Add new SentenceTransformer model

1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+    "word_embedding_dimension": 768,
+    "pooling_mode_cls_token": true,
+    "pooling_mode_mean_tokens": false,
+    "pooling_mode_max_tokens": false,
+    "pooling_mode_mean_sqrt_len_tokens": false,
+    "pooling_mode_weightedmean_tokens": false,
+    "pooling_mode_lasttoken": false,
+    "include_prompt": true
+}

README.md

@@ -0,0 +1,1097 @@
+---
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- dense
+- generated_from_trainer
+- dataset_size:4500
+- loss:MatryoshkaLoss
+- loss:MultipleNegativesRankingLoss
+base_model: ibm-granite/granite-embedding-english-r2
+widget:
+- source_sentence: You are tasked with creating a module in Elm to render an article
+    document. The module should include functions to render the body, navigation,
+    main content, titles, headings, subheadings, paragraphs, code blocks, images,
+    and references. You need to define the necessary types and functions to achieve
+    this.
+  sentences:
+  - '4605'
+  - "Context: \nAnswer: ```elm\nmodule ArticleRenderer exposing (Rendered, renderDocument,\
+    \ body, navigation, mainContent, title, heading, subheading, paragraph, codeBlock,\
+    \ imageBlock, renderReference)\n\nimport Html exposing (Html, div, nav, main,\
+    \ h1, h2, h3, p, img, pre, figure, a, span)\nimport Html.Attributes exposing (style,\
+    \ src, href, target, rel, hidden, type_)\nimport Html.Styled.Attributes as Attributes\
+    \ exposing (css)\nimport Document exposing (Inline, FlatInline, Key, Text, Link,\
+    \ Reference, Code, Image)\n\n\ntype alias Rendered msg =\n    Html msg\n\n\n--\
+    \ Navigation\nnavigation : Rendered msg\nnavigation =\n    Html.nav\n        [\
+    \ css [ Css.marginBottom (rem 1) ]\n        ]\n        [ navLink \"Go back to\
+    \ overview\" Route.Index\n        ]\n\n\nnavLink : String -> Route -> Rendered\
+    \ msg\nnavLink text route =\n    viewLink\n        { url = Route.toPath route\n\
+    \        , text = [ Html.text text ]\n        , styles = [ Css.fontStyle Css.italic\
+    \ ]\n        }\n\n\n-- Document rendering\nrenderDocument : Article -> Rendered\
+    \ msg\nrenderDocument article =\n    article.document\n        |> List.map renderBlock\n\
+    \        |> document\n\n\nrenderBlock : Block -> Rendered msg\nrenderBlock block\
+    \ =\n    case block of\n        Title content ->\n            title content\n\n\
+    \        Heading contents ->\n            heading contents\n\n        Subheading\
+    \ contents ->\n            subheading contents\n\n        Paragraph contents ->\n\
+    \            paragraph [] contents\n\n        CodeBlock code ->\n            codeBlock\
+    \ code\n\n        ImageBlock image ->\n            imageBlock image\n\n\n-- Landmarks\n\
+    body : List (Rendered msg) -> Rendered msg\nbody content =\n    Html.div\n   \
+    \     [ css\n            [ Css.padding (rem 1)\n            , Css.maxWidth (rem\
+    \ 48)\n            , Css.margin Css.auto\n            ]\n        ]\n        content\n\
+    \n\nmainContent : List (Rendered msg) -> Rendered msg\nmainContent contents =\n\
+    \    Html.main_ [] contents\n\n\n-- Text\ntitle : String -> Rendered msg\ntitle\
+    \ text =\n    Html.h1\n        [ css\n            [ headingStyle\n           \
+    \ , Css.fontSize (rem 1.5)\n            ]\n        ]\n        [ Html.text text\
+    \ ]\n\n\nheading : List (Inline Path) -> Rendered msg\nheading contents =\n  \
+    \  Html.h2\n        [ css\n            [ headingStyle\n            , Css.fontSize\
+    \ (rem 1.25)\n            ]\n        ]\n        (List.map renderInline contents)\n\
+    \n\nsubheading : List (Inline Path) -> Rendered msg\nsubheading contents =\n \
+    \   Html.h3\n        [ css\n            [ headingStyle\n            , Css.fontSize\
+    \ (rem 1.1)\n            ]\n        ]\n        (List.map renderInline contents)\n\
+    \n\nparagraph : List Css.Style -> List (Inline Path) -> Rendered msg\nparagraph\
+    \ styles content =\n    Html.p\n        [ css (paragraphStyle :: styles)\n   \
+    \     ]\n        (List.map renderInline content)\n\n\ncodeBlock : Document.Code\
+    \ -> Rendered msg\ncodeBlock code =\n    Html.pre [ css [ codeBackgroundStyle,\
+    \ Css.padding (em 1) ] ]\n        [ Html.code [ css [ codeFontStyle ] ] [ Html.text\
+    \ code.src ] ]\n\n\nimageBlock : Document.Image Path -> Rendered msg\nimageBlock\
+    \ image =\n    Html.figure\n        [ css\n            [ Css.margin2 paragraphSpacing\
+    \ zero\n            , framedStyle\n            ]\n        ]\n        [ Html.a\n\
+    \            [ Attributes.href <| Path.toAbsolute image.fallbackSource.source.src\n\
+    \            , Attributes.target \"_blank\"\n            , Attributes.rel \"noopener\"\
+    \n            ]\n            [ Html.img\n                [ Attributes.src (Path.toAbsolute\
+    \ image.fallbackSource.source.src)\n                , Attributes.alt image.alt\n\
+    \                , Attributes.width image.fallbackSource.source.width\n      \
+    \          , Attributes.height image.fallbackSource.source.height\n          \
+    \      , css\n                    [ Css.display Css.block\n                  \
+    \  , Css.maxWidth (pct 100)\n                    , Css.width (pct 100)\n     \
+    \               , Css.height Css.auto\n                    ]\n               \
+    \ ]\n            ]\n        , Html.figcaption\n            [ css\n           \
+    \     [ Css.boxSizing Css.borderBox\n                , Css.width (pct 100)\n \
+    \               , Css.padding (rem 0.5)\n                ]\n            ]\n  \
+    \          [ Html.text image.caption ]\n        ]\n\n\n-- Text styles\nheadingStyle\
+    \ : Css.Style\nheadingStyle =\n    Css.batch\n        [ headingFontFamily\n  \
+    \      , Css.fontWeight Css.bold\n        , Css.margin zero\n        , Css.lineHeight\
+    \ (num 1.2)\n        ]\n\n\nparagraphStyle : Css.Style\nparagraphStyle =\n   \
+    \ Css.batch\n        [ paragraphFontStyle\n        , Css.margin zero\n       \
+    \ ]\n\n\ncodeFontStyle : Css.Style\ncodeFontStyle =\n    Css.batch\n        [\
+    \ Css.whiteSpace Css.preWrap\n        , Css.fontFamilies [ \"Source Code Pro\"\
+    , \"monospace\" ]\n        ]\n\n\ncodeBackgroundStyle : Css.Style\ncodeBackgroundStyle\
+    \ =\n    Css.batch\n        [ Css.borderRadius (em 0.2)\n        , Css.backgroundColor\
+    \ (Css.hsla 0 0 0.5 0.15)\n        , Css.padding2 (em 0.05) (em 0.2)\n       \
+    \ , Css.fontSize (em 0.95)\n        ]\n\n\nframedStyle : Css.Style\nframedStyle\
+    \ =\n    let\n        spacing =\n            0.5\n    in\n    Css.batch\n    \
+    \    [ framedBorderStyle\n        , Css.borderRadius (rem spacing)\n        ]\n\
+    \n\nframedBorderStyle : Css.Style\nframedBorderStyle =\n    Css.border3 (px 1)\
+    \ Css.solid borderColor\n\n\nparagraphSpacing : Css.Rem\nparagraphSpacing =\n\
+    \    rem 1\n\n\nborderColor : Css.Color\nborderColor =\n    Css.hsla 0 0 0 0.25\n\
+    \n\nparagraphFontStyle : Css.Style\nparagraphFontStyle =\n    Css.batch\n    \
+    \    [ Css.lineHeight (num 1.35)\n        ]\n\n\n-- Helper functions\nrenderInline\
+    \ : Inline Path -> Rendered msg\nrenderInline inline =\n    case inline of\n \
+    \       TextInline text ->\n            renderText [] text\n\n        LinkInline\
+    \ link ->\n            renderLink link\n\n        ReferenceInline reference ->\n\
+    \            renderReference reference\n\n        CodeInline code ->\n       \
+    \     renderCode code\n\n        KeysInline keys ->\n            renderKeys keys\n\
+    \n\nrenderText : List Css.Style -> Text -> Rendered msg\nrenderText extraStyles\
+    \ text =\n    let\n        italic =\n            if text.style.emphasized then\n\
+    \                [ Css.fontStyle Css.italic ]\n\n            else\n          \
+    \      []\n\n        styles =\n            italic ++ extraStyles\n    in\n   \
+    \ if text.style.emphasized then\n        Html.em [ css styles ] [ Html.text text.content\
+    \ ]\n\n    else if List.isEmpty styles then\n        Html.text text.content\n\n\
+    \    else\n        Html.span [ css styles ] [ Html.text text.content ]\n\n\nrenderLink\
+    \ : Link -> Rendered msg\nrenderLink link =\n    viewLink\n        { text = List.map\
+    \ (renderText []) link.text\n        , url = Url.toString link.url\n        ,\
+    \ styles = []\n        }\n\n\nviewLink : { text : List (Rendered msg), url : String,\
+    \ styles : List Css.Style } -> Rendered msg\nviewLink { text, url, styles } =\n\
+    \    let\n        unvisitedColor =\n            Css.rgb 22 22 162\n\n        visitedColor\
+    \ =\n            Css.inherit\n    in\n    Html.a\n        [ Attributes.href url\n\
+    \        , css\n            ([ Css.color unvisitedColor\n             , Css.visited\n\
+    \                [ Css.color visitedColor\n                ]\n             , hover\n\
+    \                [ Css.textDecorationStyle Css.dotted\n                ]\n   \
+    \          ]\n                ++ styles\n            )\n        ]\n        text\n\
+    \n\nrenderReference : Reference Path -> Rendered msg\nrenderReference reference\
+    \ =\n    viewLink\n        { text =\n            List.map\n                (renderText\n\
+    \                    [ Css.fontWeight Css.bold\n                    , Css.fontSize\
+    \ (em 0.8)\n                    ]\n                )\n                reference.text\n\
+    \        , url = Path.toAbsolute reference.path\n        , styles = []\n     \
+    \   }\n\n\nrenderCode : Code -> Rendered msg\nrenderCode code =\n    Html.code\n\
+    \        [ css [ codeFontStyle, codeBackgroundStyle ]\n        ]\n        [ Html.text\
+    \ code.src ]\n\n\nrenderKeys : Keys -> Rendered msg\nrenderKeys keys =\n    case\
+    \ keys of\n        ( first, [] ) ->\n            renderKey first\n\n        (\
+    \ first, rest ) ->\n            Html.kbd [ css [ Css.whiteSpace Css.preWrap ]\
+    \ ]\n                (List.map renderKey (first :: rest)\n                   \
+    \ |> List.intersperse (Html.text \"+\\u{200B}\")\n                )\n\n\nrenderKey\
+    \ : Key -> Rendered msg\nrenderKey key =\n    let\n        keyBorderColor =\n\
+    \            Css.hsl 0 0 0.75\n\n        keyText =\n            case key of\n\
+    \                Letter l ->\n                    String.fromChar l\n\n      \
+    \          Ctrl ->\n                    \"Ctrl\"\n\n                Shift ->\n\
+    \                    \"Shift\\u{00A0}⇧\"\n\n                Enter ->\n       \
+    \             \"Enter\\u{00A0}↵\"\n\n                Tab ->\n                \
+    \    \"Tab\\u{00A0}↹\"\n\n                Up ->\n                    \"↑\\u{00A0}up\"\
+    \n\n                Down ->\n                    \"↓\\u{00A0}down\"\n    in\n\
+    \    Html.kbd\n        [ css\n            [ codeFontStyle\n            , Css.fontSize\
+    \ (em 0.8)\n            , Css.padding2 (em 0) (em 0.1)\n            , Css.border3\
+    \ (px 1) Css.solid keyBorderColor\n            , Css.borderRadius (em 0.2)\n \
+    \           , Css.boxShadow5 Css.inset zero (px -1) zero keyBorderColor\n    \
+    \        , Css.verticalAlign Css.center\n            , Css.whiteSpace Css.pre\n\
+    \            ]\n        ]\n        [ Html.text keyText ]\n```"
+  - "Context: \nAnswer: 40"
+- source_sentence: 'You are tasked with creating a graded object in a category `C`
+    using a type `β`. A graded object over `C` is essentially a function `β → C` into
+    the objects of `C`. Your goal is to define the `graded_object` in a category,
+    where you will project the `i`-th component of the graded object and create a
+    shift functor on the graded objects. Additionally, you need to construct the total
+    functor `graded_object β C ⥤ C` and prove that it is faithful.
+
+
+    Write a program that accomplishes the following tasks:
+
+    1. Define the graded object in a category.
+
+    2. Create a shift functor on the graded objects.
+
+    3. Construct the total functor and prove that it is faithful.'
+  sentences:
+  - "Context: \nAnswer: 33"
+  - '1514'
+  - "Context: \nAnswer: ```haskell\nimport algebra.group.basic\nimport category_theory.pi.basic\n\
+    import category_theory.shift\n\nnamespace category_theory\n\nuniverses w v u\n\
+    \ndef graded_object (β : Type w) (C : Type u) : Type (max w u) := β → C\n\ninstance\
+    \ inhabited_graded_object (β : Type w) (C : Type u) [inhabited C] :\n  inhabited\
+    \ (graded_object β C) :=\n⟨λ b, inhabited.default C⟩\n\ninstance category_of_graded_objects\
+    \ (β : Type w) : category.{(max w v)} (graded_object β C) :=\ncategory_theory.pi\
+    \ (λ _, C)\n\ndef eval {β : Type w} (b : β) : graded_object β C ⥤ C :=\n{ obj\
+    \ := λ X, X b,\n  map := λ X Y f, f b }\n\nsection\nvariable (C)\n\ndef comap_eq\
+    \ {β γ : Type w} {f g : β → γ} (h : f = g) : comap (λ _, C) f ≅ comap (λ _, C)\
+    \ g :=\n{ hom := { app := λ X b, eq_to_hom begin dsimp [comap], subst h, end },\n\
+    \  inv := { app := λ X b, eq_to_hom begin dsimp [comap], subst h, end }, }\n\n\
+    lemma comap_eq_symm {β γ : Type w} {f g : β → γ} (h : f = g) :\n  comap_eq C h.symm\
+    \ = (comap_eq C h).symm :=\nby tidy\n\nlemma comap_eq_trans {β γ : Type w} {f\
+    \ g h : β → γ} (k : f = g) (l : g = h) :\n  comap_eq C (k.trans l) = comap_eq\
+    \ C k ≪≫ comap_eq C l :=\nbegin\n  ext X b,\n  simp,\nend\n\ndef comap_equiv {β\
+    \ γ : Type w} (e : β ≃ γ) :\n  (graded_object β C) ≌ (graded_object γ C) :=\n\
+    { functor := comap (λ _, C) (e.symm : γ → β),\n  inverse := comap (λ _, C) (e\
+    \ : β → γ),\n  counit_iso := (comap_comp (λ _, C) _ _).trans (comap_eq C (by {\
+    \ ext, simp } )),\n  unit_iso := (comap_eq C (by { ext, simp } )).trans (comap_comp\
+    \ _ _ _).symm,\n  functor_unit_iso_comp' := λ X, by { ext b, dsimp, simp, } }\n\
+    \nend\n\ninstance has_shift {β : Type*} [add_comm_group β] (s : β) :\n  has_shift\
+    \ (graded_object_with_shift s C) :=\n{ shift := comap_equiv C\n  { to_fun := λ\
+    \ b, b-s,\n    inv_fun := λ b, b+s,\n    left_inv := λ x, (by simp),\n    right_inv\
+    \ := λ x, (by simp), } }\n\ninstance has_zero_morphisms [has_zero_morphisms C]\
+    \ (β : Type w) :\n  has_zero_morphisms.{(max w v)} (graded_object β C) :=\n{ has_zero\
+    \ := λ X Y,\n  { zero := λ b, 0 } }\n\nlemma zero_apply [has_zero_morphisms C]\
+    \ (β : Type w) (X Y : graded_object β C) (b : β) :\n  (0 : X ⟶ Y) b = 0 := rfl\n\
+    \nopen_locale zero_object\n\ninstance has_zero_object [has_zero_object C] [has_zero_morphisms\
+    \ C] (β : Type w) :\n  has_zero_object.{(max w v)} (graded_object β C) :=\n{ zero\
+    \ := λ b, (0 : C),\n  unique_to := λ X, ⟨⟨λ b, 0⟩, λ f, (by ext)⟩,\n  unique_from\
+    \ := λ X, ⟨⟨λ b, 0⟩, λ f, (by ext)⟩, } }\n\nvariables (β : Type)\nvariables (C\
+    \ : Type u) [category.{v} C]\nvariables [has_coproducts C]\n\ndef total : graded_object\
+    \ β C ⥤ C :=\n{ obj := λ X, ∐ (λ i : ulift.{v} β, X i.down),\n  map := λ X Y f,\
+    \ limits.sigma.map (λ i, f i.down) }\n\ninstance : faithful (total β C) :=\n{\
+    \ map_injective' := λ X Y f g w,\n  begin\n    classical,\n    ext i,\n    replace\
+    \ w := sigma.ι (λ i : ulift.{v} β, X i.down) ⟨i⟩ ≫= w,\n    erw [colimit.ι_map,\
+    \ colimit.ι_map] at w,\n    exact mono.right_cancellation _ _ w,\n  end }\n\n\
+    end graded_object\n```"
+- source_sentence: 'You are required to implement a CUDA kernel function for deterministic
+    devoxelization. The function takes input features of size (n, c), indices of size
+    (N, 8), weight of size (N, 8), and is expected to produce output features of size
+    (N, c). The kernel function should be able to perform the following steps:
+
+    1. Calculate the index based on the thread and block dimensions.
+
+    2. Iterate through each value of i (less than N) and j (less than c).
+
+    3. Access the corresponding indices, weight, and feat based on the current iteration.
+
+    4. Perform a calculation involving the indices, weight, and feat arrays to populate
+    the output array.'
+  sentences:
+  - "Context: \nAnswer: -15"
+  - "Context: \nAnswer: ```c\n#include <stdio.h>\n#include <stdlib.h>\n#include <thrust/device_vector.h>\n\
+    #include \"../common/gpu.cuh\"\n\n__global__ void deterministic_devoxelize_kernel(int\
+    \ N, int c, const int *__restrict__ indices, const float *__restrict__ weight,\
+    \ const float *__restrict__ feat, float *__restrict__ out){\n    int index = blockIdx.x\
+    \ * blockDim.x + threadIdx.x;\n    int i = index / c;\n    int j = index % c;\n\
+    \    \n    if(i < N){\n        const int* indices_ = indices + 8 * i;\n      \
+    \  const float *weight_ = weight + 8 * i;\n        const float *feat_ = feat +\
+    \ j;\n        \n        float cur_feat;\n        for(int k = 0; k < 8; k++){\n\
+    \            cur_feat = (indices_[k] >= 0) ? feat_[indices_[k] * c]  : 0; \n \
+    \           out[i * c + j] += weight_[k] * cur_feat;\n        }\n    }\n}\n\n\
+    void deterministic_devoxelize_wrapper(int N, int c, const int * indices, const\
+    \ float * weight, const float * feat, float * out){\n    deterministic_devoxelize_kernel<<<N,\
+    \ c>>>(N, c, indices, weight, feat, out);\n}\n```\nPlease note that the solution\
+    \ provided is a CUDA kernel function for deterministic devoxelization, along with\
+    \ a wrapper function for easier usage."
+  - '4073'
+- source_sentence: 'You are tasked with implementing a grayscale morphological operation
+    with flat linear structuring elements in C++ using the CUDA framework. Your function
+    should take in an input volume, step vectors for line segments, the number of
+    steps for line segments, an operation to perform, and the block size for GPU processing.
+    The input volume is a numeric array, the lineSteps parameter is an int32 matrix
+    representing step vectors for line segments, and the lineLens parameter is an
+    int32 vector representing the number of steps for line segments.
+
+
+    Your function should validate the inputs and ensure that the number of steps vectors
+    and step lengths are equal. It should then allocate an output volume and extract
+    line segments from the input parameters. Finally, your function should perform
+    the specified morphological operation using flat linear structuring elements and
+    return the output volume with the result of the operation.'
+  sentences:
+  - '3896'
+  - "Context: \nAnswer: SMTP is a push protocol for sending emails, while IMAP (Internet\
+    \ Message Access Protocol) is a pull protocol for retrieving emails from a server.\
+    \ IMAP allows users to manage emails on the server (e.g., filtering, searching),\
+    \ whereas SMTP only transmits messages. IMAP is preferred for client access because\
+    \ it enables asynchronous retrieval, supports offline use, and maintains email\
+    \ state across devices, unlike SMTP's stateless nature."
+  - "Context: \nAnswer: ```cpp\n#include <stdexcept>\n#include <vector>\n\n#include\
+    \ \"mex.h\"\n\n#include \"view.cuh\"\n#include \"morph.cuh\"\n#include \"strel.cuh\"\
+    \n#include \"flat_linear_morph.cuh\"\n\n#include \"mex_common.cuh\"\n\ntemplate\
+    \ <class Ty>\nvoid flatLinearMorphOp(mxArray *mxRes, const mxArray *mxVol, const\
+    \ std::vector<gpho::LineSeg>& lines,\n    int op, int3 blockSize);\n\nvoid mexFunction(int\
+    \ nlhs, mxArray *plhs[], int nrhs, const mxArray *prhs[])\n{\n    // Validate\
+    \ inputs (to be implemented)\n\n    // Allocate output (to be implemented)\n\n\
+    \    // Extract line segments (to be implemented)\n\n    // Run function (to be\
+    \ implemented)\n}\n\ntemplate <class Ty>\nvoid flatLinearMorphOp(mxArray *mxRes,\
+    \ const mxArray *mxVol, const std::vector<gpho::LineSeg>& lines,\n    int op,\
+    \ int3 blockSize)\n{\n    gpho::HostView<Ty> res(static_cast<Ty *>(mxGetData(mxRes)),\
+    \ volSize(mxRes));\n    gpho::HostView<const Ty> vol(static_cast<const Ty *>(mxGetData(mxVol)),\
+    \ volSize(mxVol));\n\n    switch (op) {\n    case MOP_DILATE:\n        gpho::flatLinearDilateErode<gpho::MORPH_DILATE>(res,\
+    \ vol, lines, blockSize);\n        break;\n    case MOP_ERODE:\n        gpho::flatLinearDilateErode<gpho::MORPH_ERODE>(res,\
+    \ vol, lines, blockSize);\n        break;\n    default:\n        abortWithMsg(\"\
+    invalid morphology op\");\n    }\n}\n```"
+- source_sentence: Calculate $(-1)^{47} + 2^{(3^3+4^2-6^2)}$.
+  sentences:
+  - "Context: \nAnswer: 2"
+  - "Context: \nAnswer: 127"
+  - '4750'
+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 ibm-granite/granite-embedding-english-r2
+  results:
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 768
+      type: dim_768
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.626
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.706
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.726
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.758
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.626
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.23533333333333334
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.1452
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.07579999999999998
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.626
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.706
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.726
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.758
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.6916401386587206
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.6704460317460319
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.6750546261347222
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 512
+      type: dim_512
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.636
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.7
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.724
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.758
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.636
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.23333333333333334
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.1448
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.07579999999999998
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.636
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.7
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.724
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.758
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.694038077949631
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.6738849206349207
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.6784599411787897
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 256
+      type: dim_256
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.638
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.698
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.712
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.75
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.638
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.2326666666666667
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.14239999999999997
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.075
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.638
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.698
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.712
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.75
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.6915490012428582
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.6731365079365079
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.6780550682950801
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 128
+      type: dim_128
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.636
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.698
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.716
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.74
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.636
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.23266666666666666
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.1432
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.074
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.636
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.698
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.716
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.74
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.6863050743630661
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.6692539682539683
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.6739281987227784
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 64
+      type: dim_64
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.628
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.692
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.714
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.734
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.628
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.23066666666666666
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.14279999999999998
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.0734
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.628
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.692
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.714
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.734
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.680595460049486
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.6635103174603174
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.6681288217342812
+      name: Cosine Map@100
+---
+
+# SentenceTransformer based on ibm-granite/granite-embedding-english-r2
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [ibm-granite/granite-embedding-english-r2](https://huggingface.co/ibm-granite/granite-embedding-english-r2). 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:** [ibm-granite/granite-embedding-english-r2](https://huggingface.co/ibm-granite/granite-embedding-english-r2) <!-- at revision 47ea694b257b703fee9253d75c2b1f2985180498 -->
+- **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': 'ModernBertModel'})
+  (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
+)
+```
+
+## Usage
+
+### Direct Usage (Sentence Transformers)
+
+First install the Sentence Transformers library:
+
+```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("shatonix/granite-embedding-math-cs")
+# Run inference
+sentences = [
+    'Calculate $(-1)^{47} + 2^{(3^3+4^2-6^2)}$.',
+    'Context: \nAnswer: 127',
+    '4750',
+]
+embeddings = model.encode(sentences)
+print(embeddings.shape)
+# [3, 768]
+
+# Get the similarity scores for the embeddings
+similarities = model.similarity(embeddings, embeddings)
+print(similarities)
+# tensor([[ 1.0000,  0.5650, -0.0154],
+#         [ 0.5650,  1.0000, -0.0246],
+#         [-0.0154, -0.0246,  1.0000]])
+```
+
+<!--
+### Direct Usage (Transformers)
+
+<details><summary>Click to see the direct usage in Transformers</summary>
+
+</details>
+-->
+
+<!--
+### Downstream Usage (Sentence Transformers)
+
+You can finetune this model on your own dataset.
+
+<details><summary>Click to expand</summary>
+
+</details>
+-->
+
+<!--
+### Out-of-Scope Use
+
+*List how the model may foreseeably be misused and address what users ought not to do with the model.*
+-->
+
+## Evaluation
+
+### Metrics
+
+#### Information Retrieval
+
+* Dataset: `dim_768`
+* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator) with these parameters:
+  ```json
+  {
+      "truncate_dim": 768
+  }
+  ```
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| cosine_accuracy@1   | 0.626      |
+| cosine_accuracy@3   | 0.706      |
+| cosine_accuracy@5   | 0.726      |
+| cosine_accuracy@10  | 0.758      |
+| cosine_precision@1  | 0.626      |
+| cosine_precision@3  | 0.2353     |
+| cosine_precision@5  | 0.1452     |
+| cosine_precision@10 | 0.0758     |
+| cosine_recall@1     | 0.626      |
+| cosine_recall@3     | 0.706      |
+| cosine_recall@5     | 0.726      |
+| cosine_recall@10    | 0.758      |
+| **cosine_ndcg@10**  | **0.6916** |
+| cosine_mrr@10       | 0.6704     |
+| cosine_map@100      | 0.6751     |
+
+#### Information Retrieval
+
+* Dataset: `dim_512`
+* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator) with these parameters:
+  ```json
+  {
+      "truncate_dim": 512
+  }
+  ```
+
+| Metric              | Value     |
+|:--------------------|:----------|
+| cosine_accuracy@1   | 0.636     |
+| cosine_accuracy@3   | 0.7       |
+| cosine_accuracy@5   | 0.724     |
+| cosine_accuracy@10  | 0.758     |
+| cosine_precision@1  | 0.636     |
+| cosine_precision@3  | 0.2333    |
+| cosine_precision@5  | 0.1448    |
+| cosine_precision@10 | 0.0758    |
+| cosine_recall@1     | 0.636     |
+| cosine_recall@3     | 0.7       |
+| cosine_recall@5     | 0.724     |
+| cosine_recall@10    | 0.758     |
+| **cosine_ndcg@10**  | **0.694** |
+| cosine_mrr@10       | 0.6739    |
+| cosine_map@100      | 0.6785    |
+
+#### Information Retrieval
+
+* Dataset: `dim_256`
+* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator) with these parameters:
+  ```json
+  {
+      "truncate_dim": 256
+  }
+  ```
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| cosine_accuracy@1   | 0.638      |
+| cosine_accuracy@3   | 0.698      |
+| cosine_accuracy@5   | 0.712      |
+| cosine_accuracy@10  | 0.75       |
+| cosine_precision@1  | 0.638      |
+| cosine_precision@3  | 0.2327     |
+| cosine_precision@5  | 0.1424     |
+| cosine_precision@10 | 0.075      |
+| cosine_recall@1     | 0.638      |
+| cosine_recall@3     | 0.698      |
+| cosine_recall@5     | 0.712      |
+| cosine_recall@10    | 0.75       |
+| **cosine_ndcg@10**  | **0.6915** |
+| cosine_mrr@10       | 0.6731     |
+| cosine_map@100      | 0.6781     |
+
+#### Information Retrieval
+
+* Dataset: `dim_128`
+* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator) with these parameters:
+  ```json
+  {
+      "truncate_dim": 128
+  }
+  ```
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| cosine_accuracy@1   | 0.636      |
+| cosine_accuracy@3   | 0.698      |
+| cosine_accuracy@5   | 0.716      |
+| cosine_accuracy@10  | 0.74       |
+| cosine_precision@1  | 0.636      |
+| cosine_precision@3  | 0.2327     |
+| cosine_precision@5  | 0.1432     |
+| cosine_precision@10 | 0.074      |
+| cosine_recall@1     | 0.636      |
+| cosine_recall@3     | 0.698      |
+| cosine_recall@5     | 0.716      |
+| cosine_recall@10    | 0.74       |
+| **cosine_ndcg@10**  | **0.6863** |
+| cosine_mrr@10       | 0.6693     |
+| cosine_map@100      | 0.6739     |
+
+#### Information Retrieval
+
+* Dataset: `dim_64`
+* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator) with these parameters:
+  ```json
+  {
+      "truncate_dim": 64
+  }
+  ```
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| cosine_accuracy@1   | 0.628      |
+| cosine_accuracy@3   | 0.692      |
+| cosine_accuracy@5   | 0.714      |
+| cosine_accuracy@10  | 0.734      |
+| cosine_precision@1  | 0.628      |
+| cosine_precision@3  | 0.2307     |
+| cosine_precision@5  | 0.1428     |
+| cosine_precision@10 | 0.0734     |
+| cosine_recall@1     | 0.628      |
+| cosine_recall@3     | 0.692      |
+| cosine_recall@5     | 0.714      |
+| cosine_recall@10    | 0.734      |
+| **cosine_ndcg@10**  | **0.6806** |
+| cosine_mrr@10       | 0.6635     |
+| cosine_map@100      | 0.6681     |
+
+<!--
+## 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: 4,500 training samples
+* Columns: <code>anchor</code>, <code>positive</code>, and <code>id</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | anchor                                                                             | positive                                                                            | id                                                                              |
+  |:--------|:-----------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|:--------------------------------------------------------------------------------|
+  | type    | string                                                                             | string                                                                              | string                                                                          |
+  | details | <ul><li>min: 8 tokens</li><li>mean: 80.08 tokens</li><li>max: 512 tokens</li></ul> | <ul><li>min: 9 tokens</li><li>mean: 165.53 tokens</li><li>max: 512 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 3.81 tokens</li><li>max: 4 tokens</li></ul> |
+* Samples:
+  | anchor                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                           | positive                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                 | id                |
+  |:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:------------------|
+  | <code>Stella’s antique shop has 3 dolls, 2 clocks and 5 glasses for sale. She sells the dolls for $5 each. The clocks are priced at $15 each. The glasses are priced at $4 each. If she spent $40 to buy everything and she sells all of her merchandise, how much profit will she make?</code>                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  | <code>Context: <br>Answer: 25</code>                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                     | <code>3430</code> |
+  | <code>You are tasked with creating a Ruby program that defines a service for creating a project in a Continuous Integration (CI) system. The service should be able to execute with valid parameters and handle specific scenarios.<br><br>The program should include the following:<br>- A class called `Ci::CreateProjectService` that defines the service for creating a project.<br>- A method within the `Ci::CreateProjectService` class called `execute` that takes in three parameters: `current_user` (representing the current user), `project` (representing the project to be created), and `ci_origin_project` (optional, representing the project to use as a template for settings and jobs).<br>- The `execute` method should handle the following scenarios:<br>  1. When executed with valid parameters, it should return a new instance of `Ci::Project` that is persisted.<br>  2. When executed without a project dump (empty string), it should raise an exception.<br>  3. When executed with a `ci_origin_project` for forking, it should use ...</code> | <code>Context: <br>Answer: ```ruby<br>class Ci::CreateProjectService<br>  def execute(current_user, project, ci_origin_project = nil)<br>    if project.empty?<br>      raise StandardError, 'Project dump is required'<br>    end<br><br>    new_project = Ci::Project.new<br>    new_project.save<br><br>    if ci_origin_project<br>      new_project.shared_runners_enabled = ci_origin_project.shared_runners_enabled<br>      new_project.public = ci_origin_project.public<br>      new_project.allow_git_fetch = ci_origin_project.allow_git_fetch<br>    end<br><br>    new_project<br>  end<br>end<br>```</code>                                                                                                                                                               | <code>656</code>  |
+  | <code>Why is the Insertion Sort algorithm considered optimal for nearly sorted datasets, and how does its time complexity compare to other quadratic sorting algorithms?</code>                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  | <code>Context: <br>Answer: Insertion Sort operates in O(n²) time complexity in the worst case, but for nearly sorted datasets, it achieves O(n) time complexity. This is because it only requires a minimal number of swaps to place elements in order. For datasets where most elements are already in their correct positions, the number of inversions (pairs out of order) is small, reducing the number of comparisons and swaps. This contrasts with other quadratic algorithms like Selection Sort, which must scan the entire dataset for each element, leading to O(n²) operations regardless of initial order. The efficiency of Insertion Sort for nearly sorted data stems from its ability to leverage existing order, making it a better choice for such scenarios.</code> | <code>1305</code> |
+* Loss: [<code>MatryoshkaLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#matryoshkaloss) with these parameters:
+  ```json
+  {
+      "loss": "MultipleNegativesRankingLoss",
+      "matryoshka_dims": [
+          768,
+          512,
+          256,
+          128,
+          64
+      ],
+      "matryoshka_weights": [
+          1,
+          1,
+          1,
+          1,
+          1
+      ],
+      "n_dims_per_step": -1
+  }
+  ```
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `eval_strategy`: epoch
+- `per_device_train_batch_size`: 64
+- `per_device_eval_batch_size`: 64
+- `gradient_accumulation_steps`: 2
+- `num_train_epochs`: 10
+- `lr_scheduler_type`: cosine
+- `warmup_ratio`: 0.1
+- `bf16`: True
+- `tf32`: True
+- `dataloader_num_workers`: 4
+- `load_best_model_at_end`: True
+- `batch_sampler`: no_duplicates
+
+#### All Hyperparameters
+<details><summary>Click to expand</summary>
+
+- `overwrite_output_dir`: False
+- `do_predict`: False
+- `eval_strategy`: epoch
+- `prediction_loss_only`: True
+- `per_device_train_batch_size`: 64
+- `per_device_eval_batch_size`: 64
+- `per_gpu_train_batch_size`: None
+- `per_gpu_eval_batch_size`: None
+- `gradient_accumulation_steps`: 2
+- `eval_accumulation_steps`: None
+- `torch_empty_cache_steps`: None
+- `learning_rate`: 5e-05
+- `weight_decay`: 0.0
+- `adam_beta1`: 0.9
+- `adam_beta2`: 0.999
+- `adam_epsilon`: 1e-08
+- `max_grad_norm`: 1.0
+- `num_train_epochs`: 10
+- `max_steps`: -1
+- `lr_scheduler_type`: cosine
+- `lr_scheduler_kwargs`: {}
+- `warmup_ratio`: 0.1
+- `warmup_steps`: 0
+- `log_level`: passive
+- `log_level_replica`: warning
+- `log_on_each_node`: True
+- `logging_nan_inf_filter`: True
+- `save_safetensors`: True
+- `save_on_each_node`: False
+- `save_only_model`: False
+- `restore_callback_states_from_checkpoint`: False
+- `no_cuda`: False
+- `use_cpu`: False
+- `use_mps_device`: False
+- `seed`: 42
+- `data_seed`: None
+- `jit_mode_eval`: False
+- `bf16`: True
+- `fp16`: False
+- `fp16_opt_level`: O1
+- `half_precision_backend`: auto
+- `bf16_full_eval`: False
+- `fp16_full_eval`: False
+- `tf32`: True
+- `local_rank`: 0
+- `ddp_backend`: None
+- `tpu_num_cores`: None
+- `tpu_metrics_debug`: False
+- `debug`: []
+- `dataloader_drop_last`: False
+- `dataloader_num_workers`: 4
+- `dataloader_prefetch_factor`: None
+- `past_index`: -1
+- `disable_tqdm`: False
+- `remove_unused_columns`: True
+- `label_names`: None
+- `load_best_model_at_end`: True
+- `ignore_data_skip`: False
+- `fsdp`: []
+- `fsdp_min_num_params`: 0
+- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
+- `fsdp_transformer_layer_cls_to_wrap`: None
+- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
+- `parallelism_config`: None
+- `deepspeed`: None
+- `label_smoothing_factor`: 0.0
+- `optim`: adamw_torch_fused
+- `optim_args`: None
+- `adafactor`: False
+- `group_by_length`: False
+- `length_column_name`: length
+- `project`: huggingface
+- `trackio_space_id`: trackio
+- `ddp_find_unused_parameters`: None
+- `ddp_bucket_cap_mb`: None
+- `ddp_broadcast_buffers`: False
+- `dataloader_pin_memory`: True
+- `dataloader_persistent_workers`: False
+- `skip_memory_metrics`: True
+- `use_legacy_prediction_loop`: False
+- `push_to_hub`: False
+- `resume_from_checkpoint`: None
+- `hub_model_id`: None
+- `hub_strategy`: every_save
+- `hub_private_repo`: None
+- `hub_always_push`: False
+- `hub_revision`: None
+- `gradient_checkpointing`: False
+- `gradient_checkpointing_kwargs`: None
+- `include_inputs_for_metrics`: False
+- `include_for_metrics`: []
+- `eval_do_concat_batches`: True
+- `fp16_backend`: auto
+- `push_to_hub_model_id`: None
+- `push_to_hub_organization`: None
+- `mp_parameters`: 
+- `auto_find_batch_size`: False
+- `full_determinism`: False
+- `torchdynamo`: None
+- `ray_scope`: last
+- `ddp_timeout`: 1800
+- `torch_compile`: False
+- `torch_compile_backend`: None
+- `torch_compile_mode`: None
+- `include_tokens_per_second`: False
+- `include_num_input_tokens_seen`: no
+- `neftune_noise_alpha`: None
+- `optim_target_modules`: None
+- `batch_eval_metrics`: False
+- `eval_on_start`: False
+- `use_liger_kernel`: False
+- `liger_kernel_config`: None
+- `eval_use_gather_object`: False
+- `average_tokens_across_devices`: True
+- `prompts`: None
+- `batch_sampler`: no_duplicates
+- `multi_dataset_batch_sampler`: proportional
+- `router_mapping`: {}
+- `learning_rate_mapping`: {}
+
+</details>
+
+### Training Logs
+| Epoch   | Step    | Training Loss | dim_768_cosine_ndcg@10 | dim_512_cosine_ndcg@10 | dim_256_cosine_ndcg@10 | dim_128_cosine_ndcg@10 | dim_64_cosine_ndcg@10 |
+|:-------:|:-------:|:-------------:|:----------------------:|:----------------------:|:----------------------:|:----------------------:|:---------------------:|
+| -1      | -1      | -             | 0.6227                 | 0.6213                 | 0.6163                 | 0.6036                 | 0.5905                |
+| 0.2817  | 10      | 10.3671       | -                      | -                      | -                      | -                      | -                     |
+| 0.5634  | 20      | 8.1302        | -                      | -                      | -                      | -                      | -                     |
+| 0.8451  | 30      | 6.6781        | -                      | -                      | -                      | -                      | -                     |
+| 1.0     | 36      | -             | 0.6371                 | 0.6373                 | 0.6368                 | 0.6384                 | 0.6297                |
+| 1.1127  | 40      | 5.6041        | -                      | -                      | -                      | -                      | -                     |
+| 1.3944  | 50      | 5.3589        | -                      | -                      | -                      | -                      | -                     |
+| 1.6761  | 60      | 5.2615        | -                      | -                      | -                      | -                      | -                     |
+| 1.9577  | 70      | 5.1322        | -                      | -                      | -                      | -                      | -                     |
+| 2.0     | 72      | -             | 0.6584                 | 0.6599                 | 0.6567                 | 0.6590                 | 0.6588                |
+| 2.2254  | 80      | 4.2222        | -                      | -                      | -                      | -                      | -                     |
+| 2.5070  | 90      | 3.6282        | -                      | -                      | -                      | -                      | -                     |
+| 2.7887  | 100     | 3.5652        | -                      | -                      | -                      | -                      | -                     |
+| 3.0     | 108     | -             | 0.6679                 | 0.6724                 | 0.6750                 | 0.6699                 | 0.6645                |
+| 3.0563  | 110     | 3.1212        | -                      | -                      | -                      | -                      | -                     |
+| 3.3380  | 120     | 1.8016        | -                      | -                      | -                      | -                      | -                     |
+| 3.6197  | 130     | 1.8941        | -                      | -                      | -                      | -                      | -                     |
+| 3.9014  | 140     | 1.8576        | -                      | -                      | -                      | -                      | -                     |
+| 4.0     | 144     | -             | 0.6900                 | 0.6923                 | 0.6937                 | 0.6863                 | 0.6771                |
+| 4.1690  | 150     | 1.0872        | -                      | -                      | -                      | -                      | -                     |
+| 4.4507  | 160     | 0.7482        | -                      | -                      | -                      | -                      | -                     |
+| 4.7324  | 170     | 0.7307        | -                      | -                      | -                      | -                      | -                     |
+| 5.0     | 180     | 0.8322        | 0.6909                 | 0.6988                 | 0.6947                 | 0.6873                 | 0.6800                |
+| 5.2817  | 190     | 0.329         | -                      | -                      | -                      | -                      | -                     |
+| 5.5634  | 200     | 0.3246        | -                      | -                      | -                      | -                      | -                     |
+| 5.8451  | 210     | 0.274         | -                      | -                      | -                      | -                      | -                     |
+| 6.0     | 216     | -             | 0.6898                 | 0.6929                 | 0.6904                 | 0.6900                 | 0.6801                |
+| 6.1127  | 220     | 0.2161        | -                      | -                      | -                      | -                      | -                     |
+| 6.3944  | 230     | 0.1178        | -                      | -                      | -                      | -                      | -                     |
+| 6.6761  | 240     | 0.1418        | -                      | -                      | -                      | -                      | -                     |
+| 6.9577  | 250     | 0.1319        | -                      | -                      | -                      | -                      | -                     |
+| 7.0     | 252     | -             | 0.6920                 | 0.6890                 | 0.6910                 | 0.6880                 | 0.6789                |
+| 7.2254  | 260     | 0.0979        | -                      | -                      | -                      | -                      | -                     |
+| 7.5070  | 270     | 0.0653        | -                      | -                      | -                      | -                      | -                     |
+| 7.7887  | 280     | 0.0852        | -                      | -                      | -                      | -                      | -                     |
+| **8.0** | **288** | **-**         | **0.6934**             | **0.69**               | **0.6934**             | **0.6877**             | **0.6825**            |
+| 8.0563  | 290     | 0.08          | -                      | -                      | -                      | -                      | -                     |
+| 8.3380  | 300     | 0.0526        | -                      | -                      | -                      | -                      | -                     |
+| 8.6197  | 310     | 0.066         | -                      | -                      | -                      | -                      | -                     |
+| 8.9014  | 320     | 0.0549        | -                      | -                      | -                      | -                      | -                     |
+| 9.0     | 324     | -             | 0.6911                 | 0.6929                 | 0.6905                 | 0.6858                 | 0.6802                |
+| 9.1690  | 330     | 0.0384        | -                      | -                      | -                      | -                      | -                     |
+| 9.4507  | 340     | 0.0523        | -                      | -                      | -                      | -                      | -                     |
+| 9.7324  | 350     | 0.0333        | -                      | -                      | -                      | -                      | -                     |
+| 10.0    | 360     | 0.0488        | 0.6916                 | 0.6940                 | 0.6915                 | 0.6863                 | 0.6806                |
+
+* The bold row denotes the saved checkpoint.
+
+### Framework Versions
+- Python: 3.12.12
+- Sentence Transformers: 5.2.0
+- Transformers: 4.57.3
+- PyTorch: 2.9.1+cu128
+- Accelerate: 1.12.0
+- Datasets: 4.4.2
+- Tokenizers: 0.22.1
+
+## 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",
+}
+```
+
+#### MatryoshkaLoss
+```bibtex
+@misc{kusupati2024matryoshka,
+    title={Matryoshka Representation Learning},
+    author={Aditya Kusupati and Gantavya Bhatt and Aniket Rege and Matthew Wallingford and Aditya Sinha and Vivek Ramanujan and William Howard-Snyder and Kaifeng Chen and Sham Kakade and Prateek Jain and Ali Farhadi},
+    year={2024},
+    eprint={2205.13147},
+    archivePrefix={arXiv},
+    primaryClass={cs.LG}
+}
+```
+
+#### MultipleNegativesRankingLoss
+```bibtex
+@misc{henderson2017efficient,
+    title={Efficient Natural Language Response Suggestion for Smart Reply},
+    author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil},
+    year={2017},
+    eprint={1705.00652},
+    archivePrefix={arXiv},
+    primaryClass={cs.CL}
+}
+```
+
+<!--
+## 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.json

@@ -0,0 +1,48 @@
+{
+  "architectures": [
+    "ModernBertModel"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 50281,
+  "classifier_activation": "silu",
+  "classifier_bias": false,
+  "classifier_dropout": 0.0,
+  "classifier_pooling": "mean",
+  "cls_token_id": 50281,
+  "decoder_bias": true,
+  "deterministic_flash_attn": false,
+  "dtype": "float32",
+  "embedding_dropout": 0.0,
+  "eos_token_id": 50282,
+  "global_attn_every_n_layers": 3,
+  "global_rope_theta": 80000.0,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_activation": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_cutoff_factor": 2.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 1152,
+  "layer_norm_eps": 1e-05,
+  "local_attention": 128,
+  "local_rope_theta": 10000.0,
+  "max_position_embeddings": 8192,
+  "mlp_bias": false,
+  "mlp_dropout": 0.0,
+  "model_type": "modernbert",
+  "norm_bias": false,
+  "norm_eps": 1e-05,
+  "num_attention_heads": 12,
+  "num_hidden_layers": 22,
+  "pad_token_id": 50283,
+  "position_embedding_type": "absolute",
+  "repad_logits_with_grad": false,
+  "sep_token_id": 50282,
+  "sparse_pred_ignore_index": -100,
+  "sparse_prediction": false,
+  "transformers_version": "4.57.3",
+  "vocab_size": 50368
+}

config_sentence_transformers.json

@@ -0,0 +1,14 @@
+{
+  "model_type": "SentenceTransformer",
+  "__version__": {
+    "sentence_transformers": "5.2.0",
+    "transformers": "4.57.3",
+    "pytorch": "2.9.1+cu128"
+  },
+  "prompts": {
+    "query": "",
+    "document": ""
+  },
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4947d92ab9822101b88590dff231f9160ff25f9092c778b2b4240f46eb0abb10
+size 596070136

modules.json

@@ -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

@@ -0,0 +1,4 @@
+{
+    "max_seq_length": 512,
+    "do_lower_case": false
+}

special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,945 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "|||IP_ADDRESS|||",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "1": {
+      "content": "<|padding|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50254": {
+      "content": "                        ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50255": {
+      "content": "                       ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50256": {
+      "content": "                      ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50257": {
+      "content": "                     ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50258": {
+      "content": "                    ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50259": {
+      "content": "                   ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50260": {
+      "content": "                  ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50261": {
+      "content": "                 ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50262": {
+      "content": "                ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50263": {
+      "content": "               ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50264": {
+      "content": "              ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50265": {
+      "content": "             ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50266": {
+      "content": "            ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50267": {
+      "content": "           ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50268": {
+      "content": "          ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50269": {
+      "content": "         ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50270": {
+      "content": "        ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50271": {
+      "content": "       ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50272": {
+      "content": "      ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50273": {
+      "content": "     ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50274": {
+      "content": "    ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50275": {
+      "content": "   ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50276": {
+      "content": "  ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50277": {
+      "content": "|||EMAIL_ADDRESS|||",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50278": {
+      "content": "|||PHONE_NUMBER|||",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50279": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50280": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50281": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50282": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50283": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50284": {
+      "content": "[MASK]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50285": {
+      "content": "[unused0]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50286": {
+      "content": "[unused1]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50287": {
+      "content": "[unused2]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50288": {
+      "content": "[unused3]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50289": {
+      "content": "[unused4]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50290": {
+      "content": "[unused5]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50291": {
+      "content": "[unused6]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50292": {
+      "content": "[unused7]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50293": {
+      "content": "[unused8]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50294": {
+      "content": "[unused9]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50295": {
+      "content": "[unused10]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50296": {
+      "content": "[unused11]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50297": {
+      "content": "[unused12]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50298": {
+      "content": "[unused13]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50299": {
+      "content": "[unused14]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50300": {
+      "content": "[unused15]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50301": {
+      "content": "[unused16]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50302": {
+      "content": "[unused17]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50303": {
+      "content": "[unused18]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50304": {
+      "content": "[unused19]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50305": {
+      "content": "[unused20]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50306": {
+      "content": "[unused21]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50307": {
+      "content": "[unused22]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50308": {
+      "content": "[unused23]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50309": {
+      "content": "[unused24]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50310": {
+      "content": "[unused25]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50311": {
+      "content": "[unused26]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50312": {
+      "content": "[unused27]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50313": {
+      "content": "[unused28]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50314": {
+      "content": "[unused29]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50315": {
+      "content": "[unused30]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50316": {
+      "content": "[unused31]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50317": {
+      "content": "[unused32]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50318": {
+      "content": "[unused33]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50319": {
+      "content": "[unused34]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50320": {
+      "content": "[unused35]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50321": {
+      "content": "[unused36]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50322": {
+      "content": "[unused37]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50323": {
+      "content": "[unused38]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50324": {
+      "content": "[unused39]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50325": {
+      "content": "[unused40]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50326": {
+      "content": "[unused41]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50327": {
+      "content": "[unused42]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50328": {
+      "content": "[unused43]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50329": {
+      "content": "[unused44]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50330": {
+      "content": "[unused45]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50331": {
+      "content": "[unused46]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50332": {
+      "content": "[unused47]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50333": {
+      "content": "[unused48]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50334": {
+      "content": "[unused49]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50335": {
+      "content": "[unused50]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50336": {
+      "content": "[unused51]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50337": {
+      "content": "[unused52]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50338": {
+      "content": "[unused53]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50339": {
+      "content": "[unused54]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50340": {
+      "content": "[unused55]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50341": {
+      "content": "[unused56]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50342": {
+      "content": "[unused57]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50343": {
+      "content": "[unused58]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50344": {
+      "content": "[unused59]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50345": {
+      "content": "[unused60]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50346": {
+      "content": "[unused61]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50347": {
+      "content": "[unused62]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50348": {
+      "content": "[unused63]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50349": {
+      "content": "[unused64]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50350": {
+      "content": "[unused65]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50351": {
+      "content": "[unused66]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50352": {
+      "content": "[unused67]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50353": {
+      "content": "[unused68]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50354": {
+      "content": "[unused69]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50355": {
+      "content": "[unused70]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50356": {
+      "content": "[unused71]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50357": {
+      "content": "[unused72]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50358": {
+      "content": "[unused73]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50359": {
+      "content": "[unused74]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50360": {
+      "content": "[unused75]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50361": {
+      "content": "[unused76]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50362": {
+      "content": "[unused77]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50363": {
+      "content": "[unused78]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50364": {
+      "content": "[unused79]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50365": {
+      "content": "[unused80]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50366": {
+      "content": "[unused81]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50367": {
+      "content": "[unused82]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 8192,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "unk_token": "[UNK]"
+}