Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

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

@@ -1,3 +1,1025 @@
----
-license: mit
----
+---
+language:
+- en
+license: apache-2.0
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- dataset_size:1456
+- loss:MatryoshkaLoss
+- loss:MultipleNegativesRankingLoss
+base_model: Snowflake/snowflake-arctic-embed-m-v2.0
+widget:
+- source_sentence: 'relation to a portfolio manager being a body corporate, shall
+    be construed with reference to : (i) the definition of control in terms of Regulation
+    2(1)(e) of SEBI (Substantial Acquisition of Shares and Takeovers) Regulations,
+    2011 as amended from time to time, if its shares are listed on any recognized
+    stock exchange; (ii) in any other case, change in the controlling interest in
+    the body corporate; Explanation. For the purpose of sub-clause (ii), the expression
+    controlling interest means, (A) an interest, whether direct or indirect, to the
+    extent of at least fifty-one percent of voting rights in the body corporate; (B)
+    right to appoint majority of the directors or to control the management directly
+    or indirectly. Page 3 of 78 reference to the definition of control in terms of
+    regulations framed under clause (h) of sub-section (2) of section 11 of the Act;
+    (B) if its shares are not listed on any recognised stock exchange, shall be construed
+    with reference to the definition of control as provided in sub-section (27) of
+    Section 2 of the Companies Act, 2013 (18 of 2013);] (f) chartered accountant"
+    means a chartered accountant as defined in clause (b) of sub- section (1) of section
+    2 of the Chartered Accountants Act, 1949 (38 of 1949) and who has obtained a certificate
+    of practice under sub-section (1) of section 6 of that Act; 5[(fa) Co-investment
+    Portfolio Manager means a Portfolio Manager who is a Manager of a Category I or
+    Category II Alternative Investment Fund(s); and: (i) provides services only to
+    the investors of such Category I or Category II Alternative Investment Fund(s);
+    and (ii) makes investment only in unlisted securities of investee companies where
+    such Category I or Category II Alternative Investment Fund(s) make investments:
+    Provided that the Co-investment Portfolio Manager may provide services to investors
+    from any other Category I or Category II Alternative Investment Fund(s) which
+    are managed by them and are also sponsored by the same Sponsor(s);] (g) discretionary
+    portfolio manager means a portfolio manager who under a contract relating to portfolio
+    management, exercises or may exercise, any degree of discretion as to the investment
+    of funds or management of the portfolio of securities of the client, as the case
+    may be; (h) eligible fund manager shall have the same meaning as assigned to it
+    in sub-section (4) of Section 9A of the Income-tax Act, 1961; (i) eligible investment
+    fund shall have the same meaning as assigned to it in sub-section (3) of Section
+    9A of the Income-tax Act, 1961; 5 Inserted by the Securities and Exchange Board
+    of India (Portfolio Managers) (Fourth Amendment) Regulations, 2021 w. Page 4 of
+    78 (j) "form" means a form specified in Schedule I; (k) goods means the goods
+    notified by the Central Government under clause (bc) of section 2 of the Securities
+    Contracts (Regulation) Act, 1956 and forming the underlying of any commodity derivative;
+    (l) "inspecting authority" means one or more persons appointed by the Board to
+    exercise powers conferred under Chapter V; 6[(la) large value accredited investor
+    means an accredited investor who has entered into an agreement with the portfolio
+    manager for a minimum investment amount of ten crore rupees;] 7[(lb) investee
+    company shall have the same meaning as assigned to it in clause (o) of sub- regulation
+    (1) of regulation 2 of the Securities and Exchange Board of India (Alternative
+    Investment Funds) Regulations, 2012; (lc) Manager shall'
+  sentences:
+  - What are the particulars of units of the scheme and/or shares and debentures of
+    the company issued for consideration other than cash?
+  - What is the maximum period allowed for a listed company to increase its public
+    shareholding to twenty-five percent after it falls below that threshold as a result
+    of an approved resolution plan under the Insolvency and Bankruptcy Code, 2016?
+  - What is the definition of "controlling interest" in the context of a body corporate
+    under the SEBI regulations?
+- source_sentence: 'The issuer making a private placement of debt securities and non-convertible
+    redeemable preference shares and seeking listing thereof on a recognised stock
+    exchange shall make the following disclosures in the placement memorandum: (a)
+    disclosures specified in 28[Schedule I] of these regulations; (b) disclosures
+    specified in the Companies Act, 2013 (18 of 2013), as applicable; (c) additional
+    disclosures as may be specified by the Board. (2) The disclosures as provided
+    in sub-regulation (1) shall be made on the websites of stock exchange(s) where
+    such securities are proposed to be listed and shall be available for download
+    in PDF or any other format as may be specified by the Board. (3) The issuer shall
+    ensure that the audited financial statements contained in the placement memorandum
+    29[] shall not be more than six months old from the date of filing placement memorandum
+    or the issue opening date, as applicable: 27 Substituted by the by the Securities
+    and Exchange Board of India (Issue and Listing of Non-Convertible Securities)
+    (Amendment) Regulations, 2024 w. Prior to substitution, it read as The debenture
+    trustee shall submit a due diligence certificate to the stock exchange: (a) in
+    case of secured debt securities, in the format as specified in Schedule IV of
+    these regulations; and (b) in case of unsecured debt securities, in the format
+    as specified in Schedule IVA of these regulations. Prior to this, it was substituted
+    by the Securities and Exchange Board of India (Issue and Listing of Non-Convertible
+    Securities) (Amendment) Regulations, 2022, w. Prior to substitution, sub-regulation
+    3 read as: Debenture trustee shall submit a due diligence certificate to the stock
+    exchange in the format as specified in Schedule IV of these regulations. 28 Substituted
+    by the Securities and Exchange Board of India (Issue and Listing of Non-Convertible
+    Securities) (Second Amendment) Regulations, 2023, w. Prior to substitution, the
+    words were Schedule II. 29 Omitted by the Securities and Exchange Board of India
+    (Issue and Listing of Non-Convertible Securities) (Second Amendment) Regulations,
+    2023, w. Prior to omission, the words were and tranche placement memorandum. Page
+    26 of 79 Provided that in case of: (a) listed issuers (whose non-convertible securities
+    or specified securities are listed on recognised stock exchange(s)), who are in
+    compliance with the listing regulations; (b) the issuers of non-convertible securities,
+    who are subsidiaries of entities who have listed their specified securities, and
+    are in compliance with the listing regulations, instead of audited financial statements
+    for the stub period, they may disclose unaudited financial information for such
+    period in the format as prescribed in the listing regulations with limited review
+    report, as filed with the stock exchange(s), subject to necessary disclosures
+    in this regard in the placement memorandum including risk factors. Allotment of
+    securities 46. The issuer shall ensure allotment of debt securities and non-convertible
+    redeemable preference shares issued on a private placement basis and credit to
+    the dematerialised account of the investors, is made within such time as may be
+    specified by the Board. PART B ADDITIONAL PROVISIONS FOR LISTING OF DEBT SECURITIES
+    ISSUED ON PRIVATE PLACEMENT BASIS Filing of shelf placement memorandum 47. 30[]
+    Creation of security 48. (1) While creating a charge or security, the issuer shall
+    have the option to create charge or security over the properties or assets (movable,
+    immovable, tangible, intangible), shares or any interest thereon, of the issuer
+    or its subsidiaries or its holding companies or its associate companies. 30 Omitted
+    by the Securities and Exchange Board of India'
+  sentences:
+  - What is the penalty for a reporting requirement violation under the PIT Regulations
+    if there is a delay of more than three months?
+  - What are the names of the members of the issuer's audit committee, nomination
+    and remuneration committee, and stakeholders relationship committee?
+  - What disclosures must an issuer include in the placement memorandum when making
+    a private placement of debt securities and non-convertible redeemable preference
+    shares?
+- source_sentence: 'Accredited refineries means refineries empanelled by the Stock
+    Exchanges; Page 4 of 26 (c) Assayer means a person engaged in the process of assessing
+    the purity or quality of gold; (d) Beneficial Owner means a person whose name
+    is recorded as such with a depository/depository participant; (e) Board means
+    the Securities and Exchange Board of India established under section 3 of the
+    Act; 1[(f) Change in control in case of a body corporate (A) if its shares are
+    listed on any recognised stock exchange, shall be construed with reference to
+    the definition of control in terms of regulations framed under clause (h) of sub-section
+    (2) of section 11 of the Act; (B) if its shares are not listed on any recognised
+    stock exchange, shall be construed with reference to the definition of control
+    as provided in sub-section (27) of Section 2 of the Companies Act, 2013 (18 of
+    2013);] (g) Depositor means a person who owns the gold deposited with the vault
+    for creation of Electronic Gold Receipt and its trading on recognized stock exchange;
+    (h) Electronic Gold Receipt shall have the meaning assigned to it under the Securities
+    Contracts (Regulation) Act, 1956; (i) Gold standard means the purity and standard
+    of gold as specified by the recognized stock exchanges; (j) Nominated agencies
+    means agencies nominated by the Directorate General of Foreign Trade for import
+    of Gold under the Foreign Trade (Development and Regulation) Act, 1992; 1 Substituted
+    by the Securities and Exchange Board of India (Change in Control in Intermediaries)
+    (Amendment) Regulations, 2023 w. Prior to the substitution, clause (f) read as
+    under: Change in control, in relation to a Vault Manager being a body corporate,
+    shall be construed with reference to: (i) the definition of control in terms of
+    regulation 2(1)(e) of SEBI (Substantial Acquisition of Shares and Takeovers) Regulations,
+    2011 as amended from time to time if its shares are listed on any recognized stock
+    exchange; (ii) in any other case, change in the controlling interest in the body
+    corporate; Explanation For the purpose of sub-clause (ii), the expression controlling
+    interest means- (A) an interest, whether direct or indirect, to the extent of
+    at least fifty-one percent of voting rights in the body corporate; or (B) right
+    to appoint majority of the directors or to control the management directly or
+    indirectly; Page 5 of 26 (k) Recognized vault means the premises encompassing
+    strong room(s) set up and managed by the Vault Manager and which conforms with
+    all the requirements specified by the Board for the purpose of providing vaulting
+    services; (l) Vault Manager means any person who carries on or intends to carry
+    on the business of providing vaulting services; (m) Vaulting service in relation
+    to gold means the storage and safekeeping of gold deposited with the Vault Manager,
+    by the depositor, for the purpose of trading in Electronic Gold Receipt and providing
+    services incidental thereto, and includes (i) utilizing the services of assayers
+    empanelled with the Stock Exchanges for testing as per the gold standard, wherever
+    required; (ii) coordination with depositories for creation, transfer and extinguishment
+    of Electronic Gold Receipt; and (iii) providing deposit, storage and withdrawal
+    services to the beneficial owners. (2) The words and expressions used and not
+    defined in these regulations, but defined in the Act, the Securities Contracts
+    (Regulation) Act, 1956, (42 of 1956), the Companies Act, 2013 (18 of 2013), the
+    Depositories Act, 1996, or any rules'
+  sentences:
+  - What happens if the eighth day, as reckoned under the Negotiable Instruments Act,
+    is itself a public holiday?
+  - What is the role of an Assayer according to the context provided?
+  - What disclosures are required regarding significant income sources that constitute
+    more than 10% of total income?
+- source_sentence: 'Regulations, 2023 w. 93 Inserted by the Securities and Exchange
+    Board of India (Buy-Back of Securities) (Second Amendment) Regulations, 2024 w.
+    Particulars Content Public Announcement i) The Public announcement shall be dated
+    and signed on behalf of the Board of Directors of the company by its manager or
+    secretary, if any, and by not less than two directors of the company one of whom
+    shall be a managing director where there is one. ii) A full and complete disclosure
+    of all material facts including the disclosures mentioned in Schedule I. iii)
+    In addition to the disclosures in Schedule A, the following disclosures shall
+    be made: i) Date of shareholders approval for buy-back, if applicable; ii) Minimum
+    and maximum number of securities that the company proposes to buy-back, sources
+    of funds from which the buy-back would be made and the cost of financing the buy-back;
+    iii) Proposed time table from opening of offer till the extinguishment of the
+    certificates; iv) Process and methodology to be adopted for the buy- back; v)
+    Brief information about the company; i) The Public announcement shall be dated
+    and signed on behalf of the Board of Directors of the company by its manager or
+    secretary, if any, and by not less than two directors of the company one of whom
+    shall be a managing director where there is one. ii) A full and complete disclosure
+    of all material facts including the disclosures mentioned in Schedule I. Page
+    46 of 51 SCHEDULE - IV [Regulation 16(iv)(b)] Public Announcement for Open Market
+    Buy-Back through Stock Exchange Particulars Content Public Announcement i) The
+    Public announcement shall be dated and signed on behalf of the Board of Directors
+    of the company by its manager or secretary, if any, and by not less than two directors
+    of the company one of whom shall be a managing director where there is one. ii)
+    A full and complete disclosure of all material facts including the disclosures
+    mentioned in Schedule I. iii) In addition to the disclosures in Schedule A, the
+    following disclosures shall be made: i) Date of shareholders approval for buy-back,
+    if applicable; ii) Minimum and maximum number of securities that the company proposes
+    to buy-back, sources of funds from which the buy-back would be made and the cost
+    of financing the buy-back; iii) Proposed time table from opening of offer till
+    the extinguishment of the certificates; iv) Process and methodology to be adopted
+    for the buy- back; v) Brief information about the company; Particulars Content
+    vi) Audited Financial information for the last 3 years and the lead manager shall
+    ensure that the particulars (audited statement and un-audited statement) contained
+    therein shall not be more than more than 6 months old from the date of the public
+    announcement together with financial ratios as may be specified by the Board;
+    Explanation: Ensure that the un-audited financial results, if any disclosed, should
+    be certified / limited review by statutory auditors. vii) Details of escrow account
+    opened and the amount deposited therein; viii) Listing details and stock market
+    data: a) high, low and average market prices of the securities of the company
+    proposed to be bought back, during the preceding three years; b) monthly high
+    and low prices for the six months preceding the date of the public announcement;
+    c) the number of securities traded on the days when the high and low prices were
+    recorded on the relevant stock exchanges during the period stated at (a) and (b)
+    above; d) the stock market data referred to above shall be shown separately for
+    periods marked by a change in capital structure, with such period commencing from
+    the date the concerned stock exchange recognises the change in the capital structure.
+    when the securities have become ex-rights or ex-bonus) ; e)'
+  sentences:
+  - What is the time frame within which a return of allotment of securities must be
+    filed with the Registrar according to the Companies (Registration Offices and
+    Fees) Rules, 2014?
+  - What is the deadline for a listed entity to put in place systems and processes
+    for compliance with clause (f) of sub-regulation (2) of regulation 34 after it
+    is required to comply for the first time?
+  - What are the specific disclosures required in a public announcement for a buy-back
+    of securities according to the Securities and Exchange Board of India regulations?
+- source_sentence: 1996. In section 19 of the Depositories Act, 1996 (hereafter in
+    this chapter referred to as the principal Act in this chapter), the following
+    Explanation shall be inserted, namely:- Explanation. For the removal of doubts,
+    it is hereby declared that power to issue directions under this section shall
+    include and always be deemed to have been included the power to direct any person,
+    who made profit or averted loss by indulging in any transaction or activity in
+    contravention of the provisions of this Act or regulations made thereunder, to
+    disgorge an amount equivalent to the wrongful gain made or loss averted by such
+    contravention.
+  sentences:
+  - What are the qualifications required for a judge to be appointed to a Special
+    Court under this Act?
+  - What is the purpose of the Explanation inserted in section 19 of the Depositories
+    Act, 1996?
+  - What is the minimum percentage of total issued shares that the acquirer must reach
+    in order for the delisting offer to be considered successful?
+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: BGE base Financial Matryoshka
+  results:
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 768
+      type: dim_768
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.4691358024691358
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.7469135802469136
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.845679012345679
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.9135802469135802
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.4691358024691358
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.24897119341563784
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.1691358024691358
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.09135802469135802
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.4691358024691358
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.7469135802469136
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.845679012345679
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.9135802469135802
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.6931888396302245
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.6220483049186752
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.6258770441533618
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 512
+      type: dim_512
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.4506172839506173
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.7530864197530864
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.8271604938271605
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.9074074074074074
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.4506172839506173
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.2510288065843621
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.16543209876543208
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.09074074074074073
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.4506172839506173
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.7530864197530864
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.8271604938271605
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.9074074074074074
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.6862124164896819
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.6141950813247109
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.618139737272647
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 256
+      type: dim_256
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.4382716049382716
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.7345679012345679
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.8271604938271605
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.8950617283950617
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.4382716049382716
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.24485596707818924
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.16543209876543208
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.08950617283950617
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.4382716049382716
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.7345679012345679
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.8271604938271605
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.8950617283950617
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.6725732937028854
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.6002816970409561
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.6055931590500198
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 128
+      type: dim_128
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.41358024691358025
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.6851851851851852
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.7777777777777778
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.8703703703703703
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.41358024691358025
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.22839506172839505
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.15555555555555553
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.08703703703703702
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.41358024691358025
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.6851851851851852
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.7777777777777778
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.8703703703703703
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.6396728651848874
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.5658534195571232
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.5718872882660476
+      name: Cosine Map@100
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: dim 64
+      type: dim_64
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.345679012345679
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.5802469135802469
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.6851851851851852
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.7901234567901234
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.345679012345679
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.19341563786008228
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.13703703703703704
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.07901234567901233
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.345679012345679
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.5802469135802469
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.6851851851851852
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.7901234567901234
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.5603350026673091
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.48750489907897315
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.49429085785187665
+      name: Cosine Map@100
+---
+
+# BGE base Financial Matryoshka
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [Snowflake/snowflake-arctic-embed-m-v2.0](https://huggingface.co/Snowflake/snowflake-arctic-embed-m-v2.0) on the json dataset. 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:** [Snowflake/snowflake-arctic-embed-m-v2.0](https://huggingface.co/Snowflake/snowflake-arctic-embed-m-v2.0) <!-- at revision 95c2741480856aa9666782eb4afe11959938017f -->
+- **Maximum Sequence Length:** 8192 tokens
+- **Output Dimensionality:** 768 dimensions
+- **Similarity Function:** Cosine Similarity
+- **Training Dataset:**
+    - json
+- **Language:** en
+- **License:** apache-2.0
+
+### Model Sources
+
+- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
+- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/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': 8192, 'do_lower_case': False}) with Transformer model: GteModel 
+  (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})
+  (2): Normalize()
+)
+```
+
+## 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("sentence_transformers_model_id")
+# Run inference
+sentences = [
+    '1996. In section 19 of the Depositories Act, 1996 (hereafter in this chapter referred to as the principal Act in this chapter), the following Explanation shall be inserted, namely:- Explanation. For the removal of doubts, it is hereby declared that power to issue directions under this section shall include and always be deemed to have been included the power to direct any person, who made profit or averted loss by indulging in any transaction or activity in contravention of the provisions of this Act or regulations made thereunder, to disgorge an amount equivalent to the wrongful gain made or loss averted by such contravention.',
+    'What is the purpose of the Explanation inserted in section 19 of the Depositories Act, 1996?',
+    'What are the qualifications required for a judge to be appointed to a Special Court under this Act?',
+]
+embeddings = model.encode(sentences)
+print(embeddings.shape)
+# [3, 768]
+
+# Get the similarity scores for the embeddings
+similarities = model.similarity(embeddings, embeddings)
+print(similarities.shape)
+# [3, 3]
+```
+
+<!--
+### 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   | 0.4691     |
+| cosine_accuracy@3   | 0.7469     |
+| cosine_accuracy@5   | 0.8457     |
+| cosine_accuracy@10  | 0.9136     |
+| cosine_precision@1  | 0.4691     |
+| cosine_precision@3  | 0.249      |
+| cosine_precision@5  | 0.1691     |
+| cosine_precision@10 | 0.0914     |
+| cosine_recall@1     | 0.4691     |
+| cosine_recall@3     | 0.7469     |
+| cosine_recall@5     | 0.8457     |
+| cosine_recall@10    | 0.9136     |
+| **cosine_ndcg@10**  | **0.6932** |
+| cosine_mrr@10       | 0.622      |
+| cosine_map@100      | 0.6259     |
+
+#### 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   | 0.4506     |
+| cosine_accuracy@3   | 0.7531     |
+| cosine_accuracy@5   | 0.8272     |
+| cosine_accuracy@10  | 0.9074     |
+| cosine_precision@1  | 0.4506     |
+| cosine_precision@3  | 0.251      |
+| cosine_precision@5  | 0.1654     |
+| cosine_precision@10 | 0.0907     |
+| cosine_recall@1     | 0.4506     |
+| cosine_recall@3     | 0.7531     |
+| cosine_recall@5     | 0.8272     |
+| cosine_recall@10    | 0.9074     |
+| **cosine_ndcg@10**  | **0.6862** |
+| cosine_mrr@10       | 0.6142     |
+| cosine_map@100      | 0.6181     |
+
+#### 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   | 0.4383     |
+| cosine_accuracy@3   | 0.7346     |
+| cosine_accuracy@5   | 0.8272     |
+| cosine_accuracy@10  | 0.8951     |
+| cosine_precision@1  | 0.4383     |
+| cosine_precision@3  | 0.2449     |
+| cosine_precision@5  | 0.1654     |
+| cosine_precision@10 | 0.0895     |
+| cosine_recall@1     | 0.4383     |
+| cosine_recall@3     | 0.7346     |
+| cosine_recall@5     | 0.8272     |
+| cosine_recall@10    | 0.8951     |
+| **cosine_ndcg@10**  | **0.6726** |
+| cosine_mrr@10       | 0.6003     |
+| cosine_map@100      | 0.6056     |
+
+#### 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   | 0.4136     |
+| cosine_accuracy@3   | 0.6852     |
+| cosine_accuracy@5   | 0.7778     |
+| cosine_accuracy@10  | 0.8704     |
+| cosine_precision@1  | 0.4136     |
+| cosine_precision@3  | 0.2284     |
+| cosine_precision@5  | 0.1556     |
+| cosine_precision@10 | 0.087      |
+| cosine_recall@1     | 0.4136     |
+| cosine_recall@3     | 0.6852     |
+| cosine_recall@5     | 0.7778     |
+| cosine_recall@10    | 0.8704     |
+| **cosine_ndcg@10**  | **0.6397** |
+| cosine_mrr@10       | 0.5659     |
+| cosine_map@100      | 0.5719     |
+
+#### 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   | 0.3457     |
+| cosine_accuracy@3   | 0.5802     |
+| cosine_accuracy@5   | 0.6852     |
+| cosine_accuracy@10  | 0.7901     |
+| cosine_precision@1  | 0.3457     |
+| cosine_precision@3  | 0.1934     |
+| cosine_precision@5  | 0.137      |
+| cosine_precision@10 | 0.079      |
+| cosine_recall@1     | 0.3457     |
+| cosine_recall@3     | 0.5802     |
+| cosine_recall@5     | 0.6852     |
+| cosine_recall@10    | 0.7901     |
+| **cosine_ndcg@10**  | **0.5603** |
+| cosine_mrr@10       | 0.4875     |
+| cosine_map@100      | 0.4943     |
+
+<!--
+## 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
+
+#### json
+
+* Dataset: json
+* Size: 1,456 training samples
+* Columns: <code>positive</code> and <code>anchor</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | positive                                                                               | anchor                                                                             |
+  |:--------|:---------------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|
+  | type    | string                                                                                 | string                                                                             |
+  | details | <ul><li>min: 110 tokens</li><li>mean: 795.06 tokens</li><li>max: 1042 tokens</li></ul> | <ul><li>min: 13 tokens</li><li>mean: 30.5 tokens</li><li>max: 215 tokens</li></ul> |
+* Samples:
+  | positive                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                 | anchor                                                                                                                                                          |
+  |:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------------------------------------------------------------------------------------|
+  | <code>its continued obligations towards the holders of debt securities. We have satisfied ourselves about the ability of the issuer to service the debt securities. PLACE DATE: DEBENTURE TRUSTEE TO THE ISSUE WITH HIS SEAL Page - 65 - of 68 FORMAT OF DUE DILIGENCE CERTIFICATE TO BE GIVEN BY THE DEBENTURE TRUSTEE BEFORE OPENING OF THE ISSUE To, SECURITIES AND EXCHANGE BOARD OF INDIA Dear Sir / Madam, SUB. : ISSUE OF BY (Issuer) We, the Debenture Trustee (s) to the above mentioned forthcoming issue state as follows: (1) We have examined documents pertaining to the said issue and other relevant documents. (2) On the basis of such examination and discussions with the issuer, its Mayor/Deputy Mayor /Directors and other officers, other agencies and independent verification of the various relevant documents,- (a) WE CONFIRM that the issuer has made adequate provisions regarding escrow payment mechanism for repayment of debt obligations, and (b) We have satisfied ourselves about the ability of the iss...</code> | <code>What specific provisions has the issuer made regarding the repayment of debt obligations?</code>                                                          |
+  | <code>sums realised by way of penalties to Consolidated Fund of India 23L. Appeal to Securities Appellate Tribunal 23M. Offences 23N. Composition of certain offences 23-O. Power to grant immunity 24. Contravention by companies 25. Certain offences to be cognizable 26. Cognizance of offences by courts 26A. Establishment of Special Courts 26B. Offences triable by Special Courts 26C. Appeal and revision 26D. Application of Code to proceedings before Special Court 26E. Transitional Provisions MISCELLANEOUS 27. Title to dividends 27A. Right to receive income from collective investment scheme 27B. Right to receive income from mutual fund 28. Act not to apply in certain cases 29. Protection of action taken in good faith 29A. Power to delegate 29B. Powers of Board not to apply to International Financial Services Centre 30. Power to make rules 30A. Special Provisions related to commodity derivatives 30B. Special provisions related to pooled investment vehicle 31. Power of Securities and Exchange Boar...</code> | <code>What powers does the Securities and Exchange Board of India have to make regulations according to the Securities Contracts (Regulation) Act, 1956?</code> |
+  | <code>the depository or the securities market as a result of the default; and (c) the repetitive nature of the default. ] CHAPTER X PROCEDURE FOR ACTION IN CASE OF DEFAULT Liability for action in case of default 92. Without prejudice to the power of the Board to take action, under the provisions of the Act and the Depositories Act, if a depository or a participant:- (a) contravenes any of the provisions of the Act, the Depositories Act, the bye-laws, agreements and these regulations; (b) fails to furnish any information relating to its activity as a depository or participant as required under these regulations; (c) does not furnish the information called for by the Board under clause (a) of sub-section (1) of section 18 of the Depositories Act or furnishes information which is false or misleading in any material particular; (d) does not co-operate in any inspection or investigation or enquiry conducted by the Board; (e) fails to comply with any direction of the Board issued under section 18 ...</code> | <code>What actions can the Board take against a depository or participant that fails to comply with the provisions of the Act or the Depositories Act?</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`: 32
+- `per_device_eval_batch_size`: 16
+- `gradient_accumulation_steps`: 16
+- `learning_rate`: 2e-05
+- `num_train_epochs`: 4
+- `lr_scheduler_type`: cosine
+- `warmup_ratio`: 0.1
+- `bf16`: True
+- `tf32`: True
+- `load_best_model_at_end`: True
+- `optim`: adamw_torch_fused
+- `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`: 32
+- `per_device_eval_batch_size`: 16
+- `per_gpu_train_batch_size`: None
+- `per_gpu_eval_batch_size`: None
+- `gradient_accumulation_steps`: 16
+- `eval_accumulation_steps`: None
+- `torch_empty_cache_steps`: None
+- `learning_rate`: 2e-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`: 4
+- `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
+- `use_ipex`: 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`: 0
+- `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}
+- `deepspeed`: None
+- `label_smoothing_factor`: 0.0
+- `optim`: adamw_torch_fused
+- `optim_args`: None
+- `adafactor`: False
+- `group_by_length`: False
+- `length_column_name`: length
+- `ddp_find_unused_parameters`: None
+- `ddp_bucket_cap_mb`: None
+- `ddp_broadcast_buffers`: False
+- `dataloader_pin_memory`: True
+- `dataloader_persistent_workers`: False
+- `skip_memory_metrics`: True
+- `use_legacy_prediction_loop`: False
+- `push_to_hub`: False
+- `resume_from_checkpoint`: None
+- `hub_model_id`: None
+- `hub_strategy`: every_save
+- `hub_private_repo`: None
+- `hub_always_push`: False
+- `gradient_checkpointing`: False
+- `gradient_checkpointing_kwargs`: None
+- `include_inputs_for_metrics`: False
+- `include_for_metrics`: []
+- `eval_do_concat_batches`: True
+- `fp16_backend`: auto
+- `push_to_hub_model_id`: None
+- `push_to_hub_organization`: None
+- `mp_parameters`: 
+- `auto_find_batch_size`: False
+- `full_determinism`: False
+- `torchdynamo`: None
+- `ray_scope`: last
+- `ddp_timeout`: 1800
+- `torch_compile`: False
+- `torch_compile_backend`: None
+- `torch_compile_mode`: None
+- `include_tokens_per_second`: False
+- `include_num_input_tokens_seen`: False
+- `neftune_noise_alpha`: None
+- `optim_target_modules`: None
+- `batch_eval_metrics`: False
+- `eval_on_start`: False
+- `use_liger_kernel`: False
+- `eval_use_gather_object`: False
+- `average_tokens_across_devices`: False
+- `prompts`: None
+- `batch_sampler`: no_duplicates
+- `multi_dataset_batch_sampler`: proportional
+
+</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 |
+|:-------:|:------:|:-------------:|:----------------------:|:----------------------:|:----------------------:|:----------------------:|:---------------------:|
+| 1.0     | 3      | -             | 0.6688                 | 0.6577                 | 0.6456                 | 0.6018                 | 0.5202                |
+| 2.0     | 6      | -             | 0.6652                 | 0.6624                 | 0.6634                 | 0.6147                 | 0.5320                |
+| 3.0     | 9      | -             | 0.6868                 | 0.6831                 | 0.6678                 | 0.6330                 | 0.5537                |
+| 3.3478  | 10     | 39.9839       | -                      | -                      | -                      | -                      | -                     |
+| **4.0** | **12** | **-**         | **0.6932**             | **0.6862**             | **0.6726**             | **0.6397**             | **0.5603**            |
+
+* The bold row denotes the saved checkpoint.
+
+### Framework Versions
+- Python: 3.11.11
+- Sentence Transformers: 4.1.0
+- Transformers: 4.52.3
+- PyTorch: 2.7.0+cu126
+- Accelerate: 1.7.0
+- Datasets: 3.6.0
+- Tokenizers: 0.21.1
+
+## 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 +1,38 @@
+{
+  "architectures": [
+    "GteModel"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "auto_map": {
+    "AutoConfig": "Snowflake/snowflake-arctic-embed-m-v2.0--configuration_hf_alibaba_nlp_gte.GteConfig",
+    "AutoModel": "Snowflake/snowflake-arctic-embed-m-v2.0--modeling_hf_alibaba_nlp_gte.GteModel"
+  },
+  "classifier_dropout": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "layer_norm_type": "layer_norm",
+  "logn_attention_clip1": false,
+  "logn_attention_scale": false,
+  "matryoshka_dimensions": [
+    256
+  ],
+  "max_position_embeddings": 8192,
+  "model_type": "gte",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pack_qkv": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "rope",
+  "rope_scaling": null,
+  "rope_theta": 160000,
+  "torch_dtype": "float32",
+  "transformers_version": "4.52.3",
+  "type_vocab_size": 1,
+  "unpad_inputs": "true",
+  "use_memory_efficient_attention": "true",
+  "vocab_size": 250048
+}

config_sentence_transformers.json

@@ -0,0 +1,12 @@
+{
+  "__version__": {
+    "sentence_transformers": "4.1.0",
+    "transformers": "4.52.3",
+    "pytorch": "2.7.0+cu126"
+  },
+  "prompts": {
+    "query": "query: "
+  },
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine"
+}

eval/Information-Retrieval_evaluation_dim_128_results.csv

@@ -0,0 +1,11 @@
+epoch,steps,cosine-Accuracy@1,cosine-Accuracy@3,cosine-Accuracy@5,cosine-Accuracy@10,cosine-Precision@1,cosine-Recall@1,cosine-Precision@3,cosine-Recall@3,cosine-Precision@5,cosine-Recall@5,cosine-Precision@10,cosine-Recall@10,cosine-MRR@10,cosine-NDCG@10,cosine-MAP@100
+1.0,3,0.38271604938271603,0.6296296296296297,0.7160493827160493,0.8271604938271605,0.38271604938271603,0.38271604938271603,0.20987654320987653,0.6296296296296297,0.14320987654320985,0.7160493827160493,0.08271604938271604,0.8271604938271605,0.5305310601606898,0.6021955458801781,0.5382570699169317
+2.0,6,0.3888888888888889,0.654320987654321,0.7654320987654321,0.8395061728395061,0.3888888888888889,0.3888888888888889,0.21810699588477364,0.654320987654321,0.1530864197530864,0.7654320987654321,0.0839506172839506,0.8395061728395061,0.5416103272584755,0.6140910300966435,0.5495464886177235
+3.0,9,0.4074074074074074,0.6851851851851852,0.7654320987654321,0.8641975308641975,0.4074074074074074,0.4074074074074074,0.22839506172839505,0.6851851851851852,0.1530864197530864,0.7654320987654321,0.08641975308641975,0.8641975308641975,0.5579389574759945,0.6321441276006302,0.5642732177438856
+4.0,12,0.41358024691358025,0.691358024691358,0.7777777777777778,0.8641975308641975,0.41358024691358025,0.41358024691358025,0.23045267489711932,0.691358024691358,0.15555555555555553,0.7777777777777778,0.08641975308641975,0.8641975308641975,0.5667793454830491,0.6391246452415552,0.5733425105038232
+1.0,3,0.38271604938271603,0.6296296296296297,0.7098765432098766,0.8271604938271605,0.38271604938271603,0.38271604938271603,0.20987654320987653,0.6296296296296297,0.14197530864197527,0.7098765432098766,0.08271604938271604,0.8271604938271605,0.5301268861454047,0.6018461575195746,0.5377603400581437
+2.0,6,0.3888888888888889,0.6604938271604939,0.7592592592592593,0.8395061728395061,0.3888888888888889,0.3888888888888889,0.22016460905349794,0.6604938271604939,0.15185185185185185,0.7592592592592593,0.0839506172839506,0.8395061728395061,0.5419189692337841,0.6143297820830638,0.5498389832031331
+1.0,3,0.38271604938271603,0.6296296296296297,0.7098765432098766,0.8271604938271605,0.38271604938271603,0.38271604938271603,0.20987654320987653,0.6296296296296297,0.1419753086419753,0.7098765432098766,0.08271604938271604,0.8271604938271605,0.5300852439741329,0.6018097174751208,0.5377970581405588
+2.0,6,0.3888888888888889,0.6666666666666666,0.7654320987654321,0.8395061728395061,0.3888888888888889,0.3888888888888889,0.2222222222222222,0.6666666666666666,0.1530864197530864,0.7654320987654321,0.0839506172839506,0.8395061728395061,0.5424064275916128,0.6147165742260062,0.550314018558461
+3.0,9,0.4074074074074074,0.6851851851851852,0.7654320987654321,0.8641975308641975,0.4074074074074074,0.4074074074074074,0.22839506172839505,0.6851851851851852,0.1530864197530864,0.7654320987654321,0.08641975308641975,0.8641975308641975,0.5589677640603566,0.6329523359560095,0.5653216884828832
+4.0,12,0.41358024691358025,0.6851851851851852,0.7777777777777778,0.8703703703703703,0.41358024691358025,0.41358024691358025,0.22839506172839505,0.6851851851851852,0.15555555555555553,0.7777777777777778,0.08703703703703702,0.8703703703703703,0.5658534195571232,0.6396728651848874,0.5718872882660476

eval/Information-Retrieval_evaluation_dim_256_results.csv

@@ -0,0 +1,12 @@
+epoch,steps,cosine-Accuracy@1,cosine-Accuracy@3,cosine-Accuracy@5,cosine-Accuracy@10,cosine-Precision@1,cosine-Recall@1,cosine-Precision@3,cosine-Recall@3,cosine-Precision@5,cosine-Recall@5,cosine-Precision@10,cosine-Recall@10,cosine-MRR@10,cosine-NDCG@10,cosine-MAP@100
+1.0,3,0.4074074074074074,0.7098765432098766,0.7901234567901234,0.8827160493827161,0.4074074074074074,0.4074074074074074,0.23662551440329216,0.7098765432098766,0.1580246913580247,0.7901234567901234,0.0882716049382716,0.8827160493827161,0.5694395453654711,0.645656331681653,0.5748532909188923
+2.0,6,0.42592592592592593,0.7222222222222222,0.8024691358024691,0.8950617283950617,0.42592592592592593,0.42592592592592593,0.24074074074074073,0.7222222222222222,0.16049382716049382,0.8024691358024691,0.08950617283950617,0.8950617283950617,0.5890113658632177,0.6635896599917582,0.5938310269670422
+3.0,9,0.43209876543209874,0.7345679012345679,0.8271604938271605,0.8888888888888888,0.43209876543209874,0.43209876543209874,0.24485596707818924,0.7345679012345679,0.16543209876543208,0.8271604938271605,0.08888888888888888,0.8888888888888888,0.5959680580050949,0.668083339265037,0.6015420392173096
+4.0,12,0.4382716049382716,0.7345679012345679,0.8271604938271605,0.8950617283950617,0.4382716049382716,0.4382716049382716,0.24485596707818924,0.7345679012345679,0.16543209876543208,0.8271604938271605,0.08950617283950617,0.8950617283950617,0.599252890456594,0.6717650853475061,0.6045643524656577
+1.0,3,0.4074074074074074,0.7098765432098766,0.7901234567901234,0.8827160493827161,0.4074074074074074,0.4074074074074074,0.23662551440329216,0.7098765432098766,0.1580246913580247,0.7901234567901234,0.0882716049382716,0.8827160493827161,0.569353811483441,0.6455672274771977,0.5747458795870237
+2.0,6,0.42592592592592593,0.7222222222222222,0.8024691358024691,0.8950617283950617,0.42592592592592593,0.42592592592592593,0.24074074074074073,0.7222222222222222,0.16049382716049382,0.8024691358024691,0.08950617283950617,0.8950617283950617,0.5890113658632177,0.6635896599917582,0.5937888489324974
+3.0,9,0.43209876543209874,0.7345679012345679,0.8271604938271605,0.8888888888888888,0.43209876543209874,0.43209876543209874,0.24485596707818924,0.7345679012345679,0.16543209876543208,0.8271604938271605,0.08888888888888888,0.8888888888888888,0.5956594160297862,0.6678128222845503,0.6012364493420029
+1.0,3,0.4074074074074074,0.7098765432098766,0.7901234567901234,0.8827160493827161,0.4074074074074074,0.4074074074074074,0.23662551440329216,0.7098765432098766,0.1580246913580247,0.7901234567901234,0.0882716049382716,0.8827160493827161,0.569353811483441,0.6455672274771977,0.5747701815434549
+2.0,6,0.42592592592592593,0.7160493827160493,0.8024691358024691,0.8950617283950617,0.42592592592592593,0.42592592592592593,0.23868312757201646,0.7160493827160493,0.16049382716049382,0.8024691358024691,0.08950617283950617,0.8950617283950617,0.5888056045463451,0.6634322544912167,0.5936225951593602
+3.0,9,0.43209876543209874,0.7345679012345679,0.8271604938271605,0.8888888888888888,0.43209876543209874,0.43209876543209874,0.24485596707818924,0.7345679012345679,0.16543209876543208,0.8271604938271605,0.08888888888888888,0.8888888888888888,0.5956594160297862,0.6678128222845503,0.6012907092614589
+4.0,12,0.4382716049382716,0.7345679012345679,0.8271604938271605,0.8950617283950617,0.4382716049382716,0.4382716049382716,0.24485596707818924,0.7345679012345679,0.16543209876543208,0.8271604938271605,0.08950617283950617,0.8950617283950617,0.6002816970409561,0.6725732937028854,0.6055931590500198

eval/Information-Retrieval_evaluation_dim_512_results.csv

@@ -0,0 +1,12 @@
+epoch,steps,cosine-Accuracy@1,cosine-Accuracy@3,cosine-Accuracy@5,cosine-Accuracy@10,cosine-Precision@1,cosine-Recall@1,cosine-Precision@3,cosine-Recall@3,cosine-Precision@5,cosine-Recall@5,cosine-Precision@10,cosine-Recall@10,cosine-MRR@10,cosine-NDCG@10,cosine-MAP@100
+1.0,3,0.41358024691358025,0.7037037037037037,0.7901234567901234,0.8827160493827161,0.41358024691358025,0.41358024691358025,0.2345679012345679,0.7037037037037037,0.1580246913580247,0.7901234567901234,0.08827160493827159,0.8827160493827161,0.5791544189692339,0.6530314161476585,0.5847635261609861
+2.0,6,0.42592592592592593,0.7160493827160493,0.8148148148148148,0.9074074074074074,0.42592592592592593,0.42592592592592593,0.23868312757201646,0.7160493827160493,0.16296296296296295,0.8148148148148148,0.09074074074074073,0.9074074074074074,0.5879850088183423,0.6654705449887022,0.5916081345311078
+3.0,9,0.4506172839506173,0.7530864197530864,0.8271604938271605,0.9074074074074074,0.4506172839506173,0.4506172839506173,0.2510288065843621,0.7530864197530864,0.16543209876543208,0.8271604938271605,0.09074074074074073,0.9074074074074074,0.6111086615716245,0.6837877914235437,0.6149641889523849
+4.0,12,0.4506172839506173,0.7530864197530864,0.8271604938271605,0.9074074074074074,0.4506172839506173,0.4506172839506173,0.2510288065843621,0.7530864197530864,0.16543209876543208,0.8271604938271605,0.09074074074074073,0.9074074074074074,0.6141950813247109,0.6862124164896819,0.618138129001409
+1.0,3,0.41975308641975306,0.7037037037037037,0.7901234567901234,0.8827160493827161,0.41975308641975306,0.41975308641975306,0.2345679012345679,0.7037037037037037,0.1580246913580247,0.7901234567901234,0.08827160493827159,0.8827160493827161,0.5825494806976288,0.6555801445258522,0.5881869785447996
+2.0,6,0.41975308641975306,0.7160493827160493,0.8148148148148148,0.9074074074074074,0.41975308641975306,0.41975308641975306,0.23868312757201646,0.7160493827160493,0.16296296296296295,0.8148148148148148,0.09074074074074073,0.9074074074074074,0.5848985890652558,0.6631923335909952,0.5885231233926944
+3.0,9,0.4567901234567901,0.7469135802469136,0.8271604938271605,0.9074074074074074,0.4567901234567901,0.4567901234567901,0.24897119341563784,0.7469135802469136,0.16543209876543208,0.8271604938271605,0.09074074074074073,0.9074074074074074,0.6147094846168919,0.6864462886956018,0.61858004728435
+1.0,3,0.41975308641975306,0.7037037037037037,0.7901234567901234,0.8888888888888888,0.41975308641975306,0.41975308641975306,0.2345679012345679,0.7037037037037037,0.1580246913580247,0.7901234567901234,0.08888888888888886,0.8888888888888888,0.5835856359004508,0.6577453114005705,0.5886596467084392
+2.0,6,0.41975308641975306,0.7160493827160493,0.8148148148148148,0.9074074074074074,0.41975308641975306,0.41975308641975306,0.23868312757201646,0.7160493827160493,0.16296296296296295,0.8148148148148148,0.09074074074074073,0.9074074074074074,0.5838697824808937,0.6623841252356157,0.5874755864501471
+3.0,9,0.4506172839506173,0.7469135802469136,0.8271604938271605,0.9074074074074074,0.4506172839506173,0.4506172839506173,0.24897119341563784,0.7469135802469136,0.16543209876543208,0.8271604938271605,0.09074074074074073,0.9074074074074074,0.6102856163041347,0.6830893519620286,0.6141635115406537
+4.0,12,0.4506172839506173,0.7530864197530864,0.8271604938271605,0.9074074074074074,0.4506172839506173,0.4506172839506173,0.2510288065843621,0.7530864197530864,0.16543209876543208,0.8271604938271605,0.09074074074074073,0.9074074074074074,0.6141950813247109,0.6862124164896819,0.618139737272647

eval/Information-Retrieval_evaluation_dim_64_results.csv

@@ -0,0 +1,11 @@
+epoch,steps,cosine-Accuracy@1,cosine-Accuracy@3,cosine-Accuracy@5,cosine-Accuracy@10,cosine-Precision@1,cosine-Recall@1,cosine-Precision@3,cosine-Recall@3,cosine-Precision@5,cosine-Recall@5,cosine-Precision@10,cosine-Recall@10,cosine-MRR@10,cosine-NDCG@10,cosine-MAP@100
+1.0,3,0.29012345679012347,0.5555555555555556,0.6358024691358025,0.7592592592592593,0.29012345679012347,0.29012345679012347,0.18518518518518517,0.5555555555555556,0.1271604938271605,0.6358024691358025,0.07592592592592592,0.7592592592592593,0.44443219674701184,0.5202045641791371,0.4516865012402207
+2.0,6,0.3148148148148148,0.5617283950617284,0.6728395061728395,0.7716049382716049,0.3148148148148148,0.3148148148148148,0.18724279835390945,0.5617283950617284,0.13456790123456788,0.6728395061728395,0.07716049382716049,0.7716049382716049,0.4595507544581621,0.53470631928077,0.4668547556983398
+3.0,9,0.3333333333333333,0.5740740740740741,0.6790123456790124,0.7839506172839507,0.3333333333333333,0.3333333333333333,0.19135802469135801,0.5740740740740741,0.13580246913580246,0.6790123456790124,0.07839506172839504,0.7839506172839507,0.4795732902214384,0.5530355054744915,0.486601128663717
+4.0,12,0.345679012345679,0.5802469135802469,0.6851851851851852,0.7901234567901234,0.345679012345679,0.345679012345679,0.19341563786008228,0.5802469135802469,0.13703703703703704,0.6851851851851852,0.07901234567901233,0.7901234567901234,0.48726484420928873,0.56013834475686,0.4939964614452466
+1.0,3,0.29012345679012347,0.5617283950617284,0.6296296296296297,0.7592592592592593,0.29012345679012347,0.29012345679012347,0.18724279835390945,0.5617283950617284,0.1259259259259259,0.6296296296296297,0.07592592592592592,0.7592592592592593,0.4458553791887127,0.521340628725392,0.453081691903953
+2.0,6,0.3148148148148148,0.5617283950617284,0.6728395061728395,0.7716049382716049,0.3148148148148148,0.3148148148148148,0.18724279835390945,0.5617283950617284,0.13456790123456788,0.6728395061728395,0.07716049382716049,0.7716049382716049,0.4596977268273567,0.5348475159090087,0.46692789473198437
+1.0,3,0.29012345679012347,0.5617283950617284,0.6296296296296297,0.7592592592592593,0.29012345679012347,0.29012345679012347,0.18724279835390945,0.5617283950617284,0.1259259259259259,0.6296296296296297,0.07592592592592592,0.7592592592592593,0.44453507740544795,0.5202217389554445,0.45181102007783713
+2.0,6,0.30864197530864196,0.5555555555555556,0.6728395061728395,0.7716049382716049,0.30864197530864196,0.30864197530864196,0.18518518518518517,0.5555555555555556,0.13456790123456788,0.6728395061728395,0.07716049382716049,0.7716049382716049,0.4559866745051933,0.5320310829157818,0.46317311303593856
+3.0,9,0.3333333333333333,0.5740740740740741,0.6790123456790124,0.7901234567901234,0.3333333333333333,0.3333333333333333,0.19135802469135801,0.5740740740740741,0.13580246913580246,0.6790123456790124,0.07901234567901233,0.7901234567901234,0.4788016852831669,0.5537221096806089,0.48526467818974156
+4.0,12,0.345679012345679,0.5802469135802469,0.6851851851851852,0.7901234567901234,0.345679012345679,0.345679012345679,0.19341563786008228,0.5802469135802469,0.13703703703703704,0.6851851851851852,0.07901234567901233,0.7901234567901234,0.48750489907897315,0.5603350026673091,0.49429085785187665

eval/Information-Retrieval_evaluation_dim_768_results.csv

@@ -0,0 +1,12 @@
+epoch,steps,cosine-Accuracy@1,cosine-Accuracy@3,cosine-Accuracy@5,cosine-Accuracy@10,cosine-Precision@1,cosine-Recall@1,cosine-Precision@3,cosine-Recall@3,cosine-Precision@5,cosine-Recall@5,cosine-Precision@10,cosine-Recall@10,cosine-MRR@10,cosine-NDCG@10,cosine-MAP@100
+1.0,3,0.4382716049382716,0.7222222222222222,0.8024691358024691,0.8950617283950617,0.4382716049382716,0.4382716049382716,0.24074074074074073,0.7222222222222222,0.16049382716049382,0.8024691358024691,0.08950617283950615,0.8950617283950617,0.5928522437781698,0.6662075156307669,0.597623503737822
+2.0,6,0.41975308641975306,0.7283950617283951,0.8271604938271605,0.9012345679012346,0.41975308641975306,0.41975308641975306,0.242798353909465,0.7283950617283951,0.16543209876543208,0.8271604938271605,0.09012345679012344,0.9012345679012346,0.5901136586321772,0.6663417172853776,0.5943313477669211
+3.0,9,0.4444444444444444,0.7345679012345679,0.8395061728395061,0.9135802469135802,0.4444444444444444,0.4444444444444444,0.24485596707818924,0.7345679012345679,0.1679012345679012,0.8395061728395061,0.09135802469135802,0.9135802469135802,0.607363315696649,0.6821825540795592,0.6110287478548849
+4.0,12,0.4691358024691358,0.7469135802469136,0.845679012345679,0.9135802469135802,0.4691358024691358,0.4691358024691358,0.24897119341563784,0.7469135802469136,0.1691358024691358,0.845679012345679,0.09135802469135802,0.9135802469135802,0.6220483049186752,0.6931888396302245,0.625915955793166
+1.0,3,0.4382716049382716,0.7345679012345679,0.8024691358024691,0.8950617283950617,0.4382716049382716,0.4382716049382716,0.2448559670781893,0.7345679012345679,0.16049382716049382,0.8024691358024691,0.08950617283950615,0.8950617283950617,0.5951327650401725,0.6680529817242347,0.5999731063107839
+2.0,6,0.41975308641975306,0.7345679012345679,0.8271604938271605,0.9012345679012346,0.41975308641975306,0.41975308641975306,0.2448559670781893,0.7345679012345679,0.16543209876543208,0.8271604938271605,0.09012345679012344,0.9012345679012346,0.5907137958063885,0.6668587439708613,0.5949318205672114
+3.0,9,0.4567901234567901,0.7345679012345679,0.8395061728395061,0.9135802469135802,0.4567901234567901,0.4567901234567901,0.24485596707818924,0.7345679012345679,0.1679012345679012,0.8395061728395061,0.09135802469135802,0.9135802469135802,0.6136120909269057,0.686779193022766,0.617263754517914
+1.0,3,0.4382716049382716,0.7283950617283951,0.808641975308642,0.9012345679012346,0.4382716049382716,0.4382716049382716,0.242798353909465,0.7283950617283951,0.16172839506172837,0.808641975308642,0.09012345679012344,0.9012345679012346,0.5944052518126591,0.6688240150844199,0.5986260312608651
+2.0,6,0.41975308641975306,0.7222222222222222,0.8271604938271605,0.9012345679012346,0.41975308641975306,0.41975308641975306,0.24074074074074073,0.7222222222222222,0.16543209876543208,0.8271604938271605,0.09012345679012344,0.9012345679012346,0.5886561826376642,0.6651946906534251,0.5928812643052896
+3.0,9,0.4567901234567901,0.7345679012345679,0.845679012345679,0.9135802469135802,0.4567901234567901,0.4567901234567901,0.24485596707818924,0.7345679012345679,0.1691358024691358,0.845679012345679,0.09135802469135802,0.9135802469135802,0.6136561826376641,0.6868390431651261,0.6173396640342221
+4.0,12,0.4691358024691358,0.7469135802469136,0.845679012345679,0.9135802469135802,0.4691358024691358,0.4691358024691358,0.24897119341563784,0.7469135802469136,0.1691358024691358,0.845679012345679,0.09135802469135802,0.9135802469135802,0.6220483049186752,0.6931888396302245,0.6258770441533618

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27157dd3963fc12375050e83b2d0de6822dfae67dbd95e85b1cccc3d118d19c0
+size 1221487872

modules.json

@@ -0,0 +1,20 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  },
+  {
+    "idx": 2,
+    "name": "2",
+    "path": "2_Normalize",
+    "type": "sentence_transformers.models.Normalize"
+  }
+]

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 8192,
+  "do_lower_case": false
+}

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "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": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa7a6ad87a7ce8fe196787355f6af7d03aee94d19c54a5eb1392ed18c8ef451a
+size 17082988

tokenizer_config.json

@@ -0,0 +1,62 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "max_length": 512,
+  "model_max_length": 32768,
+  "pad_to_multiple_of": null,
+  "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "</s>",
+  "stride": 0,
+  "tokenizer_class": "XLMRobertaTokenizerFast",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<unk>"
+}