\n\n        Columns of type *list* are not supported. Convert such\
+    \ feature\n        columns to type array if all entries in the list are of numeric\n\
+    \        types. If the lists contain data of mixed types, separate\n        them\
+    \ out into different columns.\n\n    l2_penalty : float, optional\n        Weight\
+    \ on the l2-regularizer of the model. The larger this weight, the\n        more\
+    \ the model coefficients shrink toward 0. This introduces bias into\n        the\
+    \ model but decreases variance, potentially leading to better\n        predictions.\
+    \ The default value is 0.01; setting this parameter to 0\n        corresponds\
+    \ to unregularized linear regression. See the ridge\n        regression reference\
+    \ for more detail.\n\n    l1_penalty : float, optional\n        Weight on l1 regularization\
+    \ of the model. Like the l2 penalty, the\n        higher the l1 penalty, the more\
+    \ the estimated coefficients shrink toward\n        0. The l1 penalty, however,\
+    \ completely zeros out sufficiently small\n        coefficients, automatically\
+    \ indicating features that are not useful for\n        the model. The default\
+    \ weight of 0 prevents any features from being\n        discarded. See the LASSO\
+    \ regression reference for more detail.\n\n    solver : string, optional\n   \
+    \     Solver to use for training the model. See the references for more detail\n\
+    \        on each solver.\n\n        - *auto (default)*: automatically chooses\
+    \ the best solver for the data\n          and model parameters.\n        - *newton*:\
+    \ Newton-Raphson\n        - *lbfgs*: limited memory BFGS\n        - *fista*: accelerated\
+    \ gradient descent\n\n        The model is trained using a carefully engineered\
+    \ collection of methods\n        that are automatically picked based on the input\
+    \ data. The ``newton``\n        method  works best for datasets with plenty of\
+    \ examples and few features\n        (long datasets). Limited memory BFGS (``lbfgs``)\
+    \ is a robust solver for\n        wide datasets (i.e datasets with many coefficients).\
+    \  ``fista`` is the\n        default solver for l1-regularized linear regression.\
+    \  The solvers are\n        all automatically tuned and the default options should\
+    \ function well.\n        See the solver options guide for setting additional\
+    \ parameters for each\n        of the solvers.\n\n        See the user guide for\
+    \ additional details on how the solver is chosen.\n\n    feature_rescaling : boolean,\
+    \ optional\n        Feature rescaling is an important pre-processing step that\
+    \ ensures that\n        all features are on the same scale. An l2-norm rescaling\
+    \ is performed\n        to make sure that all features are of the same norm. Categorical\n\
+    \        features are also rescaled by rescaling the dummy variables that are\n\
+    \        used to represent them. The coefficients are returned in original scale\n\
+    \        of the problem. This process is particularly useful when features\n \
+    \       vary widely in their ranges.\n\n    validation_set : SFrame, optional\n\
+    \n        A dataset for monitoring the model's generalization performance.\n \
+    \       For each row of the progress table, the chosen metrics are computed\n\
+    \        for both the provided training dataset and the validation_set. The\n\
+    \        format of this SFrame must be the same as the training set.\n       \
+    \ By default this argument is set to 'auto' and a validation set is\n        automatically\
+    \ sampled and used for progress printing. If\n        validation_set is set to\
+    \ None, then no additional metrics\n        are computed. The default value is\
+    \ 'auto'.\n\n    convergence_threshold : float, optional\n\n      Convergence\
+    \ is tested using variation in the training objective. The\n      variation in\
+    \ the training objective is calculated using the difference\n      between the\
+    \ objective values between two steps. Consider reducing this\n      below the\
+    \ default value (0.01) for a more accurately trained model.\n      Beware of overfitting\
+    \ (i.e a model that works well only on the training\n      data) if this parameter\
+    \ is set to a very low value.\n\n    lbfgs_memory_level : int, optional\n\n  \
+    \    The L-BFGS algorithm keeps track of gradient information from the\n     \
+    \ previous ``lbfgs_memory_level`` iterations. The storage requirement for\n  \
+    \    each of these gradients is the ``num_coefficients`` in the problem.\n   \
+    \   Increasing the ``lbfgs_memory_level`` can help improve the quality of\n  \
+    \    the model trained. Setting this to more than ``max_iterations`` has the\n\
+    \      same effect as setting it to ``max_iterations``.\n\n    max_iterations\
+    \ : int, optional\n\n      The maximum number of allowed passes through the data.\
+    \ More passes over\n      the data can result in a more accurately trained model.\
+    \ Consider\n      increasing this (the default value is 10) if the training accuracy\
+    \ is\n      low and the *Grad-Norm* in the display is large.\n\n    step_size\
+    \ : float, optional (fista only)\n\n      The starting step size to use for the\
+    \ ``fista`` and ``gd`` solvers. The\n      default is set to 1.0, this is an aggressive\
+    \ setting. If the first\n      iteration takes a considerable amount of time,\
+    \ reducing this parameter\n      may speed up model training.\n\n    verbose :\
+    \ bool, optional\n        If True, print progress updates.\n\n    Returns\n  \
+    \  -------\n    out : LinearRegression\n        A trained model of type\n    \
+    \    :class:`~turicreate.linear_regression.LinearRegression`.\n\n    See Also\n\
+    \    --------\n    LinearRegression, turicreate.boosted_trees_regression.BoostedTreesRegression,\
+    \ turicreate.regression.create\n\n    Notes\n    -----\n    - Categorical variables\
+    \ are encoded by creating dummy variables. For a\n      variable with :math:`K`\
+    \ categories, the encoding creates :math:`K-1` dummy\n      variables, while the\
+    \ first category encountered in the data is used as the\n      baseline.\n\n \
+    \   - For prediction and evaluation of linear regression models with sparse\n\
+    \      dictionary inputs, new keys/columns that were not seen during training\n\
+    \      are silently ignored.\n\n    - Any 'None' values in the data will result\
+    \ in an error being thrown.\n\n    - A constant term is automatically added for\
+    \ the model intercept. This term\n      is not regularized.\n\n    - Standard\
+    \ errors on coefficients are only available when `solver=newton`\n      or when\
+    \ the default `auto` solver option chooses the newton method and if\n      the\
+    \ number of examples in the training data is more than the number of\n      coefficients.\
+    \ If standard errors cannot be estimated, a column of `None`\n      values are\
+    \ returned.\n\n\n    References\n    ----------\n    - Hoerl, A.E. and Kennard,\
+    \ R.W. (1970) `Ridge regression: Biased Estimation\n      for Nonorthogonal Problems\n\
+    \      <http://amstat.tandfonline.com/doi/abs/10.1080/00401706.1970.10488634>`_.\n\
+    \      Technometrics 12(1) pp.55-67\n\n    - Tibshirani, R. (1996) `Regression\
+    \ Shrinkage and Selection via the Lasso <h\n      ttp://www.jstor.org/discover/10.2307/2346178?uid=3739256&uid=2&uid=4&sid=2\n\
+    \      1104169934983>`_. Journal of the Royal Statistical Society. Series B\n\
+    \      (Methodological) 58(1) pp.267-288.\n\n    - Zhu, C., et al. (1997) `Algorithm\
+    \ 778: L-BFGS-B: Fortran subroutines for\n      large-scale bound-constrained\
+    \ optimization\n      <https://dl.acm.org/citation.cfm?id=279236>`_. ACM Transactions\
+    \ on\n      Mathematical Software 23(4) pp.550-560.\n\n    - Barzilai, J. and\
+    \ Borwein, J. `Two-Point Step Size Gradient Methods\n      <http://imajna.oxfordjournals.org/content/8/1/141.short>`_.\
+    \ IMA Journal of\n      Numerical Analysis 8(1) pp.141-148.\n\n    - Beck, A.\
+    \ and Teboulle, M. (2009) `A Fast Iterative Shrinkage-Thresholding\n      Algorithm\
+    \ for Linear Inverse Problems\n      <http://epubs.siam.org/doi/abs/10.1137/080716542>`_.\
+    \ SIAM Journal on\n      Imaging Sciences 2(1) pp.183-202.\n\n    - Zhang, T.\
+    \ (2004) `Solving large scale linear prediction problems using\n      stochastic\
+    \ gradient descent algorithms\n      <https://dl.acm.org/citation.cfm?id=1015332>`_.\
+    \ ICML '04: Proceedings of\n      the twenty-first international conference on\
+    \ Machine learning p.116.\n\n\n    Examples\n    --------\n\n    Given an :class:`~turicreate.SFrame`\
+    \ ``sf`` with a list of columns\n    [``feature_1`` ... ``feature_K``] denoting\
+    \ features and a target column\n    ``target``, we can create a\n    :class:`~turicreate.linear_regression.LinearRegression`\
+    \ as follows:\n\n    >>> data =  turicreate.SFrame('https://static.turi.com/datasets/regression/houses.csv')\n\
+    \n    >>> model = turicreate.linear_regression.create(data, target='price',\n\
+    \    ...                                  features=['bath', 'bedroom', 'size'])\n\
+    \n\n    For ridge regression, we can set the ``l2_penalty`` parameter higher (the\n\
+    \    default is 0.01). For Lasso regression, we set the l1_penalty higher, and\n\
+    \    for elastic net, we set both to be higher.\n\n    .. sourcecode:: python\n\
+    \n      # Ridge regression\n      >>> model_ridge = turicreate.linear_regression.create(data,\
+    \ 'price', l2_penalty=0.1)\n\n      # Lasso\n      >>> model_lasso = turicreate.linear_regression.create(data,\
+    \ 'price', l2_penalty=0.,\n                                                  \
+    \                 l1_penalty=1.0)\n\n      # Elastic net regression\n      >>>\
+    \ model_enet  = turicreate.linear_regression.create(data, 'price', l2_penalty=0.5,\n\
+    \                                                                 l1_penalty=0.5)"
+  sentences:
+  - "def create(dataset, target, features=None, l2_penalty=1e-2, l1_penalty=0.0,\n\
+    \    solver='auto', feature_rescaling=True,\n    convergence_threshold = _DEFAULT_SOLVER_OPTIONS['convergence_threshold'],\n\
+    \    step_size = _DEFAULT_SOLVER_OPTIONS['step_size'],\n    lbfgs_memory_level\
+    \ = _DEFAULT_SOLVER_OPTIONS['lbfgs_memory_level'],\n    max_iterations = _DEFAULT_SOLVER_OPTIONS['max_iterations'],\n\
+    \    validation_set = \"auto\",\n    verbose=True):\n\n    \"\"\"\n    Create\
+    \ a :class:`~turicreate.linear_regression.LinearRegression` to\n    predict a\
+    \ scalar target variable as a linear function of one or more\n    features. In\
+    \ addition to standard numeric and categorical types, features\n    can also be\
+    \ extracted automatically from list- or dictionary-type SFrame\n    columns.\n\
+    \n    The linear regression module can be used for ridge regression, Lasso, and\n\
+    \    elastic net regression (see References for more detail on these methods).\
+    \ By\n    default, this model has an l2 regularization weight of 0.01.\n\n   \
+    \ Parameters\n    ----------\n    dataset : SFrame\n        The dataset to use\
+    \ for training the model.\n\n    target : string\n        Name of the column containing\
+    \ the target variable.\n\n    features : list[string], optional\n        Names\
+    \ of the columns containing features. 'None' (the default) indicates\n       \
+    \ that all columns except the target variable should be used as features.\n\n\
+    \        The features are columns in the input SFrame that can be of the\n   \
+    \     following types:\n\n        - *Numeric*: values of numeric type integer\
+    \ or float.\n\n        - *Categorical*: values of type string.\n\n        - *Array*:\
+    \ list of numeric (integer or float) values. Each list element\n          is treated\
+    \ as a separate feature in the model.\n\n        - *Dictionary*: key-value pairs\
+    \ with numeric (integer or float) values\n          Each key of a dictionary is\
+    \ treated as a separate feature and the\n          value in the dictionary corresponds\
+    \ to the value of the feature.\n          Dictionaries are ideal for representing\
+    \ sparse data.\n\n        Columns of type *list* are not supported. Convert such\
+    \ feature\n        columns to type array if all entries in the list are of numeric\n\
+    \        types. If the lists contain data of mixed types, separate\n        them\
+    \ out into different columns.\n\n    l2_penalty : float, optional\n        Weight\
+    \ on the l2-regularizer of the model. The larger this weight, the\n        more\
+    \ the model coefficients shrink toward 0. This introduces bias into\n        the\
+    \ model but decreases variance, potentially leading to better\n        predictions.\
+    \ The default value is 0.01; setting this parameter to 0\n        corresponds\
+    \ to unregularized linear regression. See the ridge\n        regression reference\
+    \ for more detail.\n\n    l1_penalty : float, optional\n        Weight on l1 regularization\
+    \ of the model. Like the l2 penalty, the\n        higher the l1 penalty, the more\
+    \ the estimated coefficients shrink toward\n        0. The l1 penalty, however,\
+    \ completely zeros out sufficiently small\n        coefficients, automatically\
+    \ indicating features that are not useful for\n        the model. The default\
+    \ weight of 0 prevents any features from being\n        discarded. See the LASSO\
+    \ regression reference for more detail.\n\n    solver : string, optional\n   \
+    \     Solver to use for training the model. See the references for more detail\n\
+    \        on each solver.\n\n        - *auto (default)*: automatically chooses\
+    \ the best solver for the data\n          and model parameters.\n        - *newton*:\
+    \ Newton-Raphson\n        - *lbfgs*: limited memory BFGS\n        - *fista*: accelerated\
+    \ gradient descent\n\n        The model is trained using a carefully engineered\
+    \ collection of methods\n        that are automatically picked based on the input\
+    \ data. The ``newton``\n        method  works best for datasets with plenty of\
+    \ examples and few features\n        (long datasets). Limited memory BFGS (``lbfgs``)\
+    \ is a robust solver for\n        wide datasets (i.e datasets with many coefficients).\
+    \  ``fista`` is the\n        default solver for l1-regularized linear regression.\
+    \  The solvers are\n        all automatically tuned and the default options should\
+    \ function well.\n        See the solver options guide for setting additional\
+    \ parameters for each\n        of the solvers.\n\n        See the user guide for\
+    \ additional details on how the solver is chosen.\n\n    feature_rescaling : boolean,\
+    \ optional\n        Feature rescaling is an important pre-processing step that\
+    \ ensures that\n        all features are on the same scale. An l2-norm rescaling\
+    \ is performed\n        to make sure that all features are of the same norm. Categorical\n\
+    \        features are also rescaled by rescaling the dummy variables that are\n\
+    \        used to represent them. The coefficients are returned in original scale\n\
+    \        of the problem. This process is particularly useful when features\n \
+    \       vary widely in their ranges.\n\n    validation_set : SFrame, optional\n\
+    \n        A dataset for monitoring the model's generalization performance.\n \
+    \       For each row of the progress table, the chosen metrics are computed\n\
+    \        for both the provided training dataset and the validation_set. The\n\
+    \        format of this SFrame must be the same as the training set.\n       \
+    \ By default this argument is set to 'auto' and a validation set is\n        automatically\
+    \ sampled and used for progress printing. If\n        validation_set is set to\
+    \ None, then no additional metrics\n        are computed. The default value is\
+    \ 'auto'.\n\n    convergence_threshold : float, optional\n\n      Convergence\
+    \ is tested using variation in the training objective. The\n      variation in\
+    \ the training objective is calculated using the difference\n      between the\
+    \ objective values between two steps. Consider reducing this\n      below the\
+    \ default value (0.01) for a more accurately trained model.\n      Beware of overfitting\
+    \ (i.e a model that works well only on the training\n      data) if this parameter\
+    \ is set to a very low value.\n\n    lbfgs_memory_level : int, optional\n\n  \
+    \    The L-BFGS algorithm keeps track of gradient information from the\n     \
+    \ previous ``lbfgs_memory_level`` iterations. The storage requirement for\n  \
+    \    each of these gradients is the ``num_coefficients`` in the problem.\n   \
+    \   Increasing the ``lbfgs_memory_level`` can help improve the quality of\n  \
+    \    the model trained. Setting this to more than ``max_iterations`` has the\n\
+    \      same effect as setting it to ``max_iterations``.\n\n    max_iterations\
+    \ : int, optional\n\n      The maximum number of allowed passes through the data.\
+    \ More passes over\n      the data can result in a more accurately trained model.\
+    \ Consider\n      increasing this (the default value is 10) if the training accuracy\
+    \ is\n      low and the *Grad-Norm* in the display is large.\n\n    step_size\
+    \ : float, optional (fista only)\n\n      The starting step size to use for the\
+    \ ``fista`` and ``gd`` solvers. The\n      default is set to 1.0, this is an aggressive\
+    \ setting. If the first\n      iteration takes a considerable amount of time,\
+    \ reducing this parameter\n      may speed up model training.\n\n    verbose :\
+    \ bool, optional\n        If True, print progress updates.\n\n    Returns\n  \
+    \  -------\n    out : LinearRegression\n        A trained model of type\n    \
+    \    :class:`~turicreate.linear_regression.LinearRegression`.\n\n    See Also\n\
+    \    --------\n    LinearRegression, turicreate.boosted_trees_regression.BoostedTreesRegression,\
+    \ turicreate.regression.create\n\n    Notes\n    -----\n    - Categorical variables\
+    \ are encoded by creating dummy variables. For a\n      variable with :math:`K`\
+    \ categories, the encoding creates :math:`K-1` dummy\n      variables, while the\
+    \ first category encountered in the data is used as the\n      baseline.\n\n \
+    \   - For prediction and evaluation of linear regression models with sparse\n\
+    \      dictionary inputs, new keys/columns that were not seen during training\n\
+    \      are silently ignored.\n\n    - Any 'None' values in the data will result\
+    \ in an error being thrown.\n\n    - A constant term is automatically added for\
+    \ the model intercept. This term\n      is not regularized.\n\n    - Standard\
+    \ errors on coefficients are only available when `solver=newton`\n      or when\
+    \ the default `auto` solver option chooses the newton method and if\n      the\
+    \ number of examples in the training data is more than the number of\n      coefficients.\
+    \ If standard errors cannot be estimated, a column of `None`\n      values are\
+    \ returned.\n\n\n    References\n    ----------\n    - Hoerl, A.E. and Kennard,\
+    \ R.W. (1970) `Ridge regression: Biased Estimation\n      for Nonorthogonal Problems\n\
+    \      <http://amstat.tandfonline.com/doi/abs/10.1080/00401706.1970.10488634>`_.\n\
+    \      Technometrics 12(1) pp.55-67\n\n    - Tibshirani, R. (1996) `Regression\
+    \ Shrinkage and Selection via the Lasso <h\n      ttp://www.jstor.org/discover/10.2307/2346178?uid=3739256&uid=2&uid=4&sid=2\n\
+    \      1104169934983>`_. Journal of the Royal Statistical Society. Series B\n\
+    \      (Methodological) 58(1) pp.267-288.\n\n    - Zhu, C., et al. (1997) `Algorithm\
+    \ 778: L-BFGS-B: Fortran subroutines for\n      large-scale bound-constrained\
+    \ optimization\n      <https://dl.acm.org/citation.cfm?id=279236>`_. ACM Transactions\
+    \ on\n      Mathematical Software 23(4) pp.550-560.\n\n    - Barzilai, J. and\
+    \ Borwein, J. `Two-Point Step Size Gradient Methods\n      <http://imajna.oxfordjournals.org/content/8/1/141.short>`_.\
+    \ IMA Journal of\n      Numerical Analysis 8(1) pp.141-148.\n\n    - Beck, A.\
+    \ and Teboulle, M. (2009) `A Fast Iterative Shrinkage-Thresholding\n      Algorithm\
+    \ for Linear Inverse Problems\n      <http://epubs.siam.org/doi/abs/10.1137/080716542>`_.\
+    \ SIAM Journal on\n      Imaging Sciences 2(1) pp.183-202.\n\n    - Zhang, T.\
+    \ (2004) `Solving large scale linear prediction problems using\n      stochastic\
+    \ gradient descent algorithms\n      <https://dl.acm.org/citation.cfm?id=1015332>`_.\
+    \ ICML '04: Proceedings of\n      the twenty-first international conference on\
+    \ Machine learning p.116.\n\n\n    Examples\n    --------\n\n    Given an :class:`~turicreate.SFrame`\
+    \ ``sf`` with a list of columns\n    [``feature_1`` ... ``feature_K``] denoting\
+    \ features and a target column\n    ``target``, we can create a\n    :class:`~turicreate.linear_regression.LinearRegression`\
+    \ as follows:\n\n    >>> data =  turicreate.SFrame('https://static.turi.com/datasets/regression/houses.csv')\n\
+    \n    >>> model = turicreate.linear_regression.create(data, target='price',\n\
+    \    ...                                  features=['bath', 'bedroom', 'size'])\n\
+    \n\n    For ridge regression, we can set the ``l2_penalty`` parameter higher (the\n\
+    \    default is 0.01). For Lasso regression, we set the l1_penalty higher, and\n\
+    \    for elastic net, we set both to be higher.\n\n    .. sourcecode:: python\n\
+    \n      # Ridge regression\n      >>> model_ridge = turicreate.linear_regression.create(data,\
+    \ 'price', l2_penalty=0.1)\n\n      # Lasso\n      >>> model_lasso = turicreate.linear_regression.create(data,\
+    \ 'price', l2_penalty=0.,\n                                                  \
+    \                 l1_penalty=1.0)\n\n      # Elastic net regression\n      >>>\
+    \ model_enet  = turicreate.linear_regression.create(data, 'price', l2_penalty=0.5,\n\
+    \                                                                 l1_penalty=0.5)\n\
+    \n    \"\"\"\n\n    # Regression model names.\n    model_name = \"regression_linear_regression\"\
+    \n    solver = solver.lower()\n\n    model = _sl.create(dataset, target, model_name,\
+    \ features=features,\n                        validation_set = validation_set,\n\
+    \                        solver = solver, verbose = verbose,\n               \
+    \         l2_penalty=l2_penalty, l1_penalty = l1_penalty,\n                  \
+    \      feature_rescaling = feature_rescaling,\n                        convergence_threshold\
+    \ = convergence_threshold,\n                        step_size = step_size,\n \
+    \                       lbfgs_memory_level = lbfgs_memory_level,\n           \
+    \             max_iterations = max_iterations)\n\n    return LinearRegression(model.__proxy__)"
+  - "def restore(self) -> None:\n        \"\"\"\n        Restore the backed-up (non-average)\
+    \ parameter values.\n        \"\"\"\n        for name, parameter in self._parameters:\n\
+    \            parameter.data.copy_(self._backups[name])"
+  - "def _get_sdict(self, env):\n        \"\"\"\n        Returns a dictionary mapping\
+    \ all of the source suffixes of all\n        src_builders of this Builder to the\
+    \ underlying Builder that\n        should be called first.\n\n        This dictionary\
+    \ is used for each target specified, so we save a\n        lot of extra computation\
+    \ by memoizing it for each construction\n        environment.\n\n        Note\
+    \ that this is re-computed each time, not cached, because there\n        might\
+    \ be changes to one of our source Builders (or one of their\n        source Builders,\
+    \ and so on, and so on...) that we can't \"see.\"\n\n        The underlying methods\
+    \ we call cache their computed values,\n        though, so we hope repeatedly\
+    \ aggregating them into a dictionary\n        like this won't be too big a hit.\
+    \  We may need to look for a\n        better way to do this if performance data\
+    \ show this has turned\n        into a significant bottleneck.\n        \"\"\"\
+    \n        sdict = {}\n        for bld in self.get_src_builders(env):\n       \
+    \     for suf in bld.src_suffixes(env):\n                sdict[suf] = bld\n  \
+    \      return sdict"
+- source_sentence: Traverse the tree below node looking for 'yield [expr]'.
+  sentences:
+  - "def retrieve_sources():\n    \"\"\"Retrieve sources using spectool\n    \"\"\"\
+    \n    spectool = find_executable('spectool')\n    if not spectool:\n        log.warn('spectool\
+    \ is not installed')\n        return\n    try:\n        specfile = spec_fn()\n\
+    \    except Exception:\n        return\n\n    cmd = [spectool, \"-g\", specfile]\n\
+    \    output = subprocess.check_output(' '.join(cmd), shell=True)\n    log.warn(output)"
+  - "def check_subscription(self, request):\n\t\t\"\"\"Redirect to the subscribe page\
+    \ if the user lacks an active subscription.\"\"\"\n\t\tsubscriber = subscriber_request_callback(request)\n\
+    \n\t\tif not subscriber_has_active_subscription(subscriber):\n\t\t\tif not SUBSCRIPTION_REDIRECT:\n\
+    \t\t\t\traise ImproperlyConfigured(\"DJSTRIPE_SUBSCRIPTION_REDIRECT is not set.\"\
+    )\n\t\t\treturn redirect(SUBSCRIPTION_REDIRECT)"
+  - "def is_generator(self, node):\n        \"\"\"Traverse the tree below node looking\
+    \ for 'yield [expr]'.\"\"\"\n        results = {}\n        if self.yield_expr.match(node,\
+    \ results):\n            return True\n        for child in node.children:\n  \
+    \          if child.type not in (syms.funcdef, syms.classdef):\n             \
+    \   if self.is_generator(child):\n                    return True\n        return\
+    \ False"
+- source_sentence: "Retrieves the content of an input given a DataSource. The input\
+    \ acts like a filter over the outputs of the DataSource.\n\n        Args:\n  \
+    \          name (str): The name of the input.\n            ds (openflow.DataSource):\
+    \ The DataSource that will feed the data.\n\n        Returns:\n            pandas.DataFrame:\
+    \ The content of the input."
+  sentences:
+  - "def valid_state(state: str) -> bool:\n    \"\"\"Validate State Argument\n\n \
+    \   Checks that either 'on' or 'off' was entered as an argument to the\n    CLI\
+    \ and make it lower case.\n\n    :param state: state to validate.\n\n    :returns:\
+    \ True if state is valid.\n\n    .. versionchanged:: 0.0.12\n        This moethod\
+    \ was renamed from validateState to valid_state to conform\n        to PEP-8.\
+    \ Also removed \"magic\" text for state and instead reference the\n        _VALID_STATES\
+    \ constant.\n    \"\"\"\n    lower_case_state = state.lower()\n\n    if lower_case_state\
+    \ in _VALID_STATES:\n        return True\n    return False"
+  - "def get_input(self, name, ds):\n        \"\"\"\n        Retrieves the content\
+    \ of an input given a DataSource. The input acts like a filter over the outputs\
+    \ of the DataSource.\n\n        Args:\n            name (str): The name of the\
+    \ input.\n            ds (openflow.DataSource): The DataSource that will feed\
+    \ the data.\n\n        Returns:\n            pandas.DataFrame: The content of\
+    \ the input.\n        \"\"\"\n        columns = self.inputs.get(name)\n      \
+    \  df = ds.get_dataframe()\n\n        # set defaults\n        for column in columns:\n\
+    \            if column not in df.columns:\n                df[column] = self.defaults.get(column)\n\
+    \n        return df[columns]"
+  - "def get_scenario_data(scenario_id,**kwargs):\n    \"\"\"\n        Get all the\
+    \ datasets from the group with the specified name\n        @returns a list of\
+    \ dictionaries\n    \"\"\"\n    user_id = kwargs.get('user_id')\n\n    scenario_data\
+    \ = db.DBSession.query(Dataset).filter(Dataset.id==ResourceScenario.dataset_id,\
+    \ ResourceScenario.scenario_id==scenario_id).options(joinedload_all('metadata')).distinct().all()\n\
+    \n    for sd in scenario_data:\n       if sd.hidden == 'Y':\n           try:\n\
+    \                sd.check_read_permission(user_id)\n           except:\n     \
+    \          sd.value      = None\n               sd.metadata = []\n\n    db.DBSession.expunge_all()\n\
+    \n    log.info(\"Retrieved %s datasets\", len(scenario_data))\n    return scenario_data"
+- source_sentence: "Split the data object along a given expression, in units.\n\n\
+    \        Parameters\n        ----------\n        expression : int or str\n   \
+    \         The expression to split along. If given as an integer, the axis at that\
+    \ index\n            is used.\n        positions : number-type or 1D array-type\n\
+    \            The position(s) to split at, in units.\n        units : str (optional)\n\
+    \            The units of the given positions. Default is same, which assumes\n\
+    \            input units are identical to first variable units.\n        parent\
+    \ : WrightTools.Collection (optional)\n            The parent collection in which\
+    \ to place the 'split' collection.\n            Default is a new Collection.\n\
+    \        verbose : bool (optional)\n            Toggle talkback. Default is True.\n\
+    \n        Returns\n        -------\n        WrightTools.collection.Collection\n\
+    \            A Collection of data objects.\n            The order of the objects\
+    \ is such that the axis points retain their original order.\n\n        See Also\n\
+    \        --------\n        chop\n            Divide the dataset into its lower-dimensionality\
+    \ components.\n        collapse\n            Collapse the dataset along one axis."
+  sentences:
+  - "def add_item(self, title, key, synonyms=None, description=None, img_url=None):\n\
+    \        \"\"\"Adds item to a list or carousel card.\n\n        A list must contain\
+    \ at least 2 items, each requiring a title and object key.\n\n        Arguments:\n\
+    \            title {str} -- Name of the item object\n            key {str} --\
+    \ Key refering to the item.\n                        This string will be used\
+    \ to send a query to your app if selected\n\n        Keyword Arguments:\n    \
+    \        synonyms {list} -- Words and phrases the user may send to select the\
+    \ item\n                              (default: {None})\n            description\
+    \ {str} -- A description of the item (default: {None})\n            img_url {str}\
+    \ -- URL of the image to represent the item (default: {None})\n        \"\"\"\n\
+    \        item = build_item(title, key, synonyms, description, img_url)\n     \
+    \   self._items.append(item)\n        return self"
+  - "def compare(a, b):\n    \"\"\"Compares two timestamps.\n\n    ``a`` and ``b``\
+    \ must be the same type, in addition to normal\n    representations of timestamps\
+    \ that order naturally, they can be rfc3339\n    formatted strings.\n\n    Args:\n\
+    \      a (string|object): a timestamp\n      b (string|object): another timestamp\n\
+    \n    Returns:\n      int: -1 if a < b, 0 if a == b or 1 if a > b\n\n    Raises:\n\
+    \      ValueError: if a or b are not the same type\n      ValueError: if a or\
+    \ b strings but not in valid rfc3339 format\n\n    \"\"\"\n    a_is_text = isinstance(a,\
+    \ basestring)\n    b_is_text = isinstance(b, basestring)\n    if type(a) != type(b)\
+    \ and not (a_is_text and b_is_text):\n        _logger.error(u'Cannot compare %s\
+    \ to %s, types differ %s!=%s',\n                      a, b, type(a), type(b))\n\
+    \        raise ValueError(u'cannot compare inputs of differing types')\n\n   \
+    \ if a_is_text:\n        a = from_rfc3339(a, with_nanos=True)\n        b = from_rfc3339(b,\
+    \ with_nanos=True)\n\n    if a < b:\n        return -1\n    elif a > b:\n    \
+    \    return 1\n    else:\n        return 0"
+  - "def split(\n        self, expression, positions, *, units=None, parent=None,\
+    \ verbose=True\n    ) -> wt_collection.Collection:\n        \"\"\"\n        Split\
+    \ the data object along a given expression, in units.\n\n        Parameters\n\
+    \        ----------\n        expression : int or str\n            The expression\
+    \ to split along. If given as an integer, the axis at that index\n           \
+    \ is used.\n        positions : number-type or 1D array-type\n            The\
+    \ position(s) to split at, in units.\n        units : str (optional)\n       \
+    \     The units of the given positions. Default is same, which assumes\n     \
+    \       input units are identical to first variable units.\n        parent : WrightTools.Collection\
+    \ (optional)\n            The parent collection in which to place the 'split'\
+    \ collection.\n            Default is a new Collection.\n        verbose : bool\
+    \ (optional)\n            Toggle talkback. Default is True.\n\n        Returns\n\
+    \        -------\n        WrightTools.collection.Collection\n            A Collection\
+    \ of data objects.\n            The order of the objects is such that the axis\
+    \ points retain their original order.\n\n        See Also\n        --------\n\
+    \        chop\n            Divide the dataset into its lower-dimensionality components.\n\
+    \        collapse\n            Collapse the dataset along one axis.\n        \"\
+    \"\"\n        # axis ------------------------------------------------------------------------------------\n\
+    \        old_expr = self.axis_expressions\n        old_units = self.units\n  \
+    \      out = wt_collection.Collection(name=\"split\", parent=parent)\n       \
+    \ if isinstance(expression, int):\n            if units is None:\n           \
+    \     units = self._axes[expression].units\n            expression = self._axes[expression].expression\n\
+    \        elif isinstance(expression, str):\n            pass\n        else:\n\
+    \            raise TypeError(\"expression: expected {int, str}, got %s\" % type(expression))\n\
+    \n        self.transform(expression)\n        if units:\n            self.convert(units)\n\
+    \n        try:\n            positions = [-np.inf] + sorted(list(positions)) +\
+    \ [np.inf]\n        except TypeError:\n            positions = [-np.inf, positions,\
+    \ np.inf]\n\n        values = self._axes[0].full\n        masks = [(values >=\
+    \ lo) & (values < hi) for lo, hi in wt_kit.pairwise(positions)]\n        omasks\
+    \ = []\n        cuts = []\n        for mask in masks:\n            try:\n    \
+    \            omasks.append(wt_kit.mask_reduce(mask))\n                cuts.append([i\
+    \ == 1 for i in omasks[-1].shape])\n                # Ensure at least one axis\
+    \ is kept\n                if np.all(cuts[-1]):\n                    cuts[-1][0]\
+    \ = False\n            except ValueError:\n                omasks.append(None)\n\
+    \                cuts.append(None)\n        for i in range(len(positions) - 1):\n\
+    \            out.create_data(\"split%03i\" % i)\n\n        for var in self.variables:\n\
+    \            for i, (imask, omask, cut) in enumerate(zip(masks, omasks, cuts)):\n\
+    \                if omask is None:\n                    # Zero length split\n\
+    \                    continue\n                omask = wt_kit.enforce_mask_shape(omask,\
+    \ var.shape)\n                omask.shape = tuple([s for s, c in zip(omask.shape,\
+    \ cut) if not c])\n                out_arr = np.full(omask.shape, np.nan)\n  \
+    \              imask = wt_kit.enforce_mask_shape(imask, var.shape)\n         \
+    \       out_arr[omask] = var[:][imask]\n                out[i].create_variable(values=out_arr,\
+    \ **var.attrs)\n\n        for ch in self.channels:\n            for i, (imask,\
+    \ omask, cut) in enumerate(zip(masks, omasks, cuts)):\n                if omask\
+    \ is None:\n                    # Zero length split\n                    continue\n\
+    \                omask = wt_kit.enforce_mask_shape(omask, ch.shape)\n        \
+    \        omask.shape = tuple([s for s, c in zip(omask.shape, cut) if not c])\n\
+    \                out_arr = np.full(omask.shape, np.nan)\n                imask\
+    \ = wt_kit.enforce_mask_shape(imask, ch.shape)\n                out_arr[omask]\
+    \ = ch[:][imask]\n                out[i].create_channel(values=out_arr, **ch.attrs)\n\
+    \n        if verbose:\n            for d in out.values():\n                try:\n\
+    \                    d.transform(expression)\n                except IndexError:\n\
+    \                    continue\n\n            print(\"split data into {0} pieces\
+    \ along <{1}>:\".format(len(positions) - 1, expression))\n            for i, (lo,\
+    \ hi) in enumerate(wt_kit.pairwise(positions)):\n                new_data = out[i]\n\
+    \                if new_data.shape == ():\n                    print(\"  {0} :\
+    \ None\".format(i))\n                else:\n                    new_axis = new_data.axes[0]\n\
+    \                    print(\n                        \"  {0} : {1:0.2f} to {2:0.2f}\
+    \ {3} {4}\".format(\n                            i, lo, hi, new_axis.units, new_axis.shape\n\
+    \                        )\n                    )\n\n        for d in out.values():\n\
+    \            try:\n                d.transform(*old_expr)\n                keep\
+    \ = []\n                keep_units = []\n                for ax in d.axes:\n \
+    \                   if ax.size > 1:\n                        keep.append(ax.expression)\n\
+    \                        keep_units.append(ax.units)\n                    else:\n\
+    \                        d.create_constant(ax.expression, verbose=False)\n   \
+    \             d.transform(*keep)\n                for ax, u in zip(d.axes, keep_units):\n\
+    \                    ax.convert(u)\n            except IndexError:\n         \
+    \       continue\n            tempax = Axis(d, expression)\n            if all(\n\
+    \                np.all(\n                    np.sum(~np.isnan(tempax.masked),\
+    \ axis=tuple(set(range(tempax.ndim)) - {j}))\n                    <= 1\n     \
+    \           )\n                for j in range(tempax.ndim)\n            ):\n \
+    \               d.create_constant(expression, verbose=False)\n        self.transform(*old_expr)\n\
+    \        for ax, u in zip(self.axes, old_units):\n            ax.convert(u)\n\n\
+    \        return out"
+pipeline_tag: sentence-similarity
+library_name: sentence-transformers
+metrics:
+- cosine_accuracy@1
+- cosine_accuracy@3
+- cosine_accuracy@5
+- cosine_accuracy@10
+- cosine_precision@1
+- cosine_precision@3
+- cosine_precision@5
+- cosine_precision@10
+- cosine_recall@1
+- cosine_recall@3
+- cosine_recall@5
+- cosine_recall@10
+- cosine_ndcg@10
+- cosine_mrr@10
+- cosine_map@100
+model-index:
+- name: SentenceTransformer based on benjamintli/modernbert-cosqa
+  results:
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: eval
+      type: eval
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.9480526153529956
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.9703010995786662
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.9751824067413422
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.9806803000719351
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.9480526153529956
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.32343369985955533
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.19503648134826843
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.09806803000719352
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.9480526153529956
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.9703010995786662
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.9751824067413422
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.9806803000719351
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.9652143122800294
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.9601788099886978
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.9606213024321194
+      name: Cosine Map@100
+---
+# SentenceTransformer based on benjamintli/modernbert-cosqa
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [benjamintli/modernbert-cosqa](https://huggingface.co/benjamintli/modernbert-cosqa). 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:** [benjamintli/modernbert-cosqa](https://huggingface.co/benjamintli/modernbert-cosqa) <!-- at revision 8d7c40aabc62d4956cab19aec28165b206d86790 -->
+- **Maximum Sequence Length:** 512 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/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': 'OptimizedModule'})
+  (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})
+)
+```
+## 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("modernbert-codesearchnet")
+# Run inference
+queries = [
+    "Split the data object along a given expression, in units.\n\n        Parameters\n        ----------\n        expression : int or str\n            The expression to split along. If given as an integer, the axis at that index\n            is used.\n        positions : number-type or 1D array-type\n            The position(s) to split at, in units.\n        units : str (optional)\n            The units of the given positions. Default is same, which assumes\n            input units are identical to first variable units.\n        parent : WrightTools.Collection (optional)\n            The parent collection in which to place the \u0027split\u0027 collection.\n            Default is a new Collection.\n        verbose : bool (optional)\n            Toggle talkback. Default is True.\n\n        Returns\n        -------\n        WrightTools.collection.Collection\n            A Collection of data objects.\n            The order of the objects is such that the axis points retain their original order.\n\n        See Also\n        --------\n        chop\n            Divide the dataset into its lower-dimensionality components.\n        collapse\n            Collapse the dataset along one axis.",
+]
+documents = [
+    'def split(\n        self, expression, positions, *, units=None, parent=None, verbose=True\n    ) -> wt_collection.Collection:\n        """\n        Split the data object along a given expression, in units.\n\n        Parameters\n        ----------\n        expression : int or str\n            The expression to split along. If given as an integer, the axis at that index\n            is used.\n        positions : number-type or 1D array-type\n            The position(s) to split at, in units.\n        units : str (optional)\n            The units of the given positions. Default is same, which assumes\n            input units are identical to first variable units.\n        parent : WrightTools.Collection (optional)\n            The parent collection in which to place the \'split\' collection.\n            Default is a new Collection.\n        verbose : bool (optional)\n            Toggle talkback. Default is True.\n\n        Returns\n        -------\n        WrightTools.collection.Collection\n            A Collection of data objects.\n            The order of the objects is such that the axis points retain their original order.\n\n        See Also\n        --------\n        chop\n            Divide the dataset into its lower-dimensionality components.\n        collapse\n            Collapse the dataset along one axis.\n        """\n        # axis ------------------------------------------------------------------------------------\n        old_expr = self.axis_expressions\n        old_units = self.units\n        out = wt_collection.Collection(name="split", parent=parent)\n        if isinstance(expression, int):\n            if units is None:\n                units = self._axes[expression].units\n            expression = self._axes[expression].expression\n        elif isinstance(expression, str):\n            pass\n        else:\n            raise TypeError("expression: expected {int, str}, got %s" % type(expression))\n\n        self.transform(expression)\n        if units:\n            self.convert(units)\n\n        try:\n            positions = [-np.inf] + sorted(list(positions)) + [np.inf]\n        except TypeError:\n            positions = [-np.inf, positions, np.inf]\n\n        values = self._axes[0].full\n        masks = [(values >= lo) & (values < hi) for lo, hi in wt_kit.pairwise(positions)]\n        omasks = []\n        cuts = []\n        for mask in masks:\n            try:\n                omasks.append(wt_kit.mask_reduce(mask))\n                cuts.append([i == 1 for i in omasks[-1].shape])\n                # Ensure at least one axis is kept\n                if np.all(cuts[-1]):\n                    cuts[-1][0] = False\n            except ValueError:\n                omasks.append(None)\n                cuts.append(None)\n        for i in range(len(positions) - 1):\n            out.create_data("split%03i" % i)\n\n        for var in self.variables:\n            for i, (imask, omask, cut) in enumerate(zip(masks, omasks, cuts)):\n                if omask is None:\n                    # Zero length split\n                    continue\n                omask = wt_kit.enforce_mask_shape(omask, var.shape)\n                omask.shape = tuple([s for s, c in zip(omask.shape, cut) if not c])\n                out_arr = np.full(omask.shape, np.nan)\n                imask = wt_kit.enforce_mask_shape(imask, var.shape)\n                out_arr[omask] = var[:][imask]\n                out[i].create_variable(values=out_arr, **var.attrs)\n\n        for ch in self.channels:\n            for i, (imask, omask, cut) in enumerate(zip(masks, omasks, cuts)):\n                if omask is None:\n                    # Zero length split\n                    continue\n                omask = wt_kit.enforce_mask_shape(omask, ch.shape)\n                omask.shape = tuple([s for s, c in zip(omask.shape, cut) if not c])\n                out_arr = np.full(omask.shape, np.nan)\n                imask = wt_kit.enforce_mask_shape(imask, ch.shape)\n                out_arr[omask] = ch[:][imask]\n                out[i].create_channel(values=out_arr, **ch.attrs)\n\n        if verbose:\n            for d in out.values():\n                try:\n                    d.transform(expression)\n                except IndexError:\n                    continue\n\n            print("split data into {0} pieces along <{1}>:".format(len(positions) - 1, expression))\n            for i, (lo, hi) in enumerate(wt_kit.pairwise(positions)):\n                new_data = out[i]\n                if new_data.shape == ():\n                    print("  {0} : None".format(i))\n                else:\n                    new_axis = new_data.axes[0]\n                    print(\n                        "  {0} : {1:0.2f} to {2:0.2f} {3} {4}".format(\n                            i, lo, hi, new_axis.units, new_axis.shape\n                        )\n                    )\n\n        for d in out.values():\n            try:\n                d.transform(*old_expr)\n                keep = []\n                keep_units = []\n                for ax in d.axes:\n                    if ax.size > 1:\n                        keep.append(ax.expression)\n                        keep_units.append(ax.units)\n                    else:\n                        d.create_constant(ax.expression, verbose=False)\n                d.transform(*keep)\n                for ax, u in zip(d.axes, keep_units):\n                    ax.convert(u)\n            except IndexError:\n                continue\n            tempax = Axis(d, expression)\n            if all(\n                np.all(\n                    np.sum(~np.isnan(tempax.masked), axis=tuple(set(range(tempax.ndim)) - {j}))\n                    <= 1\n                )\n                for j in range(tempax.ndim)\n            ):\n                d.create_constant(expression, verbose=False)\n        self.transform(*old_expr)\n        for ax, u in zip(self.axes, old_units):\n            ax.convert(u)\n\n        return out',
+    'def add_item(self, title, key, synonyms=None, description=None, img_url=None):\n        """Adds item to a list or carousel card.\n\n        A list must contain at least 2 items, each requiring a title and object key.\n\n        Arguments:\n            title {str} -- Name of the item object\n            key {str} -- Key refering to the item.\n                        This string will be used to send a query to your app if selected\n\n        Keyword Arguments:\n            synonyms {list} -- Words and phrases the user may send to select the item\n                              (default: {None})\n            description {str} -- A description of the item (default: {None})\n            img_url {str} -- URL of the image to represent the item (default: {None})\n        """\n        item = build_item(title, key, synonyms, description, img_url)\n        self._items.append(item)\n        return self',
+    'def compare(a, b):\n    """Compares two timestamps.\n\n    ``a`` and ``b`` must be the same type, in addition to normal\n    representations of timestamps that order naturally, they can be rfc3339\n    formatted strings.\n\n    Args:\n      a (string|object): a timestamp\n      b (string|object): another timestamp\n\n    Returns:\n      int: -1 if a < b, 0 if a == b or 1 if a > b\n\n    Raises:\n      ValueError: if a or b are not the same type\n      ValueError: if a or b strings but not in valid rfc3339 format\n\n    """\n    a_is_text = isinstance(a, basestring)\n    b_is_text = isinstance(b, basestring)\n    if type(a) != type(b) and not (a_is_text and b_is_text):\n        _logger.error(u\'Cannot compare %s to %s, types differ %s!=%s\',\n                      a, b, type(a), type(b))\n        raise ValueError(u\'cannot compare inputs of differing types\')\n\n    if a_is_text:\n        a = from_rfc3339(a, with_nanos=True)\n        b = from_rfc3339(b, with_nanos=True)\n\n    if a < b:\n        return -1\n    elif a > b:\n        return 1\n    else:\n        return 0',
+]
+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([[0.9188, 0.1817, 0.1583]])
+```
+<!--
+### 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.*
+-->
+## Evaluation
+### Metrics
+#### Information Retrieval
+* Dataset: `eval`
+* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
+| Metric              | Value      |
+|:--------------------|:-----------|
+| cosine_accuracy@1   | 0.9481     |
+| cosine_accuracy@3   | 0.9703     |
+| cosine_accuracy@5   | 0.9752     |
+| cosine_accuracy@10  | 0.9807     |
+| cosine_precision@1  | 0.9481     |
+| cosine_precision@3  | 0.3234     |
+| cosine_precision@5  | 0.195      |
+| cosine_precision@10 | 0.0981     |
+| cosine_recall@1     | 0.9481     |
+| cosine_recall@3     | 0.9703     |
+| cosine_recall@5     | 0.9752     |
+| cosine_recall@10    | 0.9807     |
+| **cosine_ndcg@10**  | **0.9652** |
+| cosine_mrr@10       | 0.9602     |
+| cosine_map@100      | 0.9606     |
+<!--
+## 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: 369,762 training samples
+* Columns: <code>query</code> and <code>positive</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | query                                                                             | positive                                                                            |
+  |:--------|:----------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|
+  | type    | string                                                                            | string                                                                              |
+  | details | <ul><li>min: 3 tokens</li><li>mean: 71.9 tokens</li><li>max: 512 tokens</li></ul> | <ul><li>min: 37 tokens</li><li>mean: 236.1 tokens</li><li>max: 512 tokens</li></ul> |
+* Samples:
+  | query                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                            | positive                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                         |
+  |:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+  | <code>Returns group object for datacenter root group.<br><br>		>>> clc.v2.Datacenter().RootGroup()<br>		<clc.APIv2.group.Group object at 0x105feacd0><br>		>>> print _<br>		WA1 Hardware</code>                                                                                                                                                                                                                                                                                                                                  | <code>def RootGroup(self):<br>		"""Returns group object for datacenter root group.<br><br>		>>> clc.v2.Datacenter().RootGroup()<br>		<clc.APIv2.group.Group object at 0x105feacd0><br>		>>> print _<br>		WA1 Hardware<br><br>		"""<br><br>		return(clc.v2.Group(id=self.root_group_id,alias=self.alias,session=self.session))</code>                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                             |
+  | <code>Calculate the euclidean distance of all array positions in "matchArr".<br><br>    :param matchArr: a dictionary of ``numpy.arrays`` containing at least two<br>        entries that are treated as cartesian coordinates.<br>    :param tKey: #TODO: docstring<br>    :param mKey: #TODO: docstring<br><br>    :returns: #TODO: docstring<br><br>            {'eucDist': numpy.array([eucDistance, eucDistance, ...]),<br>             'posPairs': numpy.array([[pos1, pos2], [pos1, pos2], ...])<br>             }</code> | <code>def calcDistMatchArr(matchArr, tKey, mKey):<br>    """Calculate the euclidean distance of all array positions in "matchArr".<br><br>    :param matchArr: a dictionary of ``numpy.arrays`` containing at least two<br>        entries that are treated as cartesian coordinates.<br>    :param tKey: #TODO: docstring<br>    :param mKey: #TODO: docstring<br><br>    :returns: #TODO: docstring<br><br>            {'eucDist': numpy.array([eucDistance, eucDistance, ...]),<br>             'posPairs': numpy.array([[pos1, pos2], [pos1, pos2], ...])<br>             }<br>    """<br>    #Calculate all sorted list of all eucledian feature distances<br>    matchArrSize = listvalues(matchArr)[0].size<br><br>    distInfo = {'posPairs': list(), 'eucDist': list()}<br>    _matrix = numpy.swapaxes(numpy.array([matchArr[tKey], matchArr[mKey]]), 0, 1)<br><br>    for pos1 in range(matchArrSize-1):<br>        for pos2 in range(pos1+1, matchArrSize):<br>            distInfo['posPairs'].append((pos1, pos2))<br>    distInfo['posPairs'] = numpy.array(distInfo['posPairs'])<br>    distInfo['eucD...</code> |
+  | <code>Format this verifier<br><br>        Returns:<br>            string: A formatted string</code>                                                                                                                                                                                                                                                                                                                                                                                                                              | <code>def format(self, indent_level, indent_size=4):<br>        """Format this verifier<br><br>        Returns:<br>            string: A formatted string<br>        """<br><br>        name = self.format_name('Literal', indent_size)<br><br>        if self.long_desc is not None:<br>            name += '\n'<br><br>        name += self.wrap_lines('value: %s\n' % str(self._literal), 1, indent_size)<br><br>        return self.wrap_lines(name, indent_level, indent_size)</code>                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                       |
+* Loss: [<code>CachedMultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cachedmultiplenegativesrankingloss) with these parameters:
+  ```json
+  {
+      "scale": 20.0,
+      "similarity_fct": "cos_sim",
+      "mini_batch_size": 64,
+      "gather_across_devices": false,
+      "directions": [
+          "query_to_doc"
+      ],
+      "partition_mode": "joint",
+      "hardness_mode": null,
+      "hardness_strength": 0.0
+  }
+  ```
+### Evaluation Dataset
+#### Unnamed Dataset
+* Size: 19,462 evaluation samples
+* Columns: <code>query</code> and <code>positive</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | query                                                                              | positive                                                                             |
+  |:--------|:-----------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------|
+  | type    | string                                                                             | string                                                                               |
+  | details | <ul><li>min: 3 tokens</li><li>mean: 71.05 tokens</li><li>max: 512 tokens</li></ul> | <ul><li>min: 40 tokens</li><li>mean: 236.22 tokens</li><li>max: 512 tokens</li></ul> |
+* Samples:
+  | query                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                         | positive                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                 |
+  |:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+  | <code>Create a new ParticipantInstance<br><br>        :param unicode attributes: An optional string metadata field you can use to store any data you wish.<br>        :param unicode twilio_address: The address of the Twilio phone number that the participant is in contact with.<br>        :param datetime date_created: The date that this resource was created.<br>        :param datetime date_updated: The date that this resource was last updated.<br>        :param unicode identity: A unique string identifier for the session participant as Chat User.<br>        :param unicode user_address: The address of the participant's device.<br><br>        :returns: Newly created ParticipantInstance<br>        :rtype: twilio.rest.messaging.v1.session.participant.ParticipantInstance</code> | <code>def create(self, attributes=values.unset, twilio_address=values.unset,<br>               date_created=values.unset, date_updated=values.unset,<br>               identity=values.unset, user_address=values.unset):<br>        """<br>        Create a new ParticipantInstance<br><br>        :param unicode attributes: An optional string metadata field you can use to store any data you wish.<br>        :param unicode twilio_address: The address of the Twilio phone number that the participant is in contact with.<br>        :param datetime date_created: The date that this resource was created.<br>        :param datetime date_updated: The date that this resource was last updated.<br>        :param unicode identity: A unique string identifier for the session participant as Chat User.<br>        :param unicode user_address: The address of the participant's device.<br><br>        :returns: Newly created ParticipantInstance<br>        :rtype: twilio.rest.messaging.v1.session.participant.ParticipantInstance<br>        """<br>        data = values.o...</code> |
+  | <code>It returns absolute url defined by node related to this page</code>                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                     | <code>def get_absolute_url(self):<br>        """<br>        It returns absolute url defined by node related to this page<br>        """<br>        try:<br>            node = Node.objects.select_related().filter(page=self)[0]<br>            return node.get_absolute_url()<br>        except Exception, e:<br>            raise ValueError(u"Error in {0}.{1}: {2}".format(self.__module__, self.__class__.__name__, e))<br>            return u""</code>                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                            |
+  | <code>Return the current scaled font.<br><br>        :return:<br>            A new :class:`ScaledFont` object,<br>            wrapping an existing cairo object.</code>                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                       | <code>def get_scaled_font(self):<br>        """Return the current scaled font.<br><br>        :return:<br>            A new :class:`ScaledFont` object,<br>            wrapping an existing cairo object.<br><br>        """<br>        return ScaledFont._from_pointer(<br>            cairo.cairo_get_scaled_font(self._pointer), incref=True)</code>                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  |
+* Loss: [<code>CachedMultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cachedmultiplenegativesrankingloss) with these parameters:
+  ```json
+  {
+      "scale": 20.0,
+      "similarity_fct": "cos_sim",
+      "mini_batch_size": 64,
+      "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`: 8192
+- `num_train_epochs`: 1
+- `learning_rate`: 2e-06
+- `warmup_steps`: 0.1
+- `bf16`: True
+- `eval_strategy`: epoch
+- `per_device_eval_batch_size`: 8192
+- `push_to_hub`: True
+- `hub_model_id`: modernbert-codesearchnet
+- `load_best_model_at_end`: True
+- `dataloader_num_workers`: 4
+- `batch_sampler`: no_duplicates
+#### All Hyperparameters
+<details><summary>Click to expand</summary>
+- `per_device_train_batch_size`: 8192
+- `num_train_epochs`: 1
+- `max_steps`: -1
+- `learning_rate`: 2e-06
+- `lr_scheduler_type`: linear
+- `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`: True
+- `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`: False
+- `project`: huggingface
+- `trackio_space_id`: trackio
+- `eval_strategy`: epoch
+- `per_device_eval_batch_size`: 8192
+- `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`: True
+- `hub_private_repo`: None
+- `hub_model_id`: modernbert-codesearchnet
+- `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`: False
+- `dataloader_num_workers`: 4
+- `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_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`: {}
+</details>
+### Training Logs
+| Epoch   | Step   | Training Loss | Validation Loss | eval_cosine_ndcg@10 |
+|:-------:|:------:|:-------------:|:---------------:|:-------------------:|
+| 0.2174  | 10     | 0.9210        | -               | -                   |
+| 0.4348  | 20     | 0.6679        | -               | -                   |
+| 0.6522  | 30     | 0.5007        | -               | -                   |
+| 0.8696  | 40     | 0.4181        | -               | -                   |
+| **1.0** | **46** | **-**         | **0.0328**      | **0.9652**          |
+* The bold row denotes the saved checkpoint.
+### Framework Versions
+- Python: 3.12.12
+- Sentence Transformers: 5.3.0
+- Transformers: 5.3.0
+- PyTorch: 2.10.0+cu128
+- Accelerate: 1.13.0
+- Datasets: 4.8.2
+- Tokenizers: 0.22.2
+## 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",
+}
+```
+#### CachedMultipleNegativesRankingLoss
+```bibtex
+@misc{gao2021scaling,
+    title={Scaling Deep Contrastive Learning Batch Size under Memory Limited Setup},
+    author={Luyu Gao and Yunyi Zhang and Jiawei Han and Jamie Callan},
+    year={2021},
+    eprint={2101.06983},
+    archivePrefix={arXiv},
+    primaryClass={cs.LG}
+}
+```
+<!--
+## 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.*
+-->

config_sentence_transformers.json ADDED Viewed

	@@ -0,0 +1,14 @@

+{
+  "model_type": "SentenceTransformer",
+  "__version__": {
+    "sentence_transformers": "5.3.0",
+    "transformers": "5.3.0",
+    "pytorch": "2.10.0+cu128"
+  },
+  "prompts": {
+    "query": "",
+    "document": ""
+  },
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine"
+}

modules.json ADDED Viewed

	@@ -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 ADDED Viewed

	@@ -0,0 +1,4 @@

+{
+    "max_seq_length": 512,
+    "do_lower_case": false
+}