SentenceTransformer based on BAAI/bge-small-en-v1.5

This is a sentence-transformers model finetuned from BAAI/bge-small-en-v1.5. It maps sentences & paragraphs to a 384-dimensional dense vector space and can be used for retrieval.

Model Details

Model Description

  • Model Type: Sentence Transformer
  • Base model: BAAI/bge-small-en-v1.5
  • Maximum Sequence Length: 512 tokens
  • Output Dimensionality: 384 dimensions
  • Similarity Function: Cosine Similarity
  • Supported Modality: Text

Model Sources

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': 'BertModel'})
  (1): Pooling({'embedding_dimension': 384, 'pooling_mode': 'mean', 'include_prompt': True})
)

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 = [
    'SummaryPerformance-driven data/instructional coach with 3 years of experience promoting innovative instructional practices which are student-focused, research-based and outcome-oriented.\nCore QualificationsEdD Curriculum and Instruction LeadershipMS EducationConference Presenter - LEAD, PIE, Title I, WTN Tech ConferenceRTI2 Coordinator K-12Classroom Teacher (8 yrs.) - Elementary gradesStudent-led Conferences dissertation - research in practiceProgram development - District Data Notebooks, RTI2 Teams, Parent/Teacher Conference reforms\nProfessional Experience2013to01/2016Data/Instructional CoachMorris Hospital|Ottawa,IL,Responsibilities: K-12 position, assist teachers to improve classroom instruction, analyze data, implement RTI2, conduct PD for teachers, facilitate PLC meetings, fulfill Learning Leader responsibilities, serve on school Leadership Teams (WCES and WCPS), and chair District RTI2 Team meetings.07/2008to06/2013General EducatorMorris Hospital|Seneca,IL,Faculty - West Carroll Elementary School Math, Science, and Social Studies - 4th grade and 5th grade07/2005to06/2008General EducatorMilan Elementary|City,STATE,Faculty - Milan Elementary School General Education Teacher - 1st grade and 3rd grade\nEducation and TrainingExpected in2016totoEdD|Instruction and Curriculum LeadershipThe University of Memphis,Memphis,TNGPA:Successfully defended dissertation on Feb. 26, 2016Expected in2012totoSelect One|Humboldt State University,Arcata,CAGPA:Completed 3 credit hoursExpected in2009toto|The University of Tennessee,Chattanooga,TNGPA:Completed 3 credit hoursExpected in2009totoMS|Education Counseling School CounselingUniversity of TN Martin,Martin,TNGPA:Magna Cum LaudeEducation Counseling School Counseling Magna Cum LaudeExpected in2005totoB.S|Education Human Learning Human Learning K-8 Postgraduate StudiesUniversity of TN Martin,,TNGPA:Magna Cum LaudeEducation Human Learning Human Learning K-8 Magna Cum Laude Postgraduate Studies\nSkillsInstruction, Leadership, School Counseling, RTI2 Meetings, PLCs',
    "Title: Data EngineerLocation: fully remote, however, priority is given to candidates local to Boston, MA; Long Island, NY; or Golden, COWork Model: 12 month contract with extensions or conversions highly possiblePay Rate: 58-68 an hour\nDay to DayA mid-sized telecom company is looking for a Sr Data Engineer to join their Business Intelligence Insights team. This team is responsible for all of the data migration, data clean up, data integration, and warehousing for the company. In this role, you will primarily be responsible for data migration and clean up in existing platforms as well as newly or soon to be integrated systems. It is necessary to be well versed in MS SQL, with the ability to import data, manipulate data and put it back in, querying, and building indexes. It is also crucial to be versed with SSIS to load and validate dimensions and measures. Lastly, it will be important for this person to have exposure and understanding of Salesforce - ability to import data, query data, get data out of Salesforce, and use SOQL. This position is currently slated as a 12 month contract, with possibility to extend or convert to an FTE. This role is offering a pay rate of $58-68hr. During the contract period, health benefits and a 401k are offered by Insight Global. Priority is given to candidates sitting in Boston, Colorado, or Long Island, however the role is fully remote. If you're interested, please apply today!\nMust Haves7 years of Data Engineering experience5+ years of experience with MS SQL or SOQLExperience with ETL tools, specifically SSISFamiliarity and understanding of Salesforce PlussesOracle or Postgress experienceTalend, Matillion, or similar tool",
    'ERM is hiring a motivated consulting Senior Electrical Engineer, PE with a focus on electrical design and analysis across Multiple Locations in the U.S. The position is hybrid with the opportunity for flexibility in working from home & office. In this role, you will work closely with multi-discipline teams including project managers, engineers, and scientists to contribute to the planning, design, permitting and implementation of engineering projects in the renewable energy and power sectors.\nSeeking candidates with Project based Engineering experience, NOT Product based. Must have experience with utility projects above 20MW and a background in renewables.\nProjects will include development and review of construction drawings, technical specifications, contract documents, permit applications and calculations for renewable energy system components including photovoltaic solar technology, electrical substations, battery energy storage systems (BESS), distribution collector systems, and wind turbines. Staff management, project controls and management support for consulting and construction projects, including scheduling, labor resourcing, and cost estimating, will be a component of this position. Diverse and broad-based experiences, both in office and field settings, should be anticipated.\nRESPONSIBILITIES:Generate andor review equipment drawings and specifications for photovoltaic system components, solar modules, inverters, BESS, transformers, cable management systems and balance of systems (BOS).Procurement of equipment.Prepare electrical designs, including electrical loading and equipment sizing calculations. Apply technical knowledge of short circuiting, reactive capability, arc flash, cable ampacity, grounding, and voltage drop. Apply knowledge of NEC and IEEEANSI standards and electrical codes, as appropriate.Prepare electrical construction project cost estimates and schedules. Develop progress-tracking and completion reports.Provide technical expertise to navigate permitting challenges in the renewable energy and power sectors.Prepare technical proposals and participate in business development with existing clients and identified leads. Assist clients in developing strategies and preparing designs for proposed facilities, and prepare project work scopes, schedules, and budgets.Conduct field investigations, construction oversight and quality assurance activities and provide field exploration support as needed for design parameter development, and during construction for oversight and Construction Quality Assurance purposes.Work with other ERM resources to deepen relationships with ERM key clients and establish new client relationships that result in significant net revenue growth.Participate in project teams and independently on a global platform in varying settings that demand new and creative solutions.Lead, manage performance, hire and retain, inspire and mentor personnel for overall success of the technical team.\nREQUIREMENTS:B.S. andor M.S. in Electrical Engineering, with a focus on electricalProfessional Engineer (PE) license.5-10 years of electrical design experience, with focus in power generation, power distribution, andor renewable energy sectors. Candidates with significantly more experience or high performing candidates with less experience are encouraged to apply as multiple positions are available.Ability to work independently with minimal supervision, individually and as part of a project team.Experience with PVsyst (preferred) or pvCase or pvDesign, AutoCAD, and ERP Software.Advanced knowledge of the local regulatory climate, with proven negotiation skills with state and local regulators.Excellent verbal, writing, and computer skills (Excel, Word, PowerPoint).Demonstrated ability to research and prepare concise and accurate technical documents, with a keen attention to detail.Excellent interpersonal communication skills with complex technical knowledge and concepts.Proven business development experience for large programscontracts and client relationships supported by repeat business, including established contacts.Ability and willingness to travel. Less than 25% travel expected.\nWho We Are:As the largest global pure play sustainability consultancy, we partner with the worlds leading organizations, creating innovative solutions to sustainability challenges and unlocking commercial opportunities that meet the needs of today while preserving opportunity for future generations.\nAt ERM we know that creating a diverse, equitable and inclusive work environment is an essential part of making our company a great place to build a career. We also see our diversity as a strength that helps us create better solutions for our clients. Our diverse team of world-class experts supports clients across the breadth of their organizations to operationalize sustainability, underpinned by our deep technical expertise in addressing their environmental, health, safety, risk and social issues. We call this capability our boots to boardroom approach for its comprehensive service model that allows ERM to develop strategic and technical solutions that advance objectives on the ground or at the executive level.',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 384]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities)
# tensor([[1.0000, 0.7283, 0.5536],
#         [0.7283, 1.0000, 0.5912],
#         [0.5536, 0.5912, 1.0000]])

Training Details

Training Dataset

Unnamed Dataset

  • Size: 3,098 training samples
  • Columns: anchor and positive
  • Approximate statistics based on the first 1000 samples:
    anchor positive
    type string string
    details
    • min: 321 tokens
    • mean: 507.2 tokens
    • max: 512 tokens
    • min: 16 tokens
    • mean: 373.52 tokens
    • max: 512 tokens
  • Samples:
    anchor positive
    Professional Summary5 years of experience on Database development and administration, knowledge of relational database on SQL Server particularly on SSMS, SSRS, SSIS, Transact-SQL and SQL Server Agent.
    *Extensive exposure to creation of Database Objects, Stored Procedures, Triggers, Views, User Defined Functions and Cursors.
    Core QualificationsSQL Server Tools: SQL Server Management Studio (SSMS)Data Warehouse Tools: MS SQL Server 2005/2008/2012 Integration ServicesBusiness Intelligence Tools: SQL Server 2005/2008/2012 Business Intelligence Development StudioProgramming Languages: T-SQLReporting Tools: SQL Server 2005/2008/2012 Reporting ServicesDevelopment Environment: Visual Studio 2005/2008/2012Operating Systems: Windows XP/2003/2008 Server, Win 3.x/95/98, Vista, Win 7Advanced Excel V-lookup, Sub-total, Pivot table, and Chart.
    ExperienceData Analyst,11/2014toCurrentLiberty Healthcare Corporation–,OK,Experience in Cons... Kindly focus on the highlighted skill in the below requirements.
    Position: Salesforce BALocation: Phoenix or Salt Lake City (Onsite)

    Key Skills: 10+ years of overall experience 5+ Salesforce Certification 5+ years hands on experience as Business Analyst BFSI domain experience is preferred
    Professional SummaryYoung professional with
    hands-on experience analyzing data and model structures for large companies,
    including the Telecom industry. Skilled Data Analyst and Business Consultant.
    Accomplished in problem solving, advising best solutions and improving business
    through data analysis. Experience leading teams
    and presenting projects. Committed to delivering best possible outcomes and
    consistently recognized for outstanding excellence on several projects. Highly
    regarded by peers and co-workers. Technical proficiency in BSCS IX, Cognos, BMC
    Remedy, Tableau, Putty, Image Now, Rstudio, Oracle, MYSQL, Java, HTML, Python,
    Shell and Pearl.
    Areas of ExpertiseData Analysis &
    Visualization, Data Warehousing, Decision Modeling, Business Intelligence, Data &
    Statistical AnalysisOperations Management, Project Leadership, Reporting & Analysis, Client Management, Product Development,Change management
    ExperienceSenior Software Engineer,2004to2011The Hartford–Peace Dale,RI,Analyzed... Mada is a startup powering inspired shopping experiences. Our A.I.-based marketplace app, The Mada App, uses patented technology to recommend personalized and shoppable outfits for each user. Dubbed Tinder for Outfits, the app curates millions of products from thousands of brands and retailers, like Revolve, Bloomingdale's, Shopbop, Urban Outfitters, and more, to revolutionize the way Gen Z shops. Now, we are working with some of the worlds largest brands on a new venture, and are looking for an uber-talented full stack developer to join our team.
    As a Software Development Engineer for Mada, you will be at the forefront of our product development, contributing to both the front-end and back-end aspects of our applications. You will work collaboratively with a multidisciplinary team to design, develop, and deploy robust and scalable solutions. Your responsibilities will include:
    iOS Application Development (Cordova & JavaScript):Design, develop, and maintain iOS applications using the C...
    Professional ProfileExpert in Functional Testing .6-Year Record of Proven ResultsSenior software QA testerwith full system development life cycle experience, including designing, developing and implementing test plans, high level calendar test cases and test processes with attention to detail resulting in high quality Change Request and production change implementationsHands-on technology professionalaccustomed to working in complex, project-based environments. Multifaceted experience in QA software testing, system testing, user-acceptance testing and production certification testing.Backed by strong credentialsincluding a Bachelor's degree, certificate in business management and advanced command of various testing tools, agile methodologies and cross-platform skills in Windows, and Unix.
    Summary of SkillsTest Plans, Cases & ProcessesFunctional RequirementsDocumentationScrum/Agile MethodologiesUI & Compatibility TestingTest strategiesDefect / Bug TrackingUAT and System TestingTesting A... Job Description
    As a Principal Software Engineer, you will be responsible for helping design, build, test, deploy and operate highly scalable solutions for the canonical asset management system for all of Oracles next generation Cloud Infrastructure. You should be a rock-solid coder, and a distributed systems generalist who can dive deep into any part of the stack and low-level systems and design broad distributed system interactions. Your passion for excellence combined with your experience will help you be an outstanding technical contributor but also help you mentor more junior engineers. You should be able to work independently and as part of a team in an Agile environment. You should be an expert communicator to both technical and non-technical stakeholders in multiple locations around the globe. You should also be able to manage multiple projects and priorities in a fast-paced environment, be results-driven, and thrive even when faced with ambiguity and uncertainty. Most importan...
  • Loss: MultipleNegativesRankingLoss with these parameters:
    {
        "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: 16
  • num_train_epochs: 1
  • learning_rate: 2e-05
  • warmup_steps: 19
  • bf16: True

All Hyperparameters

Click to expand
  • per_device_train_batch_size: 16
  • num_train_epochs: 1
  • max_steps: -1
  • learning_rate: 2e-05
  • lr_scheduler_type: linear
  • lr_scheduler_kwargs: None
  • warmup_steps: 19
  • optim: adamw_torch_fused
  • optim_args: None
  • weight_decay: 0.0
  • adam_beta1: 0.9
  • adam_beta2: 0.999
  • adam_epsilon: 1e-08
  • optim_target_modules: None
  • gradient_accumulation_steps: 1
  • average_tokens_across_devices: True
  • max_grad_norm: 1.0
  • label_smoothing_factor: 0.0
  • bf16: True
  • fp16: False
  • bf16_full_eval: False
  • fp16_full_eval: False
  • tf32: None
  • gradient_checkpointing: False
  • gradient_checkpointing_kwargs: None
  • torch_compile: False
  • torch_compile_backend: None
  • torch_compile_mode: None
  • use_liger_kernel: False
  • liger_kernel_config: None
  • use_cache: False
  • neftune_noise_alpha: None
  • torch_empty_cache_steps: None
  • auto_find_batch_size: False
  • log_on_each_node: True
  • logging_nan_inf_filter: True
  • include_num_input_tokens_seen: no
  • log_level: passive
  • log_level_replica: warning
  • disable_tqdm: False
  • project: huggingface
  • trackio_space_id: None
  • trackio_bucket_id: None
  • trackio_static_space_id: None
  • 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: False
  • 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_static_graph: None
  • 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: {}

Training Logs

Epoch Step Training Loss
0.2577 50 2.2187
0.5155 100 1.9433
0.7732 150 1.9014

Training Time

  • Training: 25.1 seconds

Framework Versions

  • Python: 3.14.3
  • Sentence Transformers: 5.4.1
  • Transformers: 5.8.0
  • PyTorch: 2.11.0+cu128
  • Accelerate: 1.14.0
  • Datasets: 4.8.5
  • Tokenizers: 0.22.2

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{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},
}
Downloads last month
51
Safetensors
Model size
33.4M params
Tensor type
F32
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for g-tertho/cv-matcher-confit

Finetuned
(379)
this model

Papers for g-tertho/cv-matcher-confit