metadata

tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - generated_from_trainer
  - dataset_size:3221
  - loss:MultipleNegativesRankingLoss
base_model: BAAI/bge-small-en
widget:
  - source_sentence: • 2 x AMD EPYC 7763 64-core processors
    sentences:
      - "QuickSpecs\nHPE Cray XD670\nConfiguration Information\nDA - 16896\_\_\_Worldwide QuickSpecs — Version 16 — 10/7/2024\nPage\_ 22"
      - "HPE 1.8TB SAS 12G Mission Critical 10K SFF SC 3-year Warranty 512e Multi Vendor HDD 872481-H21\nHard Drive Blank Kits \_\nHPE Small Form Factor Hard Drive Blank Kit 666987-B21\nNotes:  Hard Drives require the selection of appropriate Drive Cage. \_\n\_\nSSD Selection\nTo streamline the configuration process for HPE ProLiant Gen10 servers and to provide the best product\navailability, HPE recommends SSDs from the list located here: http://www.hpe.com/products/recommend .\n\_\nAll SSD options listed are compatible on both the XL675d and XL645d servers, except where explicitly\nmarked.\nRead Intensive - 12G SAS - SFF - Solid State Drives \_\nHPE 960GB SAS 12G Read Intensive SFF SC Value SAS Multi Vendor SSD P36997-H21\nHPE 1.92TB SAS 12G Read Intensive SFF SC Value SAS Multi Vendor SSD P36999-H21\nHPE 3.84TB SAS 12G Read Intensive SFF SC Value SAS Multi Vendor SSD P37001-H21\nHPE 7.68TB SAS 12G Read Intensive SFF SC Value SAS Multi Vendor SSD P37003-H21\nMixed Use - 12G SAS - SFF - Solid State Drives \_\nHPE 960GB SAS 12G Mixed Use SFF SC Value SAS Multi Vendor SSD P37005-H21\nHPE 1.92TB SAS 12G Mixed Use SFF SC Value SAS Multi Vendor SSD P37011-H21\nHPE 3.84TB SAS 12G Mixed Use SFF SC Value SAS Multi Vendor SSD P37017-H21\nMixed Use - 6G SATA - SFF - Solid State Drives \_\nHPE 480GB SATA 6G Mixed Use SFF SC Multi Vendor SSD P18432-H21\nHPE 960GB SATA 6G Mixed Use SFF SC Multi Vendor SSD P18434-H21\nHPE 1.92TB SATA 6G Mixed Use SFF SC Multi Vendor SSD P18436-H21\nHPE 3.84TB SATA 6G Mixed Use SFF SC Multi Vendor SSD P18438-H21\nRead Intensive - 6G SATA - SFF - Solid State Drives \_\nHPE 240GB SATA 6G Read Intensive SFF SC Multi Vendor SSD P18420-H21\nHPE 480GB SATA 6G Read Intensive SFF SC Multi Vendor SSD P18422-H21\nHPE 960GB SATA 6G Read Intensive SFF SC Multi Vendor SSD P18424-H21\nHPE 1.92TB SATA 6G Read Intensive SFF SC Multi Vendor SSD P18426-H21\nHPE 3.84TB SATA 6G Read Intensive SFF SC Multi Vendor SSD P18428-H21\nHPE 7.68TB SATA 6G Read Intensive SFF SC Multi Vendor SSD P18430-H21\n\_\nRead Intensive - NVMe - SFF - Solid State Drives \_\nHPE 480GB NVMe Gen3 Mainstream Performance Read Intensive M.2 Multi Vendor SSD P40513-H21\nHPE 960GB NVMe Gen3 Mainstream Performance Read Intensive M.2 Multi Vendor SSD P40514-H21\nHPE 1.92TB NVMe Gen3 Mainstream Performance Read Intensive M.2 Multi Vendor SSD P40515-H21\nHPE 3.84TB NVMe Gen4 Mainstream Performance Read Intensive SFF SC U.3 Static V2\nMulti Vendor SSD\nP64845-H21\nHPE 480GB NVMe Gen4 Mainstream Performance Read Intensive M.2 PM9A3 SSD P69543-H21\nMixed Use - NVMe - SFF - Solid State Drives \_\nHPE 1.6TB NVMe Gen4 Mainstream Performance Mixed Use SFF SC U.3 Static V2 Multi\nVendor SSD\nP65003-H21\nQuickSpecs\nHPE Apollo 6500 Gen10 Plus System\nAdditional Options\nDA - 16700\_\_\_Worldwide QuickSpecs — Version 25 — 6/3/2024\nPage\_ 45"
      - "Intel Xeon-Gold 6434 3.7GHz 8-core 195W Processor Kit for HPE Cray XD\nP56395-\nB21\nIntel Xeon-Gold 5415+ 2.9GHz 8-core 150W Processor Kit for HPE Cray XD\nP56391-\nB21\n\_\nNotes:\n−  \"HPE Cray XD220v CPU 1 Rear FIO Heat Sink Kit\" (P49855-B21) must be ordered for 1st\nProcessor.\n−  \"HPE Cray XD220v CPU 2 Front Heat Sink Kit\" (P49854-B21) must be ordered for 2nd\nProcessor."
  - source_sentence: '- 2 x 16 GB DDR4-2933-MHz memory modules'
    sentences:
      - "HPE Performance Cluster Manager 1 Node 3yr 24x7 Support Perpetual LTU Q9V60A\nNotes:\n−  One license per node.\n−  Includes three years of support.\n−  This is a perpetual license. The software will continue working even when the support term ends.\nHPE Performance Cluster Manager FIO Software Q9V61A\nNotes:\n−  This SKU does not include the license. Please order with Q9V60AAE.\n−  Order one per node\nHPE Performance Cluster Manager Media Kit Q9V62A\nNotes:  One media kit per solution.\n\_\n\_\nHPE Power Distribution Units\nPower Distribution Units (PDUs) are an integral piece to this data center solution and HPE offers several\ntypes. Basic PDUs provide reliable power with 0U or 1U installation options. Metered PDUs have added\nintelligence to precisely track power usage and switched PDUs provide both local and remote power\nmanagement. There are additional metered PDUs that are recommended for this solution that are not part\nof the mainstream PDU product offering. They are as follows:\nHPE Switched 3-phase 66.5kVA/60309 5-wire 100A/277V 21-breaker Vertical NA PDU R8P19A\nHPE Metered 3Ph 66.5kVA/60309 100A 5-wire 480/277V Outlets (21) SDG23/Vertical NA\nPDU\n879034-B21\nHPE Metered 3Ph 39.9kVA/60309 60A 5-wire 480/277V Outlets (21) SDG23/Vertical NA\nPDU \_\n880459-B21\nHPE Metered 3Ph 57.6kVA/60309 100A 5-wire 80A/230V Outlets (3) C13 (18) C19/Vertical\nNA PDU\n880460-B21\nHPE Metered 3Ph 34.5kVA/60309 60A 5-wire 48A/230V Outlets (3) C13 (18) C19/Vertical NA\nFIO PDU\n880461-B21\nHPE Cray Supercomputer 60A 415V 3 Phase 24 CX PDU R4N30A\nHPE Mtrd 3P 69.1kVA 125A 96A230V FIO PDU 880462-B21\nHPE Metered 3Ph 45.1kVA/60309 63A 5-wire 63A/230V Outlets (3) C13 (18) C19/Vertical\nINTL FIO PDU\n880463-B21\nHPE Cray Supercomputer 63A 400V 3 Phase 24 CX PDU \_ R4N29A\nHPE G2 Metered/Switched 3Ph 17.3kVA/60309 4-wire 48A/208V Out (12) C13 (12)\nC19/Vertical NA/JP PDU\nP9S22A\nHPE G2 Metered 3Ph 17.3kVA/60309 60A 4-wire 48A/208V Outlets (12) C13 (12)\nC19/Vertical NA/JP PDU\nP9R86A\nHPE G2 Metered Modular 3Ph 17.3kVA/60309 60A 4-wire 48A/208V Outlets (6) C19/1U\nHorizontal NA/JP PDU\nP9R80A\nQuickSpecs\nHPE Cray XD2000\nConfiguration Information\nDA - 16905\_\_\_Worldwide QuickSpecs — Version 20 — 10/7/2024\nPage\_ 28"
      - "World's most secure industry standard server using HPE iLO5\n\_\nHPE ProLiant XL675d Gen10 Plus - Front Panel View\n1. Serial number / iLO Information pull tab 4. Chassis front door lever button\n2. Power Switch module 5. Drive Box 2\n3. Drive Box 1 6. Dedicated iLO management port\n\_\nQuickSpecs\nHPE Apollo 6500 Gen10 Plus System\nOverview\nDA - 16700\_\_\_Worldwide QuickSpecs — Version 25 — 6/3/2024\nPage\_ 2"
      - "8SFF Front View - 8 SFF + optional Universal Media Bay, optical Drive, Display Port, USB2.0, and\nSATA Drive shown \_\n\_ \_\n1. Quick removal access panel 9. Health LED \_\n2. Serial number/iLO information pull tab 10. NIC Status  1 \_\n3. Display Port (optional - shown) 11. Unit ID Button/LED \_\n4. Universal Media Bay (optional): 12. USB 3.2 Gen1 port \_\n\_ Option1: Optical drive bay + Display port &\nUSB 2.0 port kit (shown)\n13. Drive bays; backplanes options \_\n\_ Option1: 8SFF x1 Tri-Mode 24G U.3 BC\nBackplane\_ Option2: 2 SFF x4 Tri-Mode 24G U.3 BC\nDrive Cage \_\n5. USB 3.2 Gen1 port (optional - shown) \_ Option2: 8SFF x4 Tri-Mode 24G U.3\nBC\nBackplane\n\_\n6. Optical Drive (optional- shown)\n7. iLO Service Port 14. Drive support label\n8. Power On / Standby button and system power LED \_ \_ \_\nNotes:  1 Front NIC LED display doesn't support NIC LED ACT/LINK indication from ALOM/PCIE/FLOM\nNIC's\n\_\n12 LFF Front View - 12 LFF + SAS drives shown \_\n\_ \_\n1. Serial number/iLO information pull tab 6. NIC Status  1 \_\n2. USB 3.2 Gen1 Port 7. Unit ID Button/LED \_\n3. iLO Service Port 8. SAS/SATA drive bays \_\nQuickSpecs\nHPE ProLiant DL320 Gen11\nOverview\nDA - 16919\_\_\_Worldwide QuickSpecs — Version 28 — 10/7/2024\nPage\_ 2"
  - source_sentence: '*   2 x PCIe x4 slots for HPE iLO 5 management per node'
    sentences:
      - "HPE ProLiant XL645d System Block Diagrams  - PCIe GPU Configuration \n\_\nQuickSpecs\nHPE Apollo 6500 Gen10 Plus System\nStandard Features\nDA - 16700\_\_\_Worldwide QuickSpecs — Version 25 — 6/3/2024\nPage\_ 18"
      - "Date Version\nHistory\nAction Description of Change\n03-Jun-2024 Version 24 Changed Additional Options section was updated.\nObsolete SKUs were removed\n04-Mar-2024 Version 23 Changed Configuration Information section was updated\nObsolete SKUs were removed\n04-Dec-2023 Version 22 Changed Configuration Information section was updated\nObsolete SKUs were removed\n06-Nov-2023 Version 21 Changed Configuration Information section was updated\nObsolete SKUs were removed\n05-Sep-2023 Version 20 Changed Configuration Information section was updated\nObsolete SKUs were removed\n10-Jul-2023 Version 19 Changed Standard Features section was updated.\n20-Jun-2023 Version 18 Changed Overview section was updated\n03-Apr-2023 Version 17 Changed Optional Features and Configuration Information sections\nwere updated\n06-Feb-2023 Version 16 Changed Overview and Configuration Information sections were\nupdated\n05-Dec-2022 Version 15 Changed Core Options section was updated\n07-Nov-2022 Version 14 Changed Configuration Information section was updated\nObsolete SKUs were removed\n01-Aug-2022 Version 13 Changed Configuration Information section was updated\n05-Jul-2022 Version 12 Changed Configuration Information section was updated\nObsolete SKUs were removed\n16-May-2022 Version 11 Changed Configuration Information section was updated\nObsolete SKUs were removed\n21-Mar-2022 Version 10 Changed Standard Features and Configuration Information were\nremoved.\n07-Feb-2022 Version 9 Changed Configuration Information section was updated\n10-Jan-2022 Version 8 Changed Additional Options section was updated.\nObsolete SKUs were removed\n01-Nov-2021 Version 7 Changed Added Software Development Tools\nOverview, Standard features and Additional Options sections\nwere updated.\nObsolete SKUs were removed\n07-Sep-2021 Version 6 Changed Additional Options section was updated.\nObsolete SKUs were removed\n02-Aug-2021 Version 5 Changed Obsolete SKUs were removed\n04-May-2021 Version 4 Changed Overview, Standard Features, Optional Features,\nConfiguration Information and Additional Options were\nremoved.\n06-Apr-2021 Version 3 Changed Standard Features, Configuration Information, Additional\nOptions and Technical Specifications sections were updated.\n01-Feb-2021 Version 2 Changed Overview, Standard Features, Configuration Information,\nAdditional Options and Technical Specifications sections were\nupdated.\nObsolete SKUs were removed\nQuickSpecs\nHPE Apollo 6500 Gen10 Plus System\nSummary of Changes\nDA - 16700\_\_\_Worldwide QuickSpecs — Version 25 — 6/3/2024\nPage\_ 52"
      - "Storage Controller Cable Kits\nHPE XL22xn Gen10+ E208ip/P408ip Cbl Kit\nHPE XL225n Gen10+ SATA Cbl Kit\nNotes:  By default, Embedded Controller will work in AHCI Mode. If \"P28417-B21 - HPE SR100i Gen10+\nSoftware RAID\" is selected, then Embedded Controller will work in SR100i Mode.\nMaximum Internal StoragePer node\nDrive Capacity Configuration\nHot Plug SFF SATA SSD 46TB 6 x 7.68TB\nHot Plug SFF SAS SSD 91TB 6 x 15.3TB\nHot Plug NVMe SSD (AMD) 30TB 2x 15.3TB\nHot Plug NVMe SSD (Intel) 92TB 6x 15.3TB\n\_\nNotes:  NVMe is x2 for Intel\nInternal Storage Devices\nOptional USB Mezz Riser Kit\n\_\nInterfaces\nKVM Serial USB Video Port (SUV)\nUSB Ports 3 external USB ports via SUV (2 regular USB, 1\nUSB management); 1 USB 3.2 Gen1 Type A Port\n(external)\nHPE iLO Remote Management Network Port NIC/Shares iLO network port (AMD only) Separate\nNIC and iLO ports on Intel node\nHealth LED 1\nPower 1\nUID 1\nDo not remove LED 1\nIndustry Standard Compliance\nACPI 6.3 Compliant\nPCIe 4.0 Compliant\nWOL Support\nMicrosoft® Logo certifications\nPXE Support\nUSB 3.0 Compliant (internal); USB 2 .0 compliant (external ports via SUV)\nSMBIOS 3.2\nUEFI 2.8\nRedfish API\nEuropean Union Erp Lot 9 Regulation European Union (EU) eco-design regulations for server and\nstorage products, known as Lot 9, establishes power thresholds for idle state, as well as efficiency\nand performance in active state which vary among configurations. HPE ProLiant Gen10 Plus servers\nQuickSpecs\nHPE Apollo 2000 Gen10 Plus System\nStandard Features\nDA - 16526\_\_\_Worldwide QuickSpecs — Version 41 — 7/1/2024\nPage\_ 14"
  - source_sentence: What type of processors are supported by the HPE Cray XD665 System?
    sentences:
      - "HPE Cray XD675 Server Top View\nItem Description \_ \_\n1. 8x AMD MI300X OAM Accelerator \_ \_\n\_\nQuickSpecs\nHPE Cray XD675\nOverview\nDA - 17239\_\_\_Worldwide QuickSpecs — Version 4 — 8/19/2024\nPage\_ 2"
      - "HPE Cray XD665\nHPE is bringing the power of supercomputing to datacenters of any size with the HPE Cray XD665 System .\nHPE Cray XD665 System is a top-performing GPU-accelerated server, delivering mixed-HPC/AI workload\nsolutions to rack-scale, in a rack and roll fashion. \_\nHPE Cray XD665 System is a 4U chassis system that contains a single 2x CPU node with 4x Nvidia H100\nTensor Core SXM5 GPUs. It offers a complete, scalable solution for AI & HPC customers everywhere, with\nflexibility of fabric, memory, storage and operating system. HPE Cray XD665 System provides maximum\nperformance for advanced HPC Simulations, AI Training and Deep Learning. \_\nBuilt with Exascale-ready networking technologies, integrated storage, extensive software portfolio and\nmanagement tools, HPE Cray XD665 Systems can enable customers to innovate and prepare for tomorrow's\nchallenges.\nHPE Cray XD665 Server System Key Features\n4U Single-Node Chassis (Air & Liquid-Cooled)\nGPUs: 4x NVIDIA® H100 Tensor Core SXM5 GPUs providing leadership performance for AI Training,\nDeep Learning and advanced HPC simulations. PCIe GPUs are not supported on Cray XD665.\nCPUs: Support for 4 th  Generation AMD® EPYC® Scalable Processors: \"Genoa\"\nDRAM: Support for up to 24x DDR5 4800MT/s DIMMs\nHigh-Speed Fabric: 5x PCIe Gen 5.0 Half-Height, Half-Length slots supporting Slingshot 11, Infiband\nNDR and Ethernet, providing direct switchable connections between High-Speed Fabric, GPUs, NVMe\ndrives and CPUs.\nStorage: Up to 8 SFF NVME U.3 and 2 M.2 RAID SSDs\nPower Supplies: 6x 3,000-Watt capacity per server system, providing full N+N redundancy.\nPCIe Expansion: 1x HHHL PCIe 5.0, 1x OCP 3.0 expansion slot with embedded 2-port 10G Base-T\n(RJ45), 1 1GbE NIC, 1x BMC Port, 1x VGA, 1x USB3.0, PWR Button/Reset/ID Button/Status LEDs \_\nNVIDIA and NVLink are trademarks and/or registered trademarks of NVIDIA Corporation in the U.S. and\nother countries. All third-party marks are the property of their respective owners. \_\nAMD and EPYC are trademarks and/or registered trademarks of Advanced Micro Devices, Inc. in the U.S.\nand other countries. All third-party marks are property of their respective owners\n\_\nQuickSpecs\nHPE Cray Supercomputing XD665 System\nOverview\nDA - 17114\_\_\_Worldwide QuickSpecs — Version 9 — 10/21/2024\nPage\_ 1"
      - "EPYC\n7543P\n32 2.8GHz 3.7GHz 2TB 225 256MB 3200MT/s\nEPYC\n7443P\n24 2.85GHs 4.0GHz 2TB 200 128 MB 3200MT/s\nEPYC\n7313P\n16 3.0GHz 3.7GHz 2TB 155 128MB 3200MT/s\nIntel Xeon \nProcessor\nCores Base\nFrequency\nMax\nFrequenc\ny\nMax\nMemory\nWattage Cache\n1.5MB/cor\ne\nMemory\nXeon 8380 40 2.3GHz 3.4GHz 6TB/socket 270 60MB 3200MT/s\nXeon 8368 38 2.4GHz 3.4GHz 6TB/socket 270 57MB 3200MT/s\nXeon\n8360Y\n36 2.4GHz 3.5GHz 6TB/socket 250 54MB 3200MT/s\nXeon 8358 32 2.6GHZ 3.4GHz 6TB/socket 250 48MB 3200MT/s\nXeon\n8352Y\n32 2.2GHz 3.4GHz 6TB/socket 205 48MB 3200MT/s\nXeon 6354 18 3.0GHz 3.6GHz 6TB/socket 205 39MB 3200MT/s\nXeon 6348 28 2.6GHz 3.5GHz 6TB/socket 235 42MB 3200MT/s\nXeon 6346 16 3.1GHz 3.6GHz 6TB/socket 205 36MB 3200MT/s\nXeon 6338 32 2.0GHz 3.2GHz 6TB/socket 205 48MB 3200MT/s\nXeon 6330 28 2.0GHZ 3.1GHz 6TB/socket 205 42MB 3200MT/s\nXeon 6342 24 2.8GHZ 3.5GHz 6TB/socket 230 36MB 3200MT/s\nXeon\n4309Y\n8 2.8GHz 3.6GHz 6TB/socket 105 12MB 3200MT/s\nXeon 4310 12 2.1GHz 3.3GHz 6TB/socket 120 18MB 3200MT/s\nXeon 4314 16 2.4GHz 3.4GHz 6TB/socket 135 24MB 3200MT/s\nXeon 4316 20 2.3GHz 3.4GHz 6TB/socket 150 30MB 3200MT/s\nXeon\n5318Y\n24 2.1GHz 3.4GHz 6TB/socket 165 36MB 3200MT/s\nXeon 5320 26 2.2GHz 3.4GHz 6TB/socket 185 39MB 3200MT/s\nXeon\n6336Y\n24 2.4GHz 3.6GHz 6TB/socket 185 36MB 3200MT/s\nXeon\n5115Y\n8 3.2GHz 3.6GHz 6TB/socket 140 12MB 3200MT/s\nXeon 5317 12 3.0GHz 3.6GHZ 6TB/socket 150 18MB 3200MT/s\nXeon 6326 16 2.9GHz 3.5GHz 6TB/socket 185 24MB 3200MT/s\nXeon 6334 8 3.6GHz 3.7GHz 6TB/socket 165 18MB 3200MT/s\nChipset\nNo Chipset - System on Chip (SoC) design\nOn System Management Chipset\nHPE iLO 5 ASIC\nRead and learn more in the  iLO  QuickSpecs\nQuickSpecs\nHPE Apollo 2000 Gen10 Plus System\nStandard Features\nDA - 16526\_\_\_Worldwide QuickSpecs — Version 41 — 7/1/2024\nPage\_ 9"
  - source_sentence: >-
      What is the website to find services for customers purchasing from a
      commercial reseller?
    sentences:
      - "HPE Cray XD675 Server Top View\nItem Description \_ \_\n1. 8x AMD MI300X OAM Accelerator \_ \_\n\_\nQuickSpecs\nHPE Cray XD675\nOverview\nDA - 17239\_\_\_Worldwide QuickSpecs — Version 4 — 8/19/2024\nPage\_ 2"
      - "AMD EPYC 7443P 2.85GHz 24-core 200W FIO Processor Kit for HPE ProLiant XL225n\nGen10 Plus\nP38737-L21\nAMD EPYC 7313P 3.0GHz 16-core 155W FIO Processor Kit for HPE ProLiant XL225n\nGen10 Plus\nP38736-L21\nAMD EPYC 7552 (2.2GHz/48-core/200W) FIO Processor Kit for HPE ProLiant XL225n\nGen10 Plus P24258-L21\nAMD EPYC 7542 (2.9GHz/32-core/225W) FIO Processor Kit for HPE ProLiant XL225n\nGen10 Plus P24259-L21\nAMD EPYC 7502 (2.5GHz/32-core/180W) FIO Processor Kit for HPE ProLiant XL225n\nGen10 Plus P24260-L21\nAMD EPYC 7452 (2.35GHz/32-core/155W) FIO Processor Kit for HPE ProLiant XL225n\nGen10 Plus P24261-L21\nAMD EPYC 7402 (2.8GHz/24-core/180W) FIO Processor Kit for HPE ProLiant XL225n\nGen10 Plus P24262-L21\nAMD EPYC 7352 (2.3GHz/24-core/155W) FIO Processor Kit for HPE ProLiant XL225n\nGen10 Plus P24263-L21\nAMD EPYC 7302 (3.0GHz/16-core/155W) FIO Processor Kit for HPE ProLiant XL225n\nGen10 Plus P24264-L21\nAMD EPYC 7702P (2.0GHz/64-core/200W) FIO Processor Kit for HPE ProLiant XL225n\nGen10 Plus P24266-L21\nAMD EPYC 7402P (2.8GHz/24-core/180W) FIO Processor Kit for HPE ProLiant XL225n\nGen10 Plus P24268-L21\nAMD EPYC 7302P (3.0GHz/16-core/155W) FIO Processor Kit for HPE ProLiant XL225n\nGen10 Plus P24269-L21\nAMD EPYC 7662 (2.0GHz/64-core/225W) FIO Processor Kit for HPE ProLiant XL225n\nGen10 Plus P24392-L21\nAMD EPYC 7642 (2.3GHz/48-core/225W) FIO Processor Kit for HPE ProLiant XL225n\nGen10 Plus P24393-L21\nAMD EPYC 7252 (3.1GHz/8-core/120W) FIO Processor Kit for HPE ProLiant XL225n\nGen10 Plus P24397-L21\nAMD EPYC 7F32 (3.7GHz/8-core/180W) FIO Processor Kit for HPE ProLiant XL225n\nGen10 Plus\nP26686-L21\nAMD EPYC 7F52 (3.5GHz/16-core/240W) FIO Processor Kit for HPE ProLiant XL225n\nGen10 Plus\nP26687-L21\nAMD EPYC 7F72 (3.2GHz/24-core/240W) FIO Processor Kit for HPE ProLiant XL225n\nGen10 Plus\nP26688-L21\n\_\n\_\nIntel Processors - Factory Integrated Processor Kit for XL220n & XL290n\nIntel Xeon-Platinum 8380 2.3GHz 40-core 270W FIO Processor Kit for HPE ProLiant\nXL2x0n Gen10 Plus P36816-L21\nIntel Xeon-Platinum 8368 2.4GHz 38-core 270W FIO Processor Kit for HPE ProLiant\nXL2x0n Gen10 Plus P36815-L21\nQuickSpecs\nHPE Apollo 2000 Gen10 Plus System\nAdditional Options\nDA - 16526\_\_\_Worldwide QuickSpecs — Version 41 — 7/1/2024\nPage\_ 33"
      - "Parts and Materials\nHPE will provide HPE-supported replacement parts and materials necessary to maintain the covered hardware\nproduct in operating condition, including parts and materials for available and recommended engineering\nimprovements. \_\nParts and components that have reached their maximum supported lifetime and/or the maximum usage\nlimitations as set forth in the manufacturer's operating manual, product quick-specs, or the technical product\ndata sheet will not be provided, repaired, or replaced as part of these services.\n\_\nHow to Purchase Services\nServices are sold by Hewlett Packard Enterprise and Hewlett Packard Enterprise Authorized Service Partners:\nServices for customers purchasing from HPE or an enterprise reseller are quoted using HPE order\nconfiguration tools.\nCustomers purchasing from a commercial reseller can find services at\nhttps://ssc.hpe.com/portal/site/ssc/\n\_\nAI Powered and Digitally Enabled Support Experience\nAchieve faster time to resolution with access to product-specific resources and expertise through a digital and\ndata driven customer experience \_\nSign into the HPE Support Center experience, featuring streamlined self-serve case creation and\nmanagement capabilities with inline knowledge recommendations. You will also find personalized task alerts\nand powerful troubleshooting support through an intelligent virtual agent with seamless transition when needed\nto a live support agent. \_\nhttps://support.hpe.com/hpesc/public/home/signin\nConsume IT On Your Terms\nHPE GreenLake  edge-to-cloud platform brings the cloud experience directly to your apps and data wherever\nthey are-the edge, colocations, or your data center. It delivers cloud services for on-premises IT infrastructure\nspecifically tailored to your most demanding workloads. With a pay-per-use, scalable, point-and-click self-\nservice experience that is managed for you, HPE GreenLake edge-to-cloud platform accelerates digital\ntransformation in a distributed, edge-to-cloud world.\nGet faster time to market\nSave on TCO, align costs to business\nScale quickly, meet unpredictable demand\nSimplify IT operations across your data centers and clouds\nTo learn more about HPE Services, please contact your Hewlett Packard Enterprise sales representative or\nHewlett Packard Enterprise Authorized Channel Partner. \_ Contact information for a representative in your area\ncan be found at \"Contact HPE\"  https://www.hpe.com/us/en/contact-hpe.html \_\nFor more information\nhttp://www.hpe.com/services\nQuickSpecs\nHPE Cray XD675\nService and Support\nDA - 17239\_\_\_Worldwide QuickSpecs — Version 4 — 8/19/2024\nPage\_ 13"
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
  - dot_accuracy@1
  - dot_accuracy@3
  - dot_accuracy@5
  - dot_accuracy@10
  - dot_precision@1
  - dot_precision@3
  - dot_precision@5
  - dot_precision@10
  - dot_recall@1
  - dot_recall@3
  - dot_recall@5
  - dot_recall@10
  - dot_ndcg@10
  - dot_mrr@10
  - dot_map@100
model-index:
  - name: SentenceTransformer based on BAAI/bge-small-en
    results:
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: Unknown
          type: unknown
        metrics:
          - type: cosine_accuracy@1
            value: 0.4857142857142857
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.8047619047619048
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.861904761904762
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.9095238095238095
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.4857142857142857
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.26825396825396824
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.17238095238095236
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.09095238095238094
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.4857142857142857
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.8047619047619048
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.861904761904762
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.9095238095238095
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.718420116457893
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.6551719576719578
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.6598918961837339
            name: Cosine Map@100
          - type: dot_accuracy@1
            value: 0.4857142857142857
            name: Dot Accuracy@1
          - type: dot_accuracy@3
            value: 0.8047619047619048
            name: Dot Accuracy@3
          - type: dot_accuracy@5
            value: 0.861904761904762
            name: Dot Accuracy@5
          - type: dot_accuracy@10
            value: 0.9095238095238095
            name: Dot Accuracy@10
          - type: dot_precision@1
            value: 0.4857142857142857
            name: Dot Precision@1
          - type: dot_precision@3
            value: 0.26825396825396824
            name: Dot Precision@3
          - type: dot_precision@5
            value: 0.17238095238095236
            name: Dot Precision@5
          - type: dot_precision@10
            value: 0.09095238095238094
            name: Dot Precision@10
          - type: dot_recall@1
            value: 0.4857142857142857
            name: Dot Recall@1
          - type: dot_recall@3
            value: 0.8047619047619048
            name: Dot Recall@3
          - type: dot_recall@5
            value: 0.861904761904762
            name: Dot Recall@5
          - type: dot_recall@10
            value: 0.9095238095238095
            name: Dot Recall@10
          - type: dot_ndcg@10
            value: 0.718420116457893
            name: Dot Ndcg@10
          - type: dot_mrr@10
            value: 0.6551719576719578
            name: Dot Mrr@10
          - type: dot_map@100
            value: 0.6598918961837339
            name: Dot Map@100

SentenceTransformer based on BAAI/bge-small-en

This is a sentence-transformers model finetuned from BAAI/bge-small-en. It maps sentences & paragraphs to a 384-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: BAAI/bge-small-en
Maximum Sequence Length: 512 tokens
Output Dimensionality: 384 tokens
Similarity Function: Cosine Similarity

Model Sources

Documentation: Sentence Transformers Documentation
Repository: Sentence Transformers on GitHub
Hugging Face: Sentence Transformers on Hugging Face

Full Model Architecture

SentenceTransformer(
  (0): Transformer({'max_seq_length': 512, 'do_lower_case': True}) with Transformer model: BertModel 
  (1): Pooling({'word_embedding_dimension': 384, '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:

pip install -U sentence-transformers

Then you can load this model and run inference.

from sentence_transformers import SentenceTransformer

# Download from the 🤗 Hub
model = SentenceTransformer("sentence_transformers_model_id")
# Run inference
sentences = [
    'What is the website to find services for customers purchasing from a commercial reseller?',
    'Parts and Materials\nHPE will provide HPE-supported replacement parts and materials necessary to maintain the covered hardware\nproduct in operating condition, including parts and materials for available and recommended engineering\nimprovements. \xa0\nParts and components that have reached their maximum supported lifetime and/or the maximum usage\nlimitations as set forth in the manufacturer\'s operating manual, product quick-specs, or the technical product\ndata sheet will not be provided, repaired, or replaced as part of these services.\n\xa0\nHow to Purchase Services\nServices are sold by Hewlett Packard Enterprise and Hewlett Packard Enterprise Authorized Service Partners:\nServices for customers purchasing from HPE or an enterprise reseller are quoted using HPE order\nconfiguration tools.\nCustomers purchasing from a commercial reseller can find services at\nhttps://ssc.hpe.com/portal/site/ssc/\n\xa0\nAI Powered and Digitally Enabled Support Experience\nAchieve faster time to resolution with access to product-specific resources and expertise through a digital and\ndata driven customer experience \xa0\nSign into the HPE Support Center experience, featuring streamlined self-serve case creation and\nmanagement capabilities with inline knowledge recommendations. You will also find personalized task alerts\nand powerful troubleshooting support through an intelligent virtual agent with seamless transition when needed\nto a live support agent. \xa0\nhttps://support.hpe.com/hpesc/public/home/signin\nConsume IT On Your Terms\nHPE GreenLake  edge-to-cloud platform brings the cloud experience directly to your apps and data wherever\nthey are-the edge, colocations, or your data center. It delivers cloud services for on-premises IT infrastructure\nspecifically tailored to your most demanding workloads. With a pay-per-use, scalable, point-and-click self-\nservice experience that is managed for you, HPE GreenLake edge-to-cloud platform accelerates digital\ntransformation in a distributed, edge-to-cloud world.\nGet faster time to market\nSave on TCO, align costs to business\nScale quickly, meet unpredictable demand\nSimplify IT operations across your data centers and clouds\nTo learn more about HPE Services, please contact your Hewlett Packard Enterprise sales representative or\nHewlett Packard Enterprise Authorized Channel Partner. \xa0 Contact information for a representative in your area\ncan be found at "Contact HPE"  https://www.hpe.com/us/en/contact-hpe.html \xa0\nFor more information\nhttp://www.hpe.com/services\nQuickSpecs\nHPE Cray XD675\nService and Support\nDA - 17239\xa0\xa0\xa0Worldwide QuickSpecs — Version 4 — 8/19/2024\nPage\xa0 13',
    'HPE Cray XD675 Server Top View\nItem Description \xa0 \xa0\n1. 8x AMD MI300X OAM Accelerator \xa0 \xa0\n\xa0\nQuickSpecs\nHPE Cray XD675\nOverview\nDA - 17239\xa0\xa0\xa0Worldwide QuickSpecs — Version 4 — 8/19/2024\nPage\xa0 2',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 384]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities.shape)
# [3, 3]

Evaluation

Metrics

Information Retrieval

Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.4857
cosine_accuracy@3	0.8048
cosine_accuracy@5	0.8619
cosine_accuracy@10	0.9095
cosine_precision@1	0.4857
cosine_precision@3	0.2683
cosine_precision@5	0.1724
cosine_precision@10	0.091
cosine_recall@1	0.4857
cosine_recall@3	0.8048
cosine_recall@5	0.8619
cosine_recall@10	0.9095
cosine_ndcg@10	0.7184
cosine_mrr@10	0.6552
cosine_map@100	0.6599
dot_accuracy@1	0.4857
dot_accuracy@3	0.8048
dot_accuracy@5	0.8619
dot_accuracy@10	0.9095
dot_precision@1	0.4857
dot_precision@3	0.2683
dot_precision@5	0.1724
dot_precision@10	0.091
dot_recall@1	0.4857
dot_recall@3	0.8048
dot_recall@5	0.8619
dot_recall@10	0.9095
dot_ndcg@10	0.7184
dot_mrr@10	0.6552
dot_map@100	0.6599

Training Details

Training Dataset

Unnamed Dataset

Size: 3,221 training samples
Columns: sentence_0 and sentence_1
Approximate statistics based on the first 1000 samples:
sentence_0 sentence_1
type string string
details
min: 3 tokens
mean: 22.72 tokens
max: 80 tokens

min: 36 tokens
mean: 328.94 tokens
max: 512 tokens

	sentence_0	sentence_1
type	string	string
details	min: 3 tokens mean: 22.72 tokens max: 80 tokens	min: 36 tokens mean: 328.94 tokens max: 512 tokens

Samples:

sentence_0	sentence_1
`What is the maximum number of Apollo n2X00 series chassis that can fit in a 42U rack?`	HPE Apollo 2000 Gen10 Plus System HPE is bringing the power of supercomputing to datacenters of any size with the Apollo 2000 Gen10 Plus system. The HPE Apollo 2000 Gen10 Plus System is a dense, multi-server platform that packs incredible performance and workload flexibility into a small datacenter space, while delivering the efficiencies of a shared infrastructure. It is designed to provide a bridge to scale-out architecture for traditional data centers, so enterprise and SME customers can achieve the space-saving value of density-optimized infrastructure in a cost-effective and non-disruptive manner. The Apollo 2000 Gen10 Plus offers a density optimized, shared infrastructure with a flexible scale-out architecture to support a variety of workloads from remote site systems to large HPC clusters and everything in between. HPE iLO5 provides built-in firmware-level server security with silicon root of trust. It can be deployed cost-effectively starting with a single 2U, shared infrastructure chassis and configured with a variety of storage options to meet the configuration needs of a wide variety of scale-out workloads. The Apollo 2000 Gen10 Plus System delivers up to four times the density of a traditional rack mount server with up to four ProLiant Gen10 Plus independent servers per 2U mounted in standard racks with rear-aisle serviceability access. A 42U rack fits up to 20 Apollo n2X00 series chassis accommodating up to 80 servers per rack. What's New Support for up to four Xilinx Alveo U50 single wide GPU's in XL290n node. Enables a robust stack of Intel 3 rd generation Xeon Scalable Processors to increase your power density and increase datacenter efficiency. Intel AVX-512 * feature increases memory bandwidth, improves frequency management to enable greater performance. Also Speed Select Technology (SST) allows Core count and frequency flexibility * The Direct Liquid Cooling (DLC) option for the Apollo 2000 Gen10 Plus System comes ready to plug and play. Choose from either CPU only or CPU plus memory cooling options. Enables flexible choices with Intel 3 rd Generation Xeon Scalable Processors and AMD 2 nd and 3 rd generation EPYC Processors New flexible infrastructure offers multiple storage options, 8 memory channels and 3200 MT/s memory, PCIe Gen4 and support for processors over 250W for improved application performance. Complete software portfolio for all customer workloads, for node to rack management, including comprehensive integrated cluster management software Secure from the start with firmware anchored into silicon with iLO5 and silicon root of trust for the highest level of system security Notes: *Available on select processors QuickSpecs HPE Apollo 2000 Gen10 Plus System Overview DA - 16526 Worldwide QuickSpecs — Version 41 — 7/1/2024 Page 1
`What is the maximum number of independent servers that can be mounted in a single 2U Apollo 2000 Gen10 Plus System chassis?`	HPE Apollo 2000 Gen10 Plus System HPE is bringing the power of supercomputing to datacenters of any size with the Apollo 2000 Gen10 Plus system. The HPE Apollo 2000 Gen10 Plus System is a dense, multi-server platform that packs incredible performance and workload flexibility into a small datacenter space, while delivering the efficiencies of a shared infrastructure. It is designed to provide a bridge to scale-out architecture for traditional data centers, so enterprise and SME customers can achieve the space-saving value of density-optimized infrastructure in a cost-effective and non-disruptive manner. The Apollo 2000 Gen10 Plus offers a density optimized, shared infrastructure with a flexible scale-out architecture to support a variety of workloads from remote site systems to large HPC clusters and everything in between. HPE iLO5 provides built-in firmware-level server security with silicon root of trust. It can be deployed cost-effectively starting with a single 2U, shared infrastructure chassis and configured with a variety of storage options to meet the configuration needs of a wide variety of scale-out workloads. The Apollo 2000 Gen10 Plus System delivers up to four times the density of a traditional rack mount server with up to four ProLiant Gen10 Plus independent servers per 2U mounted in standard racks with rear-aisle serviceability access. A 42U rack fits up to 20 Apollo n2X00 series chassis accommodating up to 80 servers per rack. What's New Support for up to four Xilinx Alveo U50 single wide GPU's in XL290n node. Enables a robust stack of Intel 3 rd generation Xeon Scalable Processors to increase your power density and increase datacenter efficiency. Intel AVX-512 * feature increases memory bandwidth, improves frequency management to enable greater performance. Also Speed Select Technology (SST) allows Core count and frequency flexibility * The Direct Liquid Cooling (DLC) option for the Apollo 2000 Gen10 Plus System comes ready to plug and play. Choose from either CPU only or CPU plus memory cooling options. Enables flexible choices with Intel 3 rd Generation Xeon Scalable Processors and AMD 2 nd and 3 rd generation EPYC Processors New flexible infrastructure offers multiple storage options, 8 memory channels and 3200 MT/s memory, PCIe Gen4 and support for processors over 250W for improved application performance. Complete software portfolio for all customer workloads, for node to rack management, including comprehensive integrated cluster management software Secure from the start with firmware anchored into silicon with iLO5 and silicon root of trust for the highest level of system security Notes: *Available on select processors QuickSpecs HPE Apollo 2000 Gen10 Plus System Overview DA - 16526 Worldwide QuickSpecs — Version 41 — 7/1/2024 Page 1
`What is the processor type supported by the HPE Apollo n2800 Gen10 Plus 24 SFF Flexible CTO chassis?`	HPE Apollo n2600 Gen10 Plus SFF CTO Chassis supports both Intel and AMD based server nodes HPE Apollo n2800 Gen10 Plus 24 SFF Flexible CTO chassis supports Intel based server nodes Backplane selection determines number and type of drives supported Item Description Item Description 1 SFF hot-plug drives 3 Health LED 2 Serial number/iLO information pull tab 4 UID button LED Chassis Rear Panel Components - 4 x 1U nodes Item Description Item Description 1 Server 3 & 4 4 iLO Ports 2 HPE Apollo Platform Manager (APM) 2.0 port 5 Server 1 & 2 3 Power supply 1 & 2 6 Optional Rack Consolidation Module (RCM) QuickSpecs HPE Apollo 2000 Gen10 Plus System Overview DA - 16526 Worldwide QuickSpecs — Version 41 — 7/1/2024 Page 2

Loss: MultipleNegativesRankingLoss with these parameters:

{
    "scale": 20.0,
    "similarity_fct": "cos_sim"
}

Training Hyperparameters

Non-Default Hyperparameters

eval_strategy: steps
per_device_train_batch_size: 256
per_device_eval_batch_size: 256
num_train_epochs: 20
multi_dataset_batch_sampler: round_robin

All Hyperparameters

Click to expand

overwrite_output_dir: False
do_predict: False
eval_strategy: steps
prediction_loss_only: True
per_device_train_batch_size: 256
per_device_eval_batch_size: 256
per_gpu_train_batch_size: None
per_gpu_eval_batch_size: None
gradient_accumulation_steps: 1
eval_accumulation_steps: None
torch_empty_cache_steps: None
learning_rate: 5e-05
weight_decay: 0.0
adam_beta1: 0.9
adam_beta2: 0.999
adam_epsilon: 1e-08
max_grad_norm: 1
num_train_epochs: 20
max_steps: -1
lr_scheduler_type: linear
lr_scheduler_kwargs: {}
warmup_ratio: 0.0
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: False
fp16: False
fp16_opt_level: O1
half_precision_backend: auto
bf16_full_eval: False
fp16_full_eval: False
tf32: None
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: False
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
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: False
hub_always_push: False
gradient_checkpointing: False
gradient_checkpointing_kwargs: None
include_inputs_for_metrics: False
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
dispatch_batches: None
split_batches: 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
batch_sampler: batch_sampler
multi_dataset_batch_sampler: round_robin

Training Logs

Epoch	Step	cosine_map@100
1.0	7	0.4864
2.0	14	0.5209
3.0	21	0.5131
4.0	28	0.5047
5.0	35	0.5480
6.0	42	0.5808
7.0	49	0.5950
7.1429	50	0.5975
8.0	56	0.6145
9.0	63	0.6268
10.0	70	0.6292
11.0	77	0.6385
12.0	84	0.6445
13.0	91	0.6279
14.0	98	0.6296
14.2857	100	0.6321
15.0	105	0.6317
16.0	112	0.6401
17.0	119	0.6590
18.0	126	0.6562
19.0	133	0.6599

Framework Versions

Python: 3.11.8
Sentence Transformers: 3.1.1
Transformers: 4.45.2
PyTorch: 2.2.2+cu121
Accelerate: 1.1.1
Datasets: 3.1.0
Tokenizers: 0.20.3

Citation

BibTeX

Sentence Transformers

@inproceedings{reimers-2019-sentence-bert,
    title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
    author = "Reimers, Nils and Gurevych, Iryna",
    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
    month = "11",
    year = "2019",
    publisher = "Association for Computational Linguistics",
    url = "https://arxiv.org/abs/1908.10084",
}

MultipleNegativesRankingLoss

@misc{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}
}