ai-recruitment-embedder

SentenceTransformer based on bkai-foundation-models/vietnamese-bi-encoder

This is a sentence-transformers model finetuned from bkai-foundation-models/vietnamese-bi-encoder. It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for retrieval.

Model Details

Model Description

• Model Type: Sentence Transformer
• Base model: bkai-foundation-models/vietnamese-bi-encoder <!-- at revision 84f9d9ada0d1a3c37557398b9ae9fcedcdf40be0 -->
• Maximum Sequence Length: 256 tokens
• Output Dimensionality: 768 dimensions
• Similarity Function: Cosine Similarity
• Supported Modality: Text

<!-- - **Training Dataset:** Unknown --> <!-- - **Language:** Unknown --> <!-- - **License:** Unknown -->

Model Sources

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

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': 'RobertaModel'})
  (1): Pooling({'embedding_dimension': 768, '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 = [
    'Chúng tôi cần một chuyên viên hành chính có tư duy logic và kỹ năng tin học văn phòng thành thạo để điều phối lịch trình, quản lý dữ liệu và hỗ trợ công tác hậu cần cho ban lãnh đạo. Ứng viên sẽ đảm nhiệm việc giao tiếp với khách hàng, xử lý chứng từ kế toán sơ bộ và tổ chức các buổi đào tạo nội bộ một cách chuyên nghiệp. Người đảm nhận vị trí này cần có khả năng chịu áp lực cao, kỹ năng giải quyết vấn đề linh hoạt và kinh nghiệm vận hành quy trình văn phòng bài bản trong hơn một thập kỷ.',
    'TEACHER Professional Summary Highly organized and detail-oriented Administrative Professional with more than 10 years experience supplying thorough, organized administrative support to senior executives. Skills Filing and data archiving, Employee training and development, Critical thinker, Microsoft Office (Excel, Publisher, PowerPoint, Word), Multi-line phone proficiency, Advanced clerical knowledge, Invoice processing, Accounting familiarity, Appointment setting, Social media knowledge, Works well under pressure, Excellent planner and coordinator, Accurate and detailed, Customer service-oriented, Articulate and well-spoken, Database management, Teaching/tutoring, Technological instruction, Effective time management Work History Teacher 08/2013 to Current Company Name – City , State Develop and implement engaging, effective, student-centered lessons in Reading, Phonics, Math, Science, Social Studies, Writing, and Language Arts. Use activities, songs/raps, and materials to enhance student learning and self-esteem. Create multi-sensory literacy and content based workstations. Conducted parent conferences, faculty and team meetings, Actively participated in activities which included: assessing student progress, assigning grades, taking attendance, recess duty, keeping parents/guardians informed through weekly progress reports/behavior charts, phone calls and email. Teacher Intern 01/2013 to 05/2013 Company Name – City , State Develop and implement engaging, effective, student-centered lessons in all subject areas for a diverse group of second grade special and regular education students. Use activities, songs, and materials to enhance student learning and self-esteem. Designed and implemented an interactive science unit on energy. Worked collaboratively with other teachers and professionals to create effective lessons that met the learning needs and abilities of all students. Legal Secretary/Office Manager 12/2011 to 12/2012 Company Name – City , State Managed office supplies, vendors, organization and upkeep. Screened applicant resumes and coordinated both phone and in-person interviews. Answered and managed incoming and outgoing calls while recording accurate messages. Contacted clients to schedule appointments and discuss the progress of cases. Worked as a team with attorneys, administrative assistants and fellow legal assistants. Entered new cases into company database. Developed, organized, and maintained filing and retrieval systems and files for court proceedings. Created, indexed and maintained client binders. Assisted attorneys in collecting information such as employment, medical and other records. Teller 08/2010 to 03/2011 Company Name – City , State Balanced daily cash deposits',
    'MARKET CONSULTANT - HEALTHCARE ADVOCATE Professional Summary Ambitious and dedicated managed care professional with robust organizational, communication and customer service skills. Multi-disciplinary industry expertise with an emphasis in provider outreach, research\\analysis and data integrity. Seeking a position to partake in new and innovative improvement processes and proactive provider education efforts. Education and Training BBA : Business Administration Human Resources Management University of New Mexico － City , State Business Administration Human Resources Management Skill Highlights Government relations knowledge Provider education and communication Personal and professional integrity Database management Relationship and team building Organizational planning Sound decision making Excellent research skills Claims analysis and review specialist Project management Professional Affiliations Member of Alpha Chi Omega Sorority Professional Experience Market Consultant - Healthcare Advocate August 2015 to Current Company Name － City , State Provides in the field market by market strategy, expertise, & execution on Risk Adjustment & Clinical Quality Programs (HEDIS/Stars) prospective and retrospective programs for Providers. Acts as a designated resource for the Provider group to gain engagement. Performs data analytics to help identify high risk members and to develop a strategy and plan for the practice. Consults to help improve coding accuracy, documentation and management of patient assessment information. Facilitates access to medical records for chart review purposes. Utilizes programs such as SalesForce, Tableau, Concur, and SharePoint to track various activities and reporting. Provider Network Specialist February 2014 to August 2015 Company Name － City , State Supported contracting efforts to "close the pricing gap" for both the Blue Community HMO and Blue Advantage HMO networks for the health insurance exchange, along with involvement in the beginning stages of additional exchange network implementations for 2015. Validated designations for all Essential Community Providers contracted with both exchange HMO lines of business. Strengthened and maintained provider relationships located within the Northeast region of New Mexico, including the Taos PHO and La Vida IPA. Audited monthly rosters received from the Taos PHO and La Vida IPA to insure correct system representation within PPW and Provider Finder. Validated credentialing status, network and pricing links utilizing Vistar, PPW, Legacy Premier and Premier Pricing.',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 768]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities)
# tensor([[1.0000, 0.5265, 0.2838],
#         [0.5265, 1.0000, 0.5863],
#         [0.2838, 0.5863, 1.0000]])

<!-- ### Direct Usage (Transformers) <details><summary>Click to see the direct usage in Transformers</summary> </details> --> <!-- ### Downstream Usage (Sentence Transformers) You can finetune this model on your own dataset. <details><summary>Click to expand</summary> </details> --> <!-- ### Out-of-Scope Use *List how the model may foreseeably be misused and address what users ought not to do with the model.* --> <!-- ## Bias, Risks and Limitations *What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.* --> <!-- ### Recommendations *What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.* -->

Training Details

Training Dataset

Unnamed Dataset

• Size: 1,031 training samples
• Columns: <code>sentence_0</code> and <code>sentence_1</code>
• Approximate statistics based on the first 100 samples:

  	sentence_0	sentence_1
  type	string	string
  modality	text	text
  details	<ul><li>min: 102 tokens</li><li>mean: 126.77 tokens</li><li>max: 172 tokens</li></ul>	<ul><li>min: 256 tokens</li><li>mean: 256.0 tokens</li><li>max: 256 tokens</li></ul>

• Samples:

  sentence_0	sentence_1
  <code>Tìm kiếm một nhân viên kho năng nổ, có khả năng vận hành thiết bị nâng hạ và tuân thủ nghiêm ngặt các quy chuẩn an toàn lao động. Vị trí này đòi hỏi sự tỉ mỉ trong việc quản lý hàng hóa, sắp xếp tồn kho và phối hợp nhịp nhàng cùng tập thể để tối ưu hóa trải nghiệm khách hàng. Ưu tiên những cá nhân có thể lực tốt, thích ứng nhanh với môi trường bán lẻ tốc độ cao và chịu được áp lực công việc lớn. Ứng viên cần sở hữu kỹ năng giao tiếp tốt, tính kỷ luật cao và thái độ phục vụ tận tâm để góp phần thúc đẩy sự phát triển chung của doanh nghiệp.</code>	<code>AIRCRAFT HYDRAULICS JOURNYMAN Summary Seeking a position as a Stocker/Receiver for Paris Walmart Super Center. Adaptive team player with the ability to take and follow orders as well as take on other responsibilities as needed. Strongly committed to enhancing customer experience and boosting company success. Highlights Friendly professional demeanor Safety awareness Well-organized Detail oriented Adaptive hands-on learner JLG manlift operations Hands-on experience with CAM software Interpersonal, written, and verbal communication Works well independently or with team Company confidentiality Capable of heavy lifting Experience Home Health Care Provider , 07/2019 to 02/2020 Company Name - City , State Worked to improve and enhance client lives through effective and compassionate care Assisted residents with bathing, dressing, grooming, feeding, lifting and transferring Provided clients with assistance in completing such tasks as purchasing supplies, paying bills and bookkeeping, effectiv...</code>
  <code>Chúng tôi đang tìm kiếm một Trợ lý điều hành kiêm nhân sự để chịu trách nhiệm quản trị công việc văn phòng, hỗ trợ lịch trình cho ban lãnh đạo và theo dõi các hoạt động liên quan đến tiền lương cũng như dữ liệu nhân sự. Ứng viên sẽ trực tiếp điều phối quy trình tiếp nhận nhân sự mới, lưu trữ hồ sơ bảo mật và duy trì hệ thống dữ liệu vận hành nội bộ. Bạn cần thành thạo các ứng dụng tin học văn phòng cùng các phần mềm quản trị doanh nghiệp để tối ưu hóa công tác điều hành và báo cáo định kỳ.</code>	<code>EXECUTIVE ASSISTANT HR Summary Skillful and dedicated Executive Assistant with extensive experience in the coordination, planning and support of daily operational and administrative functions in a highly confidential environment. Focused, results-driven professional looking to obtain a career oriented administrative position with Newark CEDC. Office Management Calendar Management Policies & Procedures Manuals Report & Document Preparation Spreadsheet & Database Creation Bookkeeping & Payroll Records Management Meeting & Event Planning Facility Management Highlights Word, Excel, Access, PowerPoint, SAP, Lotus Notes, Oracle Experience Executive Assistant HR 01/2014 to Current Company Name City , State Providing administrative support to President of home-care service provider to the Developmentally Disable population. Maintain calendar, process requisitions, and organize company meetings. Administer pre-employment training and testing. Mange bi-weekly payroll for 100 employees Maintain s...</code>
  <code>Doanh nghiệp đang tìm kiếm một Nhà nghiên cứu công nghệ sinh học phụ trách thiết kế và thực hiện các thí nghiệm sinh học phân tử, nuôi cấy vi sinh vật và phân tích dữ liệu chuyên sâu. Ứng viên sẽ chịu trách nhiệm tối ưu hóa quy trình sản xuất sinh học, vận hành các thiết bị phòng thí nghiệm tiên tiến và làm chủ các công cụ mô phỏng số liệu. Vị trí này đòi hỏi tư duy logic nhạy bén, khả năng tự chủ cao trong công việc cùng năng lực dẫn dắt các dự án nghiên cứu khoa học đột phá.</code>	<code>RESEARCH SCIENTIST Summary Highly motivated Research Scientist possessing proficiency in numerous disciplines of the biotechnology and in-vitro diagnostic ( IVD ) industry. Self starter •knowledgeable •analytical •decision maker •effective natural leader Adaptable, Analytical, Dedicated, Driven, Effective, Focused, Hardworking, Highly motivated, Innovative Meticulous, Multi-task-oriented, Organized, Outstanding, Performance driven, Personable, Pragmatic, Proactive, Productive, Proficient, Skilled, Versatile Highlights EndNote, Softmax Pro, MS-Office Suite ( Excel, PowerPoint & Word ), C/C++, Windows & Mac OS. Accomplishments To Discover and Characterize Epigenetic Modifications of Chromatin That Can Affect Organismal Lifespan (2012) Carried out reverse genetic screen to identify mutations in Histone H3 & H4 that might affect yeast growth in varying nutrient conditions. Identified a histone acetyl transferase, SAS2 that modifies H3K14A under nutrient stress based on microarray analysis ...</code>

• Loss: <code>MultipleNegativesRankingLoss</code> 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
• per_device_eval_batch_size: 16
• multi_dataset_batch_sampler: round_robin

All Hyperparameters

<details><summary>Click to expand</summary>

• per_device_train_batch_size: 16
• num_train_epochs: 1
• max_steps: -1
• learning_rate: 5e-05
• lr_scheduler_type: linear
• lr_scheduler_kwargs: None
• warmup_steps: 0
• 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
• label_smoothing_factor: 0.0
• bf16: False
• 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: 16
• 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: None
• fsdp_config: None
• 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: round_robin
• router_mapping: {}
• learning_rate_mapping: {}

</details>

Training Time

• Training: 1.4 minutes

Framework Versions

• Python: 3.12.13
• Sentence Transformers: 5.6.0
• Transformers: 5.13.1
• PyTorch: 2.11.0+cu128
• Accelerate: 1.14.0
• Datasets: 4.0.0
• 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},
}

<!-- ## 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.* -->