Add new SentenceTransformer model

.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 +1,5 @@
+{
+    "embedding_dimension": 2048,
+    "pooling_mode": "mean",
+    "include_prompt": true
+}

README.md

@@ -0,0 +1,1232 @@
+---
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- dataset_size:15509
+- loss:MultipleNegativesRankingLoss
+base_model: nvidia/llama-nemotron-embed-1b-v2
+widget:
+- source_sentence: What was the total underlying EBITDA for FY23?
+  sentences:
+  - 'Refining & Chemicals
+
+
+    Refining Chemicals Q1 2020 -6,292 -2,410 Q1 2021 10,205 4,470 Change Q1 2020 to
+    Q1 2021 +16,497 +6,880
+
+
+    ''000 tons
+
+
+    Q1 2020 Q1 2021 Volume 276.5 298.0 Change +7.8%
+
+
+    Operating Profit
+
+
+    Production of Major Chemical Products
+
+
+    RMB Million
+
+
+    ''000 tons
+
+
+    Crude Processing Volume
+
+
+    Production of Major Oil Products
+
+
+    MM bbl
+
+
+    Q1 2021 Q1 2020 Change Ethylene 1,609 1,539 4.5% Synthetic Resin 2,642 2,473 6.8%
+    Synthetic Fiber Raw Materials 316 342 -7.6% Synthetic Rubber 263 246 6.9% Urea
+    382 261 46.4%
+
+
+    Q1 2021 Q1 2020 Change Total 26,946 25,208 6.9% Gasoline 12,395 10,967 13.0% Kerosene
+    2,842 2,394 18.7% Diesel 11,709 11,847 -1.2%'
+  - 'Year Core business TCXO chip shortage Total FY19 $114m $114m FY20 $119m $119m
+    FY21 $128m $128m FY22 $141m $8m $149m FY23 $164m $8m $172m
+
+
+    Strong core business growth offsets chip-shortage revenue impacts Financial result
+    reflects investment in future growth and inflationary pressures
+
+
+    Revenue
+
+
+    Revenue Gross Margin $180.3m $88.8m ▲$8.4m +5% ▼$1.3m -7%
+
+
+    Underlying EBITDA Operating cash flow $42.2m $11.1m ▼$12.2m -23% ▼$19.1m -63%
+
+
+    Net profit after tax Net cash $23.2m $16.5m ▼$-9.9m -30% ▼$6.8m -29%
+
+
+    Year Core TCXO chip shortage Associate Total FY19 $11m $11m FY20 $15m $15m FY21
+    $23m $23m FY22 $37m $11m $15m $63m FY23 $39m $11m $15m $65m
+
+
+    Underlying EBITDA'
+  - 'Key Metrics Significant growth across all key metrics
+
+
+    FY23 includes an 8-month contribution from StarVale (completed 1 November 2022).
+
+
+    Operating cash flow less capex.
+
+
+    NPATA and EPSA are before amortisation of acquired intangible assets.
+
+
+    Metric FY24 ($m) FY23 ($m) Growth (%) Notes Total Transaction Value 1,054 852
+    +24% Lottery Retailing 544 (FY23: 449) Group Revenue 159.3 118.7 +34% Revenue
+    Margin 15.1% (FY23: 13.9%) Underlying EBITDA 2 76.6 58.9 +30% Und. EBITDA Margin
+    48.1% (FY23: 49.6%) Underlying NPATA 2,3 46.4 35.3 +31% Und. EPSA 2,3 73.7 cps
+    (FY23: 56.1 cps) Free Cash Flow 4 54.1 47.5 +14% Cash Conversion 125% (FY23: 146%)
+    Dividend Declared (cps) 54.5 43.0 +27% 1H: 27.0 cps (23.0)
+
+
+    Underlying reflects adjustments for one-off costs: EBITDA $1.4m in FY24 (FY23:
+    $0.8m) and NPATA $0.8m in FY24 (FY23: $1.5m).'
+- source_sentence: How much money did the business bring in from core tasks in the
+    final quarter compared to the prior year?
+  sentences:
+  - 'Please refer to the Quarterly report for further details
+
+
+    2021 are predecessor combined financial figures
+
+
+    Summary statement of cash flow
+
+
+    OTL Q4 PRESENTATION
+
+
+    YTD 22 cash flow from investing and financing activities are greatly affected
+    by split, re-organisation and financing transactions recorded in Q1 22
+
+
+    Cash Flow (NOKm) Q4 22 Q4 21 * FY 22 FY 21 * Profit/(loss) before tax 108,7 47,5
+    226,2 102,8 Adjustment for provisions and other non-cash elements 97,7 76,9 438,9
+    300,0 Changes in working capital 89,7 62,4 10,6 (7,5) Cash generated from operations
+    296,1 186,8 675,7 395,2 Net interest (paid) / received (30,3) (1,9) (86,8) (5,4)
+    Net income tax paid (6,1) (3,0) (21,2) (20,8) Net cash flow from operating activities
+    259,6 182,0 567,7 369,1 Net cash flow from investing activities (102,4) (309,0)
+    (2 705,4) (437,7) Net cash flow from financing activities (4,8) 417,5 2 200,2
+    445,7 Effects of exchange rate changes on cash and cash equivalents (15,6) (0,8)
+    (0,1) (1,7) Net increase (decrease) in cash and cash equivalents 136,9 289,8 62,3
+    375,3
+
+
+    Cash flow
+
+
+    Comments'
+  - '2023 (£) 2022 (£) For audit services Audit of the financial statements of the
+    company 10,655 9,650 For other services Taxation compliance services 917 1,000
+    All other non-audit services 1,833 923 2,750 1,923
+
+
+    Fees payable to the company''s auditor and associates:
+
+
+    Government grants comprise of Coronavirus Job Retention Scheme receipts of £Nil
+    (2022: £295,469).
+
+
+    3 Turnover and other revenue
+
+
+    4 Operating profit
+
+
+    Operating profit for the year is stated after charging/(crediting):
+
+
+    2023 (£) 2022 (£) Other revenue - - Grants received - 295,469
+
+
+    5 Auditor''s remuneration
+
+
+    6 Employees
+
+
+    2023 Number 2022 Number Management 18 18 Hotel, restaurant and leisure staff 187
+    158 Total 205 176
+
+
+    2023 (£) 2022 (£) Government grants - (296,409) Depreciation of owned tangible
+    fixed assets 131,351 89,063 Profit on disposal of tangible fixed assets (20,653)
+    (1,332,660) Operating lease charges 8,553 5,181
+
+
+    The average monthly number of persons (including directors) employed by the company
+    during the year was:'
+  - 'Balance Sheet Dec 31, 2019 (€ million)
+
+
+    Profit and loss statement Q4 YTD 2019 (€ million)
+
+
+    Revenue (115) Profit from sale-leaseback transactions (55) Rental expenses (829)
+    EBITDA 774 Depreciation expense (699) Operating Income 75 Net interest expenses
+    172 Taxes (27) Net Income 70
+
+
+    Cash flow statement Q4 YTD 2019 (€ million)
+
+
+    EFFECTS INCLUDING NXSTAGE
+
+
+    Net leverage ratio increased by 0.7.
+
+
+    Q4 YTD 2019 | EFFECTS ACCORDING TO IFRS 16
+
+
+    Cash provided by operating activities 620 Cash used in investing activities (61)
+    Cash used in financing activities (559) Total 0
+
+
+    © │ Conference Call │ Q4 2019 02/20/2020 Page 36
+
+
+    Assets 4,356 Right-of-use assets 4,361 Machinery and equipment 36 Other assets
+    (41) Liabilities 4,356 Lease liabilities 4,705 Other financial debt 92 Other liabilities
+    (232) Equity (209)'
+- source_sentence: consolidated cash flow operating activities 2021
+  sentences:
+  - 'CONSOLIDATED FINANCIAL STATEMENTS Bufab Annual and Sustainability Report 2021
+    | 53
+
+
+    Note 31 Dec 2021 31 Dec 2020 SEK million Operating activities Profit before financial
+    items 664 452 Depreciation/amortisation and impairment 193 183 Interest and other
+    finance income 1 3 Interest and other finance expenses –52 –60 Other non-cash
+    items 45 –8 Income tax paid –137 –89 Cash flow from operating activities before
+    changes in working capital 714 480 Cash flow from changes in working capital Increase
+    (–) / decrease (+) in inventories –651 96 Increase (–) / decrease (+) in operating
+    receivables –200 –111 Increase (+) / decrease (–) in operating liabilities 309
+    105 Cash flow from operating activities 172 570 Investing activities Acquisition
+    of intangible assets –31 –5 Acquisition of property, plant and equipment –3 –61
+    Company acquisitions including additional purchase considerations 33 –301 –23
+    Cash flow from investing activities –335 –89 Financing activities Dividend paid
+    –103 0 Call options 34 4 3 Repurchase of own shares 34 0 0 Redemption call options/sale
+    of own shares 15 10 Amortisation lease contracts –111 –109 Borrowings, non-current
+    36 461 284 Loan repayments, non-current 36 –230 –631 Change in current liabilities
+    36 122 –62 Cash flow from financing activities 158 –396 Cash flow for the year
+    36 –5 86 Cash and cash equivalents at beginning of year 292 216 Translation differences
+    6 –10 Cash and cash equivalents at year-end 293 292
+
+
+    Consolidated cash-flow statement'
+  - 'The above statement should be read in conjunction with the accompanying notes.
+    - 13 - PleaseSign Document PLSDOC02dd252c8d63bbf4cc3f8e86c0
+
+
+    Note 2021 $''000 2020 $''000 Cash flow from operating activities Cash receipts
+    in the course of operations 141,276 Cash payments in the course of operations
+    (134,477) Income tax paid - Interest received 12 Interest paid (5) 19(b) Net cash
+    received in operating activities 6,806 Cash flow from investment activities Payments
+    for purchases of property, plant and equipment (64) Principal received from Finance
+    Leased Assets 375 Interest received from Finance Leased Assets 122 Net cash used
+    in investing activities 433 Cash flow from financing activities Dividends paid
+    (792) (Repayment)/Proceeds from Bank Loans (120) Principal paid for Finance Leased
+    Liabilities (745) Interest paid for Finance Leased Liabilities (328) Net cash
+    used in financing activities (1,985) Net Increase in cash held 5,254 Cash and
+    cash equivalents at beginning of financial year 4,182 19(a) Cash and cash equivalents
+    at end of financial year 9,436
+
+
+    CONSOLIDATED STATEMENT OF CASH FLOWS FOR THE YEAR ENDED 30 JUNE 2021'
+  - 'The illustration reflects TDC Group''s Q1 2020 performance based on our segment
+    reporting. Following the legal separation, trading on an arm''s length basis between
+    Nuuday, TDC NET and the shared services centres in Headquarters has been implemented
+    and is reflected in the financial figures.
+
+
+    Business unit performance in Q1 2020
+
+
+    TDC Group tdc net nuuday Revenue (DKKm) 4,126  (-4.1%) 1,773 (-0.7%) 3,764 (-4.2%)
+    Gross profit (DKKm) 2,979 (-3.8%) 1,653 (-2.1%) 1,406 (-4.5%) EBITDA (DKKm) 1,664
+    (-2.0%) 1,125 (0.6%) 458 (-9.1%)
+
+
+    1 Both absolute figures and growth rates do not amount to 100% as headquarters
+    and eliminations are not included in the table.'
+- source_sentence: How many kilometers of National Highways were constructed by NHAI
+    in the 2023-24 period?
+  sentences:
+  - 'Year EPC BOT-Toll HAM TOT FY19 59% 41% FY20 82% 12% 6% FY21 47% 44% 9% FY22 40%
+    56% 1% 2% FY23 43% 51% 2% 3% FY24 56% 24% 20%
+
+
+    This offers private capital a major opportunity to invest in infrastructure growth.
+
+
+    Private Capex picking Momentum
+
+
+    Yearly Awards (in Kms)
+
+
+    Source: pib.gov.in, MoRTH, PTI and SIAM India, World Road Statistics 2023, CRISIL
+
+
+    NHAI plans to monetize INR 600 Bn of operational highways via the TOT Model.
+
+
+    These assets (which includes 95% of EPC/HAM road projects) were previously on
+    NHAI''s balance sheet.
+
+
+    Opportunities under PPP
+
+
+    Projects totaling 871 Kms, valued at Rs. 456 bn, will likely be available for
+    bidding on BOT basis, including opportunities from NHAI & other State Agencies.
+
+
+    Total completed National Highway stands at ~146,000 kms, of which ~46,179 kms
+    is 4 lane and above in configuration.
+
+
+    This shift to private investment frees up NHAI resources for new projects and
+    network expansion.
+
+
+    28'
+  - '2021年度 2022年度 増減 概況 半導体 売上高 1,294 1,469 174 ディスク媒体事業からの撤退影響があったものの、電動車（xEV）向け及び産業分野向けのパワー半導体の需要拡大及び為替影響により、売上高は前年同期を上回りました。また、営業損益も、パワー半導体の生産能力増強に係る費用の増加や素材価格及び動力費の高騰影響があったものの、高操業の維持による生産及び売上の増加により、前年同期を上回りました。
+    営業損益 192 225 33 発電プラント 売上高 443 557 113 再生可能エネルギーの大口案件及び案件差等により、売上高、営業損益ともに前年同期を上回りました。
+    営業損益 -11 2 14 食品流通 売上高 653 684 31 自販機 14％増収 中国の子会社における貸倒引当金計上による損益悪化影響があったものの、国内の需要拡大に加え、原価低減の推進等により、売上高、営業損益ともに前年同期を上回りました。店舗流通
+    3％減収 営業損益 16 29 13 前年同期の金銭機器の大口案件影響により、売上高、営業損益ともに前年同期を下回りました。
+
+
+    2021年度 2022年度 増減 産業 776 785 9 ディスク媒体 60 0 -60 電装 519 684 165
+
+
+    売上高内訳
+
+
+    +53 +29 8*為替影響※ 2021年度実績は、2022年度の事業組替の数値を反映しています。
+
+
+    （単位：億円）
+
+
+    第3四半期累計 セグメント別概況②（対前年）'
+  - 'FY length Constructed (kms) FY15 4410 FY16 6061 FY17 8231 FY18 9829 FY19 10956
+    FY20 10237 FY21 13327 FY22 10457 FY23 10301 8MFY24 5248
+
+
+    Highway construction growth 20%
+
+
+    1.46 Lakh Km+ 28.3 Km/Day
+
+
+    Growing Private Sector Involvement
+
+
+    6.37 Mn. Kms
+
+
+    INVESTOR PRESENTATION 26
+
+
+    INDUSTRY OVERVIEW (INDIA)
+
+
+    60 HAM Projects Rolled Out worth over $10 Bn
+
+
+    National Highways (NH) constructions
+
+
+    2nd Largest Road Network in the World
+
+
+    Rapid Growth in National Highways
+
+
+    2023-24
+
+
+    NHAI Constructed 6,644 km
+
+
+    Investment raised by NHAI InvIT - $102 Bn+ (from Fils & Dils upto Dec 2022) (Source)
+
+
+    Total length of National Highways (2022-23)'
+- source_sentence: deferred tax assets opening balance inventory loss 2022
+  sentences:
+  - 'e. Information on unused loss carryforwards
+
+
+    The movements of deferred tax assets and deferred tax liabilities were as follows:
+
+
+    For the year ended December 31, 2021
+
+
+    December 31 2022 Loss carryforwards Expiry in 2027 $ - Expiry in 2028 $ 46,056
+    Expiry in 2029 $ 72,486 Expiry in 2030 $ 97,191 Total $ 215,733
+
+
+    Opening Balance Recognized in Profit or Loss Closing Balance Temporary differences
+    Unrealized exchange gain and loss $ 3 $ (332) Unrealized inventory loss $ 1,113
+    $ 560 Others $ 402 $ (228) Total $ 1,518 $ -
+
+
+    Opening Balance Recognized in Profit or Loss Closing Balance Temporary differences
+    Unrealized exchange gain and loss $ 113 $ (110) Unrealized inventory loss $ 1,849
+    $ (736) Others $ (444) $ 846 Total $ 1,518 $ -
+
+
+    Unused Amount Expiry Year $ 46,056 2028 $ 72,486 2029 $ 97,191 2030 Total $ 215,733
+
+
+    d. Items for which no deferred tax assets have been recognized
+
+
+    The Company offset certain deferred tax assets and deferred tax liabilities which
+    met the offset criteria.
+
+
+    c. Deferred tax assets and liabilities
+
+
+    Loss carryforwards as of December 31, 2022 comprised:
+
+
+    For the year ended December 31, 2022'
+  - 'PILGRIM FOODSERVICE LIMITED
+
+    NOTES TO THE FINANCIAL STATEMENTS (CONTINUED)
+
+    FOR THE YEAR ENDED 30 APRIL 2025
+
+
+    |   |   | 2025 £ | 2024 £ |
+
+    |---|---|---|---|
+
+    | 17 | Stocks |   |   |
+
+    |   | Finished goods and goods for resale | 4,149,563 | 3,602,784 |
+
+
+    |   |   | 2025 £ | 2024 £ |
+
+    |---|---|---|---|
+
+    | 18 | Debtors |   |   |
+
+    |   | Amounts falling due within one year: |   |   |
+
+    |   | Trade debtors | 4,056,601 | 3,939,861 |
+
+    |   | Corporation tax recoverable | 386,649 | - |
+
+    |   | Other debtors | 51,029 | 285,195 |
+
+    |   | Prepayments and accrued income | 894,513 | 810,422 |
+
+    |   |   | 5,388,792 | 5,035,478 |
+
+
+    |   |   | Notes | 2025 £ | 2024 £ |
+
+    |---|---|---|---|---|
+
+    | 19 | Creditors: amounts falling due within one year |   |   |   |
+
+    |   | Bank loans and overdrafts | 21 | 750,004 | 1,572,186 |
+
+    |   | Obligations under finance leases | 22 | 929,382 | 221,527 |
+
+    |   | Trade creditors |   | 6,972,922 | 5,358,604 |
+
+    |   | Amounts due to group undertakings |   | 49,502 | - |
+
+    |   | Corporation tax |   | 324,698 | 342,382 |
+
+    |   | Other taxation and social security |   | 843,069 | 292,562 |
+
+    |   | Other creditors |   | 3,361,115 | 802,545 |
+
+    |   | Accruals |   |   | 2,269,019 |
+
+    |   |   |   | 13,230,692 | 10,858,915 |
+
+
+    |   |   | Notes | 2025 £ | 2024 £ |
+
+    |---|---|---|---|---|
+
+    | 20 | Creditors: amounts falling due after more than one year |   |   |   |
+
+    |   | Bank loans and overdrafts | 21 | 1,174,972 | 1,925,178 |
+
+    |   | Obligations under finance leases | 22 | 3,026,050 | 927,331 |
+
+    |   | Shareholder loans | 21 | 1,925,125 | 681,083 |
+
+    |   |   |   | 6,126,147 | 3,533,592 |
+
+
+    -26-'
+  - 'The movements of deferred tax assets and deferred tax liabilities were as follows:
+
+
+    For the year ended December 31, 2022
+
+
+    d. Deferred tax assets and liabilities
+
+
+    December 31 2022 2021 Current tax liabilities Income tax payable $ 473,781 $ 255,744
+
+
+    b. Income tax recognized in other comprehensive income
+
+
+    Opening Balance Recognized in Profit or Loss Recognized in Other Comprehensive
+    Income Closing Balance Deferred tax assets Temporary differences Unrealized loss
+    on write-down of inventories $ 250 $ 8 $ - $ 258 Unrealized employee compensation
+    241 (241) - - Exchanges difference on foreign operations 73,357 - (23,271) 50,086
+    Unrealized exchange losses 15,010 (15,010) - - Total $ 88,858 $ (15,243) $ (23,271)
+    $ 50,344 Deferred tax liabilities Temporary differences Unrealized exchange gain
+    $ - $ 2,525 $ - $ 2,525
+
+
+    For the Year Ended December 31 2022 2021 Deferred tax In respect of the current
+    year $ (23,271) $ (9,510) Translation of foreign operations
+
+
+    c. Current tax assets and liabilities'
+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 nvidia/llama-nemotron-embed-1b-v2
+  results:
+  - task:
+      type: information-retrieval
+      name: Information Retrieval
+    dataset:
+      name: financial corpus
+      type: financial_corpus
+    metrics:
+    - type: cosine_accuracy@1
+      value: 0.663
+      name: Cosine Accuracy@1
+    - type: cosine_accuracy@3
+      value: 0.787
+      name: Cosine Accuracy@3
+    - type: cosine_accuracy@5
+      value: 0.837
+      name: Cosine Accuracy@5
+    - type: cosine_accuracy@10
+      value: 0.897
+      name: Cosine Accuracy@10
+    - type: cosine_precision@1
+      value: 0.663
+      name: Cosine Precision@1
+    - type: cosine_precision@3
+      value: 0.2623333333333333
+      name: Cosine Precision@3
+    - type: cosine_precision@5
+      value: 0.1674
+      name: Cosine Precision@5
+    - type: cosine_precision@10
+      value: 0.08970000000000002
+      name: Cosine Precision@10
+    - type: cosine_recall@1
+      value: 0.663
+      name: Cosine Recall@1
+    - type: cosine_recall@3
+      value: 0.787
+      name: Cosine Recall@3
+    - type: cosine_recall@5
+      value: 0.837
+      name: Cosine Recall@5
+    - type: cosine_recall@10
+      value: 0.897
+      name: Cosine Recall@10
+    - type: cosine_ndcg@10
+      value: 0.7762155985486033
+      name: Cosine Ndcg@10
+    - type: cosine_mrr@10
+      value: 0.7380559523809528
+      name: Cosine Mrr@10
+    - type: cosine_map@100
+      value: 0.742572410600174
+      name: Cosine Map@100
+---
+
+# SentenceTransformer based on nvidia/llama-nemotron-embed-1b-v2
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [nvidia/llama-nemotron-embed-1b-v2](https://huggingface.co/nvidia/llama-nemotron-embed-1b-v2) on the financial-filings-sparse-retrieval-training dataset. It maps sentences & paragraphs to a 2048-dimensional dense vector space and can be used for retrieval.
+
+## Model Details
+
+### Model Description
+- **Model Type:** Sentence Transformer
+- **Base model:** [nvidia/llama-nemotron-embed-1b-v2](https://huggingface.co/nvidia/llama-nemotron-embed-1b-v2) <!-- at revision 113abe4acafa848e77ead9c0623205e511932348 -->
+- **Maximum Sequence Length:** 2048 tokens
+- **Output Dimensionality:** 2048 dimensions
+- **Similarity Function:** Cosine Similarity
+- **Supported Modality:** Text
+- **Training Dataset:**
+    - financial-filings-sparse-retrieval-training
+<!-- - **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({'transformer_task': 'feature-extraction', 'modality_config': {'text': {'method': 'forward', 'method_output_name': 'last_hidden_state'}}, 'module_output_name': 'token_embeddings', 'architecture': 'LlamaBidirectionalModel'})
+  (1): Pooling({'embedding_dimension': 2048, 'pooling_mode': 'mean', '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("abanfalvi/finance-llama-nemotron-embed-1b-v2")
+# Run inference
+queries = [
+    'deferred tax assets opening balance inventory loss 2022',
+]
+documents = [
+    'The movements of deferred tax assets and deferred tax liabilities were as follows:\n\nFor the year ended December 31, 2022\n\nd. Deferred tax assets and liabilities\n\nDecember 31 2022 2021 Current tax liabilities Income tax payable $ 473,781 $ 255,744\n\nb. Income tax recognized in other comprehensive income\n\nOpening Balance Recognized in Profit or Loss Recognized in Other Comprehensive Income Closing Balance Deferred tax assets Temporary differences Unrealized loss on write-down of inventories $ 250 $ 8 $ - $ 258 Unrealized employee compensation 241 (241) - - Exchanges difference on foreign operations 73,357 - (23,271) 50,086 Unrealized exchange losses 15,010 (15,010) - - Total $ 88,858 $ (15,243) $ (23,271) $ 50,344 Deferred tax liabilities Temporary differences Unrealized exchange gain $ - $ 2,525 $ - $ 2,525\n\nFor the Year Ended December 31 2022 2021 Deferred tax In respect of the current year $ (23,271) $ (9,510) Translation of foreign operations\n\nc. Current tax assets and liabilities',
+    'e. Information on unused loss carryforwards\n\nThe movements of deferred tax assets and deferred tax liabilities were as follows:\n\nFor the year ended December 31, 2021\n\nDecember 31 2022 Loss carryforwards Expiry in 2027 $ - Expiry in 2028 $ 46,056 Expiry in 2029 $ 72,486 Expiry in 2030 $ 97,191 Total $ 215,733\n\nOpening Balance Recognized in Profit or Loss Closing Balance Temporary differences Unrealized exchange gain and loss $ 3 $ (332) Unrealized inventory loss $ 1,113 $ 560 Others $ 402 $ (228) Total $ 1,518 $ -\n\nOpening Balance Recognized in Profit or Loss Closing Balance Temporary differences Unrealized exchange gain and loss $ 113 $ (110) Unrealized inventory loss $ 1,849 $ (736) Others $ (444) $ 846 Total $ 1,518 $ -\n\nUnused Amount Expiry Year $ 46,056 2028 $ 72,486 2029 $ 97,191 2030 Total $ 215,733\n\nd. Items for which no deferred tax assets have been recognized\n\nThe Company offset certain deferred tax assets and deferred tax liabilities which met the offset criteria.\n\nc. Deferred tax assets and liabilities\n\nLoss carryforwards as of December 31, 2022 comprised:\n\nFor the year ended December 31, 2022',
+    'PILGRIM FOODSERVICE LIMITED\nNOTES TO THE FINANCIAL STATEMENTS (CONTINUED)\nFOR THE YEAR ENDED 30 APRIL 2025\n\n|   |   | 2025 £ | 2024 £ |\n|---|---|---|---|\n| 17 | Stocks |   |   |\n|   | Finished goods and goods for resale | 4,149,563 | 3,602,784 |\n\n|   |   | 2025 £ | 2024 £ |\n|---|---|---|---|\n| 18 | Debtors |   |   |\n|   | Amounts falling due within one year: |   |   |\n|   | Trade debtors | 4,056,601 | 3,939,861 |\n|   | Corporation tax recoverable | 386,649 | - |\n|   | Other debtors | 51,029 | 285,195 |\n|   | Prepayments and accrued income | 894,513 | 810,422 |\n|   |   | 5,388,792 | 5,035,478 |\n\n|   |   | Notes | 2025 £ | 2024 £ |\n|---|---|---|---|---|\n| 19 | Creditors: amounts falling due within one year |   |   |   |\n|   | Bank loans and overdrafts | 21 | 750,004 | 1,572,186 |\n|   | Obligations under finance leases | 22 | 929,382 | 221,527 |\n|   | Trade creditors |   | 6,972,922 | 5,358,604 |\n|   | Amounts due to group undertakings |   | 49,502 | - |\n|   | Corporation tax |   | 324,698 | 342,382 |\n|   | Other taxation and social security |   | 843,069 | 292,562 |\n|   | Other creditors |   | 3,361,115 | 802,545 |\n|   | Accruals |   |   | 2,269,019 |\n|   |   |   | 13,230,692 | 10,858,915 |\n\n|   |   | Notes | 2025 £ | 2024 £ |\n|---|---|---|---|---|\n| 20 | Creditors: amounts falling due after more than one year |   |   |   |\n|   | Bank loans and overdrafts | 21 | 1,174,972 | 1,925,178 |\n|   | Obligations under finance leases | 22 | 3,026,050 | 927,331 |\n|   | Shareholder loans | 21 | 1,925,125 | 681,083 |\n|   |   |   | 6,126,147 | 3,533,592 |\n\n-26-',
+]
+query_embeddings = model.encode_query(queries)
+document_embeddings = model.encode_document(documents)
+print(query_embeddings.shape, document_embeddings.shape)
+# [1, 2048] [3, 2048]
+
+# Get the similarity scores for the embeddings
+similarities = model.similarity(query_embeddings, document_embeddings)
+print(similarities)
+# tensor([[0.5039, 0.4746, 0.2891]], dtype=torch.bfloat16)
+```
+<!--
+### 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: `financial_corpus`
+* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.sentence_transformer.evaluation.InformationRetrievalEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| cosine_accuracy@1   | 0.663      |
+| cosine_accuracy@3   | 0.787      |
+| cosine_accuracy@5   | 0.837      |
+| cosine_accuracy@10  | 0.897      |
+| cosine_precision@1  | 0.663      |
+| cosine_precision@3  | 0.2623     |
+| cosine_precision@5  | 0.1674     |
+| cosine_precision@10 | 0.0897     |
+| cosine_recall@1     | 0.663      |
+| cosine_recall@3     | 0.787      |
+| cosine_recall@5     | 0.837      |
+| cosine_recall@10    | 0.897      |
+| **cosine_ndcg@10**  | **0.7762** |
+| cosine_mrr@10       | 0.7381     |
+| cosine_map@100      | 0.7426     |
+
+<!--
+## 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
+
+#### financial-filings-sparse-retrieval-training
+
+* Dataset: financial-filings-sparse-retrieval-training
+* Size: 15,509 training samples
+* Columns: <code>anchor</code>, <code>positive</code>, and <code>negative</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | anchor                                                                            | positive                                                                              | negative                                                                              |
+  |:--------|:----------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------|
+  | type    | string                                                                            | string                                                                                | string                                                                                |
+  | details | <ul><li>min: 5 tokens</li><li>mean: 16.07 tokens</li><li>max: 61 tokens</li></ul> | <ul><li>min: 52 tokens</li><li>mean: 341.78 tokens</li><li>max: 1566 tokens</li></ul> | <ul><li>min: 56 tokens</li><li>mean: 373.04 tokens</li><li>max: 1713 tokens</li></ul> |
+* Samples:
+  | anchor                                                                                                                          | positive                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                 | negative                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                 |
+  |:--------------------------------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+  | <code>What is the unit of measurement used for Oil EUR on the vertical axis of the Relative Peer Well Performance chart?</code> | <code>Relative Peer Well Performance<br><br>Source: RSEG (2019)<br><br>Note: Bubbles are sized by well count and colored by oil %<br><br>Oil EUR (Mbbl/1,000')<br><br>\| \| 0 \| 5 \| 10 \| 15 \| 20 \| 25 \| 30 \| 35 \| 40 \| 45 \| 50 \| \|---\|---\|---\|---\|---\|---\|---\|---\|---\|---\|---\|---\|---\| \| Average Horizontal Interwell Spacing (ft) \| 0 \| 100 \| 200 \| 300 \| 400 \| 500 \| 600 \| 700 \| 80\|<br><br>Wellhead Liquids (%)<br><br><40 \| 40-55 \| >55</code>                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                 | <code>Exhibit B
+
+  Total Stockholder Return for the Company and each of the Peer Companies shall be calculated in accordance with the following formula, with the result expressed as a percentage:
+
+  The Company’s Relative Total Stockholder Return measured against the Peer Group shall be determined by first ranking the Company and each of the Peer Companies by their respective Total Stockholder Returns (highest to lowest) over the Performance Period. The Company’s Relative Total Stockholder Return shall be the Company’s percentile ranking determined from such numerical ranking, which percentile ranking shall be calculated as 100 multiplied by a fraction, the numerator of which is (x) the number of Peer Companies that are ranked lower than the Company by their respective Total Stockholder Returns and the denominator of which is (y) the number of Peer Companies in the Peer Group at the time of the determination minus one (1).
+
+  The number of Conditional PSUs with which you are credited, if any, at t...</code> |
+  | <code>Q3 FY22 EBITDA decline reasons inflation</code>                                                                           | <code>Net sales is growing at healthy CAGR of 8.7% over 2 years, despite pandemic induced setbacks on our summer season brand sales<br><br>Metric YoY Gr 2 Year CAGR Net Sales 2.3 % 8.7% EBIDTA (34.8) % (7.0) % PBT * 1205.7 % 104.0% PAT * 1239.1 % 134.4%<br><br>Quarterly Performance - Q3 FY 22<br><br>EBIDTA de-grew mainly due to impact on gross margins on account of product mix and inflationary price increases in key raw materials & packing materials<br><br>PBT after exceptional items is growing mainly due to reduction in finance cost due to repayment of intercompany loan and nil exceptional item in the current quarter compared to Rs.342 million in previous year comparable period<br><br>The previous year comparable period includes exceptional items of Rs.342 million.</code>                                                                                                                                                                                                                                          | <code>PVC Pipes and Fittings volume registered a y-o-y growth of 4.2% to 1,58,266 MT.
+
+  Business continues to be net debt free
+
+  PAT grew by 30% from Rs 431 Cr to 560 Cr
+
+  EBITDA dropped to Rs 242 Cr (vs. Rs. 346 Cr)
+
+  Segment Revenue – Q3 FY22
+
+  All Numbers reported in the presentation are on standalone basis
+
+  Segment Volume – Q3 FY22
+
+  Total revenue registered a y-o-y growth of 38% to Rs. 3,054 Cr
+
+  Segment MT PVC P&F 46,994 PVC Resin 43,464
+
+  PVC Resin volume registered a y-o-y decline of 36% to 43,464 MT
+
+  PVC Pipes & Fittings volume registered a y-o-y decline of 15.3% to 46,994 MT.
+
+  PVC Resin volume registered a y-o-y decline of 9.4% to 1,45,742 MT
+
+  Total revenue registered a y-o-y decline of 5.7% to Rs. 1,005 Cr from Rs.1066 Cr
+
+  Strong liquidity and healthy balance sheet
+
+  Profitability slightly impacted by higher input prices
+
+  PAT decreased by 31% from Rs 256 Cr to Rs 178 Cr
+
+  Q3 FY22 9M FY22
+
+  Segment Rs Cr PVC Resin 832 P&F 636
+
+  Strong business performance despite lower demand
+
+  Strong YTD perfo...</code> |
+  | <code>What was the total value of trade creditors in 2022?</code>                                                               | <code>2022 (£) 2021 (£) Trade debtors 1,849,235 1,877,661 Other debtors 105,874 75,543 Prepayments and accrued income 36,698 61,917 Total 1,991,807 2,015,121 Deferred tax asset (note 10) 341,000 408,000 Total Debtors 2,332,807 2,423,121
+
+  The following are the major deferred tax liabilities and assets recognised by the company and movements thereon:
+
+  The deferred tax falling due after more than one year relates to losses carried forward.
+
+  Amounts falling due within one year:
+
+  10-
+
+  Movements in the year:
+
+  Assets 2022 (£) Assets 2021 (£) Accelerated capital allowances (5,000) (6,000) Tax losses 346,000 414,000 Total Balances 341,000 408,000
+
+  Balances:
+
+  2022 (£) 2021 (£) Trade creditors 160,773 61,453 Amounts owed to group undertakings 732,753 1,370,540 Taxation and social security 234,304 239,278 Other creditors 284,740 460,640 Accruals and deferred income 903,386 1,042,016 Total Creditors 2,315,956 3,173,927
+
+  9 Creditors: amounts falling due within one year
+
+  8 Debtors
+
+  10 Deferred taxation
+
+  20...</code> | <code>15 Other non-current liabilities
+
+  2024 (£m) 2023 (£m) Trade and other debtors 22 22 Prepayments and accrued income 12 12 Total 34 34
+
+  The decrease in provisions for impairment of trade debtors and accrued income of £18m (2022/23: £18m decrease) is equal to the credit to the consolidated income statement of £14m (2022/23: £11m credit), and write-offs of trade debtors of £4m (2022/23: £7m).
+
+  13 Debtors
+
+  2024 (£m) 2023 (£m) Lease liabilities 121 120 Deferred income¹ - 25 Total 121 145
+
+  The Directors consider that the carrying amount of trade and other debtors is approximate to their fair value. Further details about the Group's credit risk management practices are disclosed in Note 16.
+
+  14 Creditors
+
+  The credit to the consolidated income statement for the year in relation to the release of impairment of trade debtors and accrued income was £14m (2022/23: £11m credit), as disclosed in Note 3.
+
+  Trade and other debtors are shown after deducting a provision for impairment against tenant debto...</code> |
+* Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
+  ```json
+  {
+      "scale": 20.0,
+      "similarity_fct": "cos_sim",
+      "gather_across_devices": false,
+      "directions": [
+          "query_to_doc"
+      ],
+      "partition_mode": "joint",
+      "hardness_mode": null,
+      "hardness_strength": 0.0
+  }
+  ```
+
+### Evaluation Dataset
+
+#### financial-filings-sparse-retrieval-training
+
+* Dataset: financial-filings-sparse-retrieval-training
+* Size: 2,738 evaluation samples
+* Columns: <code>anchor</code>, <code>positive</code>, and <code>negative</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | anchor                                                                            | positive                                                                              | negative                                                                              |
+  |:--------|:----------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------|
+  | type    | string                                                                            | string                                                                                | string                                                                                |
+  | details | <ul><li>min: 4 tokens</li><li>mean: 16.07 tokens</li><li>max: 52 tokens</li></ul> | <ul><li>min: 56 tokens</li><li>mean: 325.18 tokens</li><li>max: 1272 tokens</li></ul> | <ul><li>min: 64 tokens</li><li>mean: 355.84 tokens</li><li>max: 1099 tokens</li></ul> |
+* Samples:
+  | anchor                                                                                                                     | positive                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                 | negative                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                            |
+  |:---------------------------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+  | <code>What was the regional distribution of holdings within the United States and Canada during the spring of 2020?</code> | <code>OWNERSHIP STAKE<br><br>March 2020 March 2019 Fully operational 97% 97% Construction 3% 3%<br><br>70 HICL ANNUAL REPORT 2020<br><br>March 2020 March 2019 UK 76% 77% EU 17% 15% North America 7% 8%<br><br>March 2020 March 2019 PPP projects 72% 71% Demand-based assets 20% 21% Regulated assets 8% 8%<br><br>MARKET SEGMENT<br><br>GEOGRAPHIC LOCATION<br><br>INVESTMENT STATUS<br><br>3.6 Portfolio Analysis<br><br>March 2020 March 2019 100% ownership 26% 25% 50%-100% ownership 34% 32% Less than 50% ownership 40% 43%<br><br>SECTOR<br><br>as at 31 March 2020<br><br>March 2020 March 2019 Accommodation 11% 11% Education 14% 15% Electricity, Gas & Water 8% 8% Health 30% 28% Fire, Law & Order 7% 7% Transport 30% 31%</code>                                                                                                                                                                                                                                                                                                        | <code>PROPERTY, PLANT & EQUIPMENT
+
+  (a) At cost, except Factory land which is at cost, less amounts written off.
+
+  Particulars Land & Building Factory Building Office Equipment's Furniture & Fixtures Plant & Machinery Vehicles Computers Electrical fittings Total Tangible Assets Intangible Assets Software Total Intangible Assets GROSS BLOCK As on 1st April 2019 17.22 443.21 46.92 37.11 2,339.36 8.32 25.50 1.80 2,919.44 4.67 4.67 Additions - 3.74 0.32 45.17 - 1.53 0.40 51.16 3.76 3.76 Disposals - - - 2.64 - - - 2.64 - - At 31 March 2020 17.22 443.21 50.67 37.43 2,381.89 8.32 27.03 2.20 2,967.96 8.43 8.43 As on 1st April 2020 17.22 443.21 50.67 37.43 2,381.89 8.32 27.03 2.20 2,967.96 8.43 8.43 Additions 24.52 - 49.09 42.36 2.08 6.27 124.33 - - Disposals - - - - - - - - - - - At 31 March 2021 41.74 443.21 100.67 80.59 2,430.98 50.68 29.11 8.47 3,092.29 8.43 8.43 DEPRECIATION As on 1st April 2019 - 320.72 41.98 27.39 2,153.01 5.39 19.32 0.12 2,567.94 4.67 4.67 Charge for the year 17.21 2.98 2.52 68...</code>            |
+  | <code>What is the interest rate charged on the loan to Karbon Carlton Staindrop LLP?</code>                                | <code>Unrelieved tax losses of £68,994 (2023: £68,994) remain available to offset against future taxable profits.
+
+  12
+
+  2024 (£) 2023 (£) Other debtors 1,821 875 Taxation 42,871 - Work in progress 8,928 - Amounts owed by Karbon Carlton Staindrop LLP 207,665 875 261,285
+
+  On the loan to Karbon Carlton Staindrop LLP, interest is charged at 7% per annum.
+
+  7 TAXATION (CONTINUED)
+
+  The tax assessed is lower than the standard rate of corporation tax in the UK (19%). The differences are explained below.
+
+  8 DEBTORS: amounts due within one year
+
+  9 DEBTORS: amounts due after one year
+
+  Current tax reconciliation
+
+  2024 (£) 2023 (£) Profit on ordinary activities before tax 5,682 374,965 Tax on profit on ordinary activities at the standard rate of corporation tax of 25% (2023: 19%) 1,421 71,243 Effects of: Expenses not deductible for tax purposes 3,113 6,157 Group relief claimed (4,534) (77,400) Current tax charge for period
+
+  2024 (£) 2023 (£) Amounts owed by Karbon Carlton Staindrop LLP - loan capital 1,776...</code> | <code>RWK GOODMAN LLP
+  NOTES TO THE FINANCIAL STATEMENTS (CONTINUED)
+  FOR THE YEAR ENDED 31 MARCH 2025
+
+  **18 Borrowings**
+  Group and LLP
+
+  || 2025| 2024|
+  |-------|-----------|-----------|
+  | Bank loan | 7,341,667 | 6,441,667 |
+  | Bank overdrafts | 5,359,258 | 4,995,132 |
+  || 12,700,925| 11,436,799|
+  | Payable within one year | 12,459,258| 11,095,132|
+  | Payable within two to five years | 241,667   | 341,667   |
+
+  The bank loan and overdrafts are secured by a fixed charge over book and other debts and a floating charge over all assets.
+  A revolving loan facility of £8,000,000 was agreed on 7 January 2025, replacing the existing RCF agreement dated 25 January 2022. The loan is repayable in full at the end of the term on 7 January 2030. Interest is charged quarterly at a rate of 2% over base rate.
+  A bank loan of £500,000 was agreed with HSBC UK Bank pic in August 2023. The loan is repayable over 60 months by monthly instalments of £9,903. Interest is charged at a rate of 2% over base rate.
+
+  **19 Provision...</code>            |
+  | <code>Newmont Corporation 2022 restricted cash reconciliation</code>                                                       | <code>```markdown
+  NEWMONT CORPORATION
+  CONSOLIDATED STATEMENTS OF CASH FLOWS
+
+  |  |  |  Year Ended December 31, |  |
+  |---|---|---|---|
+  |  | 2022 | 2021 | 2020 |
+  |  |  | (in millions) |  |
+
+  |  |  |  |  |
+  |---|---|---|---|
+  | Reconciliation of cash, cash equivalents and restricted cash: |  |  |  |
+  | Cash and cash equivalents | $ 2,877 | $ 4,992 | $ 5,540 |
+  | Restricted cash included in Other current assets | 1 | 2 | 2 |
+  | Restricted cash included in Other non-current assets | 66 | 99 | 106 |
+  | Total cash, cash equivalents and restricted cash | $ 2,944 | $ 5,093 | $ 5,648 |
+
+  |  |  |  |  |
+  |---|---|---|---|
+  | Supplemental cash flow information: |  |  |  |
+  | Income and mining taxes paid, net of refunds | $ 1,122 | $ 1,534 | $ 400 |
+  | Interest paid, net of amounts capitalized | $ 172 | $ 229 | $ 261 |
+
+  (1) Acquisitions, net for the year ended December 31, 2021 is primarily related to the asset acquisition of the remaining 85.1% of GT Gold. Refer to
+  Note 1 for additional information.
+  The accompanying ...</code> | <code>Component Percentage Personal Bonus 6% Base Salary 14% Company Bonus 15% Restricted Stock Units 20% Performance Stock Units 45%<br><br>Component Objectives/Alignment Stock Price Performance • Value varies with NEM performance • Retention component Relative Stock Performance Long-term incentive to outperform gold competitors: • Absolute share price performance • Relative TSR performance Operating Performance Growth Pipeline/ Sustainability • Safety, Free Cash Flow, CSC, ROCE • Reserves and Resources • Sustainability and External Relations Leadership Measures • Individual objectives (with defined targets) • Leadership Pipeline results Base Salary • Adjusted for performance, scope • Market rate<br><br>Objectives/Alignment<br><br>Incentive vehicles balance key performance elements<br><br>Pay mix (CEO % shown)<br><br>Executive Compensation Structure<br><br>BANK OF AMERICA 2020 GLOBAL METALS, MINING & STEEL CONFERENCE NEWMONT CORPORATION<br><br>Plans support value chain to operating and market performance</code> |
+* Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
+  ```json
+  {
+      "scale": 20.0,
+      "similarity_fct": "cos_sim",
+      "gather_across_devices": false,
+      "directions": [
+          "query_to_doc"
+      ],
+      "partition_mode": "joint",
+      "hardness_mode": null,
+      "hardness_strength": 0.0
+  }
+  ```
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `per_device_train_batch_size`: 2
+- `max_steps`: 100
+- `learning_rate`: 3e-05
+- `lr_scheduler_type`: constant_with_warmup
+- `warmup_steps`: 0.03
+- `gradient_accumulation_steps`: 8
+- `fp16`: True
+- `gradient_checkpointing`: True
+- `load_best_model_at_end`: True
+
+#### All Hyperparameters
+<details><summary>Click to expand</summary>
+
+- `per_device_train_batch_size`: 2
+- `num_train_epochs`: 3.0
+- `max_steps`: 100
+- `learning_rate`: 3e-05
+- `lr_scheduler_type`: constant_with_warmup
+- `lr_scheduler_kwargs`: None
+- `warmup_steps`: 0.03
+- `optim`: adamw_torch_fused
+- `optim_args`: None
+- `weight_decay`: 0.0
+- `adam_beta1`: 0.9
+- `adam_beta2`: 0.999
+- `adam_epsilon`: 1e-08
+- `optim_target_modules`: None
+- `gradient_accumulation_steps`: 8
+- `average_tokens_across_devices`: True
+- `max_grad_norm`: 1.0
+- `label_smoothing_factor`: 0.0
+- `bf16`: False
+- `fp16`: True
+- `bf16_full_eval`: False
+- `fp16_full_eval`: False
+- `tf32`: None
+- `gradient_checkpointing`: True
+- `gradient_checkpointing_kwargs`: None
+- `torch_compile`: False
+- `torch_compile_backend`: None
+- `torch_compile_mode`: None
+- `use_liger_kernel`: False
+- `liger_kernel_config`: None
+- `use_cache`: False
+- `neftune_noise_alpha`: None
+- `torch_empty_cache_steps`: None
+- `auto_find_batch_size`: False
+- `log_on_each_node`: True
+- `logging_nan_inf_filter`: True
+- `include_num_input_tokens_seen`: no
+- `log_level`: passive
+- `log_level_replica`: warning
+- `disable_tqdm`: False
+- `project`: huggingface
+- `trackio_space_id`: trackio
+- `per_device_eval_batch_size`: 8
+- `prediction_loss_only`: True
+- `eval_on_start`: False
+- `eval_do_concat_batches`: True
+- `eval_use_gather_object`: False
+- `eval_accumulation_steps`: None
+- `include_for_metrics`: []
+- `batch_eval_metrics`: False
+- `save_only_model`: False
+- `save_on_each_node`: False
+- `enable_jit_checkpoint`: False
+- `push_to_hub`: False
+- `hub_private_repo`: None
+- `hub_model_id`: None
+- `hub_strategy`: every_save
+- `hub_always_push`: False
+- `hub_revision`: None
+- `load_best_model_at_end`: True
+- `ignore_data_skip`: False
+- `restore_callback_states_from_checkpoint`: False
+- `full_determinism`: False
+- `seed`: 42
+- `data_seed`: None
+- `use_cpu`: False
+- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
+- `parallelism_config`: None
+- `dataloader_drop_last`: False
+- `dataloader_num_workers`: 0
+- `dataloader_pin_memory`: True
+- `dataloader_persistent_workers`: False
+- `dataloader_prefetch_factor`: None
+- `remove_unused_columns`: True
+- `label_names`: None
+- `train_sampling_strategy`: random
+- `length_column_name`: length
+- `ddp_find_unused_parameters`: None
+- `ddp_bucket_cap_mb`: None
+- `ddp_broadcast_buffers`: False
+- `ddp_backend`: None
+- `ddp_timeout`: 1800
+- `fsdp`: []
+- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
+- `deepspeed`: None
+- `debug`: []
+- `skip_memory_metrics`: True
+- `do_predict`: False
+- `resume_from_checkpoint`: None
+- `warmup_ratio`: None
+- `local_rank`: -1
+- `prompts`: None
+- `batch_sampler`: batch_sampler
+- `multi_dataset_batch_sampler`: proportional
+- `router_mapping`: {}
+- `learning_rate_mapping`: {}
+
+</details>
+
+### Training Logs
+<details><summary>Click to expand</summary>
+
+| Epoch      | Step    | Training Loss | Validation Loss | financial_corpus_cosine_ndcg@10 |
+|:----------:|:-------:|:-------------:|:---------------:|:-------------------------------:|
+| 0.0021     | 1       | 0.8457        | -               | -                               |
+| 0.0041     | 2       | 0.7959        | -               | -                               |
+| 0.0062     | 3       | 0.4863        | -               | -                               |
+| 0.0083     | 4       | 0.6768        | -               | -                               |
+| 0.0103     | 5       | 0.5869        | -               | -                               |
+| 0.0124     | 6       | 0.5967        | -               | -                               |
+| 0.0144     | 7       | 0.7900        | -               | -                               |
+| 0.0165     | 8       | 0.7373        | -               | -                               |
+| 0.0186     | 9       | 0.4951        | -               | -                               |
+| 0.0206     | 10      | 0.5439        | -               | -                               |
+| 0.0227     | 11      | 0.4619        | -               | -                               |
+| 0.0248     | 12      | 0.6357        | -               | -                               |
+| 0.0268     | 13      | 0.5322        | -               | -                               |
+| 0.0289     | 14      | 0.4619        | -               | -                               |
+| 0.0309     | 15      | 0.6592        | -               | -                               |
+| 0.0330     | 16      | 0.7598        | -               | -                               |
+| 0.0351     | 17      | 0.4766        | -               | -                               |
+| 0.0371     | 18      | 0.7471        | -               | -                               |
+| 0.0392     | 19      | 0.7686        | -               | -                               |
+| 0.0413     | 20      | 0.4521        | -               | -                               |
+| 0.0433     | 21      | 0.5898        | -               | -                               |
+| 0.0454     | 22      | 0.5352        | -               | -                               |
+| 0.0474     | 23      | 0.7715        | -               | -                               |
+| 0.0495     | 24      | 0.5576        | -               | -                               |
+| 0.0516     | 25      | 0.6650        | 0.7444          | -                               |
+| 0.0536     | 26      | 0.2832        | -               | -                               |
+| 0.0557     | 27      | 0.5557        | -               | -                               |
+| 0.0578     | 28      | 0.6738        | -               | -                               |
+| 0.0598     | 29      | 0.5635        | -               | -                               |
+| 0.0619     | 30      | 0.5264        | -               | -                               |
+| 0.0640     | 31      | 0.5576        | -               | -                               |
+| 0.0660     | 32      | 0.7480        | -               | -                               |
+| 0.0681     | 33      | 0.3516        | -               | -                               |
+| 0.0701     | 34      | 0.4668        | -               | -                               |
+| 0.0722     | 35      | 0.3682        | -               | -                               |
+| 0.0743     | 36      | 0.4756        | -               | -                               |
+| 0.0763     | 37      | 0.4404        | -               | -                               |
+| 0.0784     | 38      | 0.4287        | -               | -                               |
+| 0.0805     | 39      | 0.4297        | -               | -                               |
+| 0.0825     | 40      | 0.5137        | -               | -                               |
+| 0.0846     | 41      | 0.5010        | -               | -                               |
+| 0.0866     | 42      | 0.3525        | -               | -                               |
+| 0.0887     | 43      | 0.4746        | -               | -                               |
+| 0.0908     | 44      | 0.4766        | -               | -                               |
+| 0.0928     | 45      | 0.4453        | -               | -                               |
+| 0.0949     | 46      | 0.5273        | -               | -                               |
+| 0.0970     | 47      | 0.5205        | -               | -                               |
+| 0.0990     | 48      | 0.4502        | -               | -                               |
+| 0.1011     | 49      | 0.6289        | -               | -                               |
+| 0.1031     | 50      | 0.6191        | 0.6595          | -                               |
+| 0.1052     | 51      | 0.4775        | -               | -                               |
+| 0.1073     | 52      | 0.4365        | -               | -                               |
+| 0.1093     | 53      | 0.4365        | -               | -                               |
+| 0.1114     | 54      | 0.5840        | -               | -                               |
+| 0.1135     | 55      | 0.3516        | -               | -                               |
+| 0.1155     | 56      | 0.3691        | -               | -                               |
+| 0.1176     | 57      | 0.4629        | -               | -                               |
+| 0.1196     | 58      | 0.6191        | -               | -                               |
+| 0.1217     | 59      | 0.5908        | -               | -                               |
+| 0.1238     | 60      | 0.3848        | -               | -                               |
+| 0.1258     | 61      | 0.3730        | -               | -                               |
+| 0.1279     | 62      | 0.5732        | -               | -                               |
+| 0.1300     | 63      | 0.5830        | -               | -                               |
+| 0.1320     | 64      | 0.4727        | -               | -                               |
+| 0.1341     | 65      | 0.3613        | -               | -                               |
+| 0.1362     | 66      | 0.4678        | -               | -                               |
+| 0.1382     | 67      | 0.5986        | -               | -                               |
+| 0.1403     | 68      | 0.2617        | -               | -                               |
+| 0.1423     | 69      | 0.3809        | -               | -                               |
+| 0.1444     | 70      | 0.4395        | -               | -                               |
+| 0.1465     | 71      | 0.3418        | -               | -                               |
+| 0.1485     | 72      | 0.3809        | -               | -                               |
+| 0.1506     | 73      | 0.3721        | -               | -                               |
+| 0.1527     | 74      | 0.3877        | -               | -                               |
+| 0.1547     | 75      | 0.3438        | 0.6091          | -                               |
+| 0.1568     | 76      | 0.4131        | -               | -                               |
+| 0.1588     | 77      | 0.6221        | -               | -                               |
+| 0.1609     | 78      | 0.3652        | -               | -                               |
+| 0.1630     | 79      | 0.3164        | -               | -                               |
+| 0.1650     | 80      | 0.3135        | -               | -                               |
+| 0.1671     | 81      | 0.2764        | -               | -                               |
+| 0.1692     | 82      | 0.7373        | -               | -                               |
+| 0.1712     | 83      | 0.3223        | -               | -                               |
+| 0.1733     | 84      | 0.4902        | -               | -                               |
+| 0.1753     | 85      | 0.4219        | -               | -                               |
+| 0.1774     | 86      | 0.3428        | -               | -                               |
+| 0.1795     | 87      | 0.3291        | -               | -                               |
+| 0.1815     | 88      | 0.3135        | -               | -                               |
+| 0.1836     | 89      | 0.3945        | -               | -                               |
+| 0.1857     | 90      | 0.2939        | -               | -                               |
+| 0.1877     | 91      | 0.3135        | -               | -                               |
+| 0.1898     | 92      | 0.3682        | -               | -                               |
+| 0.1919     | 93      | 0.5322        | -               | -                               |
+| 0.1939     | 94      | 0.3594        | -               | -                               |
+| 0.1960     | 95      | 0.2666        | -               | -                               |
+| 0.1980     | 96      | 0.3730        | -               | -                               |
+| 0.2001     | 97      | 0.4292        | -               | -                               |
+| 0.2022     | 98      | 0.4131        | -               | -                               |
+| 0.2042     | 99      | 0.4580        | -               | -                               |
+| **0.2063** | **100** | **0.3711**    | **0.5381**      | **-**                           |
+| -1         | -1      | -             | -               | 0.7762                          |
+
+* The bold row denotes the saved checkpoint.
+</details>
+
+### Training Time
+- **Training**: 4.6 hours
+
+### Framework Versions
+- Python: 3.12.13
+- Sentence Transformers: 5.4.1
+- Transformers: 5.5.0
+- PyTorch: 2.10.0+cu128
+- Accelerate: 1.13.0
+- Datasets: 4.3.0
+- Tokenizers: 0.22.2
+
+## Citation
+
+### BibTeX
+
+#### Sentence Transformers
+```bibtex
+@inproceedings{reimers-2019-sentence-bert,
+    title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
+    author = "Reimers, Nils and Gurevych, Iryna",
+    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
+    month = "11",
+    year = "2019",
+    publisher = "Association for Computational Linguistics",
+    url = "https://arxiv.org/abs/1908.10084",
+}
+```
+
+#### MultipleNegativesRankingLoss
+```bibtex
+@misc{oord2019representationlearningcontrastivepredictive,
+      title={Representation Learning with Contrastive Predictive Coding},
+      author={Aaron van den Oord and Yazhe Li and Oriol Vinyals},
+      year={2019},
+      eprint={1807.03748},
+      archivePrefix={arXiv},
+      primaryClass={cs.LG},
+      url={https://arxiv.org/abs/1807.03748},
+}
+```
+
+<!--
+## Glossary
+
+*Clearly define terms in order to be accessible across audiences.*
+-->
+
+<!--
+## Model Card Authors
+
+*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
+-->
+
+<!--
+## Model Card Contact
+
+*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
+-->

config.json

@@ -0,0 +1,43 @@
+{
+  "architectures": [
+    "LlamaBidirectionalModel"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoConfig": "llama_bidirectional_model.LlamaBidirectionalConfig",
+    "AutoModel": "llama_bidirectional_model.LlamaBidirectionalModel"
+  },
+  "bos_token_id": 128000,
+  "dtype": "bfloat16",
+  "eos_token_id": 128001,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama_bidirec",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 16,
+  "num_key_value_heads": 8,
+  "pad_token_id": null,
+  "pooling": "avg",
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_parameters": {
+    "factor": 32.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_theta": 500000.0,
+    "rope_type": "llama3"
+  },
+  "temperature": 1.0,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.5.0",
+  "use_bidirectional_attention": true,
+  "use_cache": true,
+  "vocab_size": 128256
+}

config_sentence_transformers.json

@@ -0,0 +1,14 @@
+{
+  "__version__": {
+    "pytorch": "2.10.0+cu128",
+    "sentence_transformers": "5.4.1",
+    "transformers": "5.5.0"
+  },
+  "default_prompt_name": null,
+  "model_type": "SentenceTransformer",
+  "prompts": {
+    "document": "passage: ",
+    "query": "query: "
+  },
+  "similarity_fn_name": "cosine"
+}

llama_bidirectional_model.py

@@ -0,0 +1,226 @@
+# SPDX-FileCopyrightText: Copyright (c) 2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
+# SPDX-License-Identifier: Apache-2.0.
+"""
+Bidirectional Llama model for embedding tasks.
+
+This module provides a modified LlamaModel that uses bidirectional (non-causal)
+attention, suitable for generating embeddings where each token should attend
+to all other tokens in the sequence.
+
+Supports transformers version 4.44 and above with a unified forward() implementation.
+
+Version compatibility notes:
+    - transformers 4.47: Setting _attn_implementation in __init__ had no effect due to
+      attention initialization order
+    - transformers 4.48+: Attention refactor (transformers#35235) activated the
+      _attn_implementation setting, which defaulted to "eager" instead of "sdpa"
+    - transformers < 4.53: LlamaModel has _update_causal_mask method that can be overridden
+    - transformers 4.53+: _update_causal_mask removed; masking moved to masking_utils module,
+      necessitating a full forward() override for custom attention masks
+    - transformers < 4.54: Decoder layer returns tuple, uses past_key_value (singular)
+    - transformers 4.54-4.55: Decoder layer returns tensor, uses past_key_value (singular)
+    - transformers 4.56+: Decoder layer returns tensor, uses past_key_values (plural),
+      DynamicCache accepts config parameter
+    - transformers 5.0+: Has native create_bidirectional_mask in masking_utils
+"""
+
+import inspect
+
+import torch
+from transformers.cache_utils import Cache, DynamicCache
+from transformers.modeling_outputs import BaseModelOutputWithPast
+from transformers.models.llama.configuration_llama import LlamaConfig
+from transformers.models.llama.modeling_llama import LlamaDecoderLayer, LlamaModel
+from transformers.utils import logging
+
+logger = logging.get_logger(__name__)
+
+# Check if native create_bidirectional_mask exists (transformers >= 5.0)
+try:
+    from transformers.masking_utils import create_bidirectional_mask
+
+    _HAS_NATIVE_BIDIRECTIONAL_MASK = True
+except ImportError:
+    from transformers.modeling_attn_mask_utils import _prepare_4d_attention_mask
+
+    _HAS_NATIVE_BIDIRECTIONAL_MASK = False
+
+# Detect API differences via introspection
+_decoder_forward_params = inspect.signature(LlamaDecoderLayer.forward).parameters
+_dynamic_cache_init_params = inspect.signature(DynamicCache.__init__).parameters
+
+# past_key_value (singular) in < 4.56, past_key_values (plural) in >= 4.56
+_USE_PLURAL_CACHE_PARAM = "past_key_values" in _decoder_forward_params
+# DynamicCache accepts config parameter in >= 4.56
+_DYNAMIC_CACHE_ACCEPTS_CONFIG = "config" in _dynamic_cache_init_params
+
+
+class LlamaBidirectionalConfig(LlamaConfig):
+    """Configuration for LlamaBidirectionalModel with pooling and temperature settings."""
+
+    model_type = "llama_bidirec"
+
+    def __init__(
+        self, pooling: str = "avg", temperature: float = 1.0, **kwargs
+    ) -> None:
+        """
+        Initialize bidirectional Llama configuration.
+
+        Args:
+            pooling: Pooling strategy for embeddings ("avg", "cls", "last", etc.)
+            temperature: Temperature scaling for embeddings
+            **kwargs: Additional arguments passed to LlamaConfig
+        """
+        self.pooling = pooling
+        self.temperature = temperature
+        super().__init__(**kwargs)
+
+
+class LlamaBidirectionalModel(LlamaModel):
+    """
+    LlamaModel modified to use bidirectional (non-causal) attention.
+
+    In standard Llama, each token can only attend to previous tokens (causal attention).
+    This model removes that restriction, allowing each token to attend to all tokens
+    in the sequence, which is useful for embedding tasks.
+
+    The key modifications are:
+        1. Setting is_causal=False on all attention layers
+        2. Using a bidirectional attention mask instead of causal mask
+    """
+
+    config_class = LlamaBidirectionalConfig
+
+    def __init__(self, config: LlamaConfig) -> None:
+        super().__init__(config)
+        for layer in self.layers:
+            layer.self_attn.is_causal = False
+
+    def _create_bidirectional_mask(
+        self,
+        input_embeds: torch.Tensor,
+        attention_mask: torch.Tensor | None,
+    ) -> torch.Tensor | None:
+        """
+        Create bidirectional attention mask.
+
+        Args:
+            input_embeds: Input embeddings tensor of shape (batch_size, seq_len, hidden_size)
+            attention_mask: Optional 2D attention mask of shape (batch_size, seq_len)
+                where 1 indicates tokens to attend to and 0 indicates masked tokens
+
+        Returns:
+            4D attention mask suitable for the attention implementation, or None
+            if no masking is needed
+        """
+        if attention_mask is None:
+            return None
+
+        if _HAS_NATIVE_BIDIRECTIONAL_MASK:
+            return create_bidirectional_mask(
+                self.config,
+                input_embeds,
+                attention_mask=attention_mask,
+            )
+
+        # Fallback for transformers < 5.0 without create_bidirectional_mask
+
+        # Flash attention handles 2D masks internally; only pass mask if there
+        # are actually masked tokens (zeros), otherwise return None for efficiency
+        if getattr(self.config, "_attn_implementation", None) == "flash_attention_2":
+            has_masked_tokens = (attention_mask == 0).any()
+            return attention_mask if has_masked_tokens else None
+
+        return _prepare_4d_attention_mask(attention_mask, input_embeds.dtype)
+
+    def forward(
+        self,
+        input_ids: torch.LongTensor | None = None,
+        attention_mask: torch.Tensor | None = None,
+        position_ids: torch.LongTensor | None = None,
+        past_key_values: Cache | None = None,
+        inputs_embeds: torch.FloatTensor | None = None,
+        cache_position: torch.LongTensor | None = None,
+        use_cache: bool | None = None,
+        **kwargs,
+    ) -> BaseModelOutputWithPast:
+        """
+        Forward pass with bidirectional attention.
+
+        Args:
+            input_ids: Input token IDs of shape (batch_size, seq_len)
+            attention_mask: Attention mask of shape (batch_size, seq_len)
+            position_ids: Position IDs for rotary embeddings
+            past_key_values: Cached key/value states for incremental decoding
+            inputs_embeds: Pre-computed input embeddings (alternative to input_ids)
+            cache_position: Position indices for cache updates
+            use_cache: Whether to return cached key/value states
+            **kwargs: Additional arguments passed to decoder layers
+
+        Returns:
+            BaseModelOutputWithPast containing last_hidden_state and past_key_values
+        """
+        if (input_ids is None) ^ (inputs_embeds is not None):
+            raise ValueError(
+                "You must specify exactly one of input_ids or inputs_embeds"
+            )
+
+        if inputs_embeds is None:
+            inputs_embeds = self.embed_tokens(input_ids)
+
+        # Initialize cache if needed
+        if use_cache and past_key_values is None:
+            if _DYNAMIC_CACHE_ACCEPTS_CONFIG:
+                past_key_values = DynamicCache(config=self.config)
+            else:
+                past_key_values = DynamicCache()
+
+        if cache_position is None:
+            past_seen_tokens = (
+                past_key_values.get_seq_length() if past_key_values is not None else 0
+            )
+            cache_position = torch.arange(
+                past_seen_tokens,
+                past_seen_tokens + inputs_embeds.shape[1],
+                device=inputs_embeds.device,
+            )
+
+        if position_ids is None:
+            position_ids = cache_position.unsqueeze(0)
+
+        bidirectional_mask = self._create_bidirectional_mask(
+            inputs_embeds, attention_mask
+        )
+
+        hidden_states = inputs_embeds
+        position_embeddings = self.rotary_emb(hidden_states, position_ids)
+
+        # Build decoder layer kwargs with correct cache parameter name
+        # (past_key_value in < 4.56, past_key_values in >= 4.56)
+        layer_kwargs = {
+            "attention_mask": bidirectional_mask,
+            "position_ids": position_ids,
+            "use_cache": use_cache,
+            "cache_position": cache_position,
+            "position_embeddings": position_embeddings,
+        }
+        if _USE_PLURAL_CACHE_PARAM:
+            layer_kwargs["past_key_values"] = past_key_values
+        else:
+            layer_kwargs["past_key_value"] = past_key_values
+
+        for decoder_layer in self.layers[: self.config.num_hidden_layers]:
+            layer_outputs = decoder_layer(hidden_states, **layer_kwargs)
+
+            # Decoder returns tuple in < 4.54, tensor in >= 4.54
+            if isinstance(layer_outputs, tuple):
+                hidden_states = layer_outputs[0]
+            else:
+                hidden_states = layer_outputs
+
+        hidden_states = self.norm(hidden_states)
+
+        return BaseModelOutputWithPast(
+            last_hidden_state=hidden_states,
+            past_key_values=past_key_values,
+        )

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b30479054f57d91bf9f76682ec2a3471a845142ba3430eb3bc146b31422dc008
+size 2516761000

modules.json

@@ -0,0 +1,20 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.base.modules.transformer.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.sentence_transformer.modules.pooling.Pooling"
+  },
+  {
+    "idx": 2,
+    "name": "2",
+    "path": "2_Normalize",
+    "type": "sentence_transformers.sentence_transformer.modules.normalize.Normalize"
+  }
+]

sentence_bert_config.json

@@ -0,0 +1,10 @@
+{
+    "transformer_task": "feature-extraction",
+    "modality_config": {
+        "text": {
+            "method": "forward",
+            "method_output_name": "last_hidden_state"
+        }
+    },
+    "module_output_name": "token_embeddings"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2290cbd256f27c08f40dc569b63abf77f9d5b012514a1e2aabb589b63ba74ba
+size 17210189

tokenizer_config.json

@@ -0,0 +1,14 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<|begin_of_text|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|end_of_text|>",
+  "is_local": false,
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 2048,
+  "pad_token": "<|end_of_text|>",
+  "tokenizer_class": "TokenizersBackend"
+}