leodellosa85/cv-matching-triplet-model

SentenceTransformer based on sentence-transformers/all-MiniLM-L6-v2

This is a sentence-transformers model finetuned from sentence-transformers/all-MiniLM-L6-v2. 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: sentence-transformers/all-MiniLM-L6-v2
• Maximum Sequence Length: 256 tokens
• Output Dimensionality: 384 dimensions
• 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': 256, 'do_lower_case': False, 'architecture': 'BertModel'})
  (1): Pooling({'word_embedding_dimension': 384, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, '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 = [
    'i.t. skills windows xp, ms office (word, excel: look-ups; pivot table; other basic functions ; power point) saral payment package- payroll software internet applicationseducation details january 2006 bachelor in hospitality management international hospitality management queen margaret university edinburg january 2006 diploma hotel management international institute of hotel management hr skill details hr management- exprience - less than 1 year monthscompany details company - atri developers description - hr payroll statutory compliance performance management company - description - employee relations and administration: creating industry specific policies, procedure, forms, formats, letters, checklists etc payroll management: salary restructuring to process payroll of 600 employees. validation of all input (attendance, leaves, and salaries) before starting salary process. processing accurate & error free salary of employees. responsible for compensation and benefits administration. coordinate with accounts team for salary processing. attendance & leave record management assuring prompt and satisfactory resolution of payroll related queries of all employees. statutory compliance management: manage various statutory compliance requirements (pf, esic, pt, gratuity, tds etc calculations, deduction, payment and return filing. generate statutory reports like form 16, form 24q. conducting session with employees on statutory policies and procedure, compliance related topics. shops and commercial establishments act (s&e) the payment of gratuity act 1972 recruitment and selection: handling recruitment like job posting in naukri portal and coordination. create annual manpower plan and budget. screen and schedule preliminary interview. arrange for employee orientation. handling joining formalities and salary account opening formalities. performance management: end to end facilitation of pms starting from creating job description & appraisal forms to disbursement of letters. kra setting, mid-year reviews, annual reviews, handling all appraisal activities (360 degree) training and development: conduct training need analysis and arrange various training session. employee engagement and employee welfare: creation and deployment of sales rewards and recognition schemes, periodic interactive sessions like monthly birthday celebration, annual day, diwali dhamaka, offsite etc. working on saral payment package- payroll software as well as on excel assisting md in hr works, offering suggestions and answering employee queries on payroll compliance related issues, other benefits (insurance, medical, reimbursement, ), full & final settlement of resigned employees.',
    'education details june 2012 to may 2015 b.a economics chennai, tamil nadu sdnbvc hr skill details company details company - anything it solution description - hr',
    'it skills languages: c (basic), java (basic) web technologies: html5, css3, bootstrap, javascript, jquery, corel draw, photoshop, illustrator databases: mysql5.0 ide & tools: sublime text, notepad operating systems: windows xp, windows 7education details september 2015 bachelor of engineer information technology nagpur, maharashtra nagpur university may 2011 hsc secondary & higher secondary state board of secondary june 2009 ssc secondary & higher secondary maharashtra state board of secondary web and graphics designer web and graphics designer - virtuous media point, pune skill details bootstrap- exprience - 24 months html5- exprience - 24 months javascript- exprience - 24 months jquery- exprience - 24 months corel draw- exprience - 24 months adobe photoshop- exprience - 24 months adobe illustrator- exprience - 12 months css3- exprience - 24 monthscompany details company - virtuous media point description - company - cnc web world description - internship program: at e-sense it solution pvt.ltd. nagpur as a web designing and developement. * presented in project competition in innovesta 15 of priyadarshini indira gandhi college of engineering, nagpur. * presented in national level paper presentation in tech-wave 2015 of s.r.m.c.e., nagpur. company - e-sense it solution pvt.ltd description - key result areas: * designed websites solutions by studying information needs, conferring with users, and studying systems flow, data usage, and work processes. * understood process requirements and provided use cases for business, functional & technical requirements. * interacted with users for requirement gathering, prepared functional specifications and low-level design documents. * participated in the software development life cycle (sdlc) and agile methodology right from requirement analysis, * performed detailed design of modules along with their implementation, and documentation integrated software modules developed by other team members. highlights: * developed various modules as per customer requirement and identified and fixed number of bugs related to code, database connectivity, ui defects and so on. * analyzed and modified existing codes to incorporate a number of changes in the application / user requirements, wrote new codes as required. * coded, implemented and integrated complex programs using technologies such as html5, css3, javascript, jquery, bootstrap. * having good command on graphics designing with effective ideas. projects * www.nitka.com, nagpur united corporation (admin), mintmetrix.com, tagline videos (admin), smartbadge (admin): - in all projects i have used technologies like html5, css3, bootstrap, javascript, jquery and text editor as sublime text. * www.shreekiaspack.co.in, www.3staragroproducts.com, www.luckystationery.co.in: - used technologies like html5, css3, bootstrap, javascript and text editor as notepad++. * design various logos, brochures, advertising banners, visiting cards, pamphlet, hoardings etc. b.e. final year project * major project: - title: web based disease diagnosis expert system. duration: 1 year description: in this project we provide a website in which doctor gives online consultation for particular disease. system gives better suggestions for any health problems. * mini project development- * shopping management system developed in c++. curriculum & extra curriculum activities company - face-it description - co-ordinator in project competition.',
]
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, 0.9921, 0.9968],
#         [0.9921, 1.0000, 0.9918],
#         [0.9968, 0.9918, 1.0000]])

Training Details

Training Dataset

Unnamed Dataset

• Size: 962 training samples
• Columns: sentence_0, sentence_1, and sentence_2
• Approximate statistics based on the first 962 samples:

  	sentence_0	sentence_1	sentence_2
  type	string	string	string
  details	min: 24 tokens mean: 225.96 tokens max: 256 tokens	min: 24 tokens mean: 224.84 tokens max: 256 tokens	min: 24 tokens mean: 224.32 tokens max: 256 tokens

• Samples:

  sentence_0	sentence_1	sentence_2
  technical skills: languages python python framework django, drf databases mysql, oracle, sqlite, mongodb web technologies css, html, restful web services rest methodologies agile, scrum version control github project managent tool jira operating systems window, unix education details be dr.bamu,aurangabad python developer python developer - arsys inovics pvt ltd skill details css- exprience - 31 months django- exprience - 31 months html- exprience - 31 months mysql- exprience - 31 months python- exprience - 31 months web services- exprience - less than 1 year months logger- exprience - less than 1 year months mongodb- exprience - less than 1 year months json- exprience - less than 1 year months unix- exprience - less than 1 year months rest- exprience - less than 1 year months sqlit3- exprience - less than 1 year monthscompany details company - arsys inovics pvt ltd description - project - f-mas (frequency monitoring and analysis systems - (f-mas)) f-mas is a project for managing netwo...	training attended: 1. successfully completed esd program conducted by zensar technologies, pune in 2017. 2. successfully completed employability training conducted by barclays, global talent track, and nasscom foundation in 2015. achievements: 1. treasurer in ieee student branch at jscoe, pune for 2017-18. 2. worked as team leader in college s various technical and cultural events from 2016 - 2017. 3. project idea got selected for final prototyping round in kpit-sparkle 2018, pune. 4. participated in avishkar 2017 conducted by savitribai phule pune university. 5. project idea submitted in accenture innovation 2018, pune. 6. brought sponsorship of rs. 15,000 from platinum auto (formerly royal enfield) in 2017, pune. 7. secured 1 st rank for college level competition of poster presentation on smart ambulance in 2017, pune. 8. organized ieee workshop on excellence in english and public speaking in 2017, pune workshops attended: 1. successfully completed 4 days workshop on medical iot cond...	education details electrical engineering skill details microsft office and excell, power point- exprience - 120 monthscompany details company - indian navy description - academia matric diploma in electrical engineering nuclear biological chemical defence and damage control including fire fighting leadership certificate course - 02 weeks management certificate course - 04 weeks advance fire fighting including industrial safety - 24 weeks
  social skills: ability to establish trust and work with a team. determined with good work ethics. ability to work under difficult situations.education details january 2011 to january 2016 mumbai, maharashtra mumbai university bachelor of electronics engineering electronics engineering mumbai, maharashtra atharva college of engineering at malad automation and electrical engineer automation and electrical engineer - smec automation pvt. ltd skill details company details company - smec automation pvt. ltd description - -18, supply, installation, testing and commissioning of water level sensor and valve actuators for water tanks at barc hospital anushaktinagar, trombay and barc facility at kalyan. implemented of academy projects like automatically tank filling with relay and float sensor level control, bottle filling on conveyor belt motion, and waste material crashing then separated on conveyor belt motion with plc controlling. role of automation and instrumentation engineer (marine and i...	technical skills automation testing selenium webdriver, testng. testing framework testng, data driven, page object model. applications & tools eclipse, postman building tool version control continuous integration maven svn jenkins database sql languages sql, java, c++ scripting languages html, javascript operating system windows domain insurance, erp, e-commerce education details january 2016 b.e. computer pune, maharashtra savitribai phule university of pune automation testing java developer and automationtesting skill details c++- exprience - 6 months database- exprience - 6 months eclipse- exprience - 6 months employee resource group- exprience - 6 months enterprise resource planning- exprience - 6 monthscompany details company - phioenix microsystem pvt.ltd. description - company - phioenix microsystem pvt.ltd. description - organization role phoenix microsystems pvt.ltd. jr. java developer projects project #1 project swb-ebs_support role java developer description inventory operat...	skills knows english as native speaker (ielts overall 8; listening 8, reading 8, writing 7 and speaking 8.5); hindi with bilingual proficiency and punjabi as native speaker. able to communicate clearly and concisely with people of diverse backgrounds and levels of authority. exceptional knowledge of administrative procedures, evidence rules and trials. can maintain a professional attitude with peers, co-workers and clients at all times. focused and driven to always meet deadlines for pretrial procedures, trials and appellate briefings by effectively utilizing resources. a microsoft certified systems engineer (2008) and very much competent in windows and word processing software education details july 2009 to may 2012 bachelor's laws bikaner, rajasthan maharaja ganga singh university august 2008 to november 2008 microsoft certified systems engineer networking chandigarh july 2005 to april 2008 bachelor's of science bio-informatics chandigarh, chandigarh panjab university advocate newcom...
  education details january 2016 bachelor of engineering lean projects mumbai, maharashtra mumbai university january 2013 diploma computer engineering ratnagiri, maharashtra maharashtra state board of technical education sap consultant sap consultant - quick learner skill details company details company - quick learner description - groomed skills with microsoft excel. job responsibilities: working on centralized sap security project which includes user vba programming for automation. level authorizations including role creation and changes. and compliance policy maintenance for sap systems. confidence and positive attitude. assisting users in troubleshooting and identifying authorization issues using su53 and trace analysis. willingness to learn & work in team. working on grc 10.x access control application and all its component. strong analytical thinking, documentation and design skills assisting in defining the scope of a project/opportunities, estimating efforts and project timeline...	competencies: sap business intelligence version sap bo 4.2 bo tools design studio, idt, webi, udt, cmc activities backend db hana, bw, bex queries, sqleducation details sap bo developer and sap hana developer sap bo developer - credit suisse skill details sap bi- exprience - 72 months cmc- exprience - 72 months hana- exprience - 36 months business intelligence- exprience - 72 months sql- exprience - 72 months sap bo- exprience - 72 monthscompany details company - accenture description - company accenture, pune environment sap bo 4.2, idt, hana views role sap bo developer and hana developer description: this project aims to provide reporting solution for swiss business users.the universe supports analyzing customer funds purchase order patterns and order lifecycle reporting. the purpose of reports is to provide an end-to-end view of the entire sales order transaction, and to track the investment orders in various funds, including the status of orders, order types along with the gross va...	education details january 2015 bachelor of engineering extc mumbai, maharashtra mumbai university january 2012 diploma industrial electronics vashi, maharashtra, in fr. agnel polytechnic etl developer etl developer skill details informatica- exprience - 36 monthscompany details company - blue shield of california description - duration: (mar 2016 - sept 2017) description: blue shield of california (bsc) is health plan provider. the intent of this project is to process feeds coming in and going out of bsc system related to eligibility, enrollment, and claims subject areas. all these feeds comes in different formats and are processed using informatica 9.6.1, oracle 11g, facets 5.0 &tidal. technical environment: etl tool (informatica power center 9.6.1), oracle 11g (sql, pl-sql), unix, facets, tidal, jira, putty. role: etl developer responsibilities: responsible for analyzing the business requirement document involved in development of informatica mappings using different transformations ...

• Loss: TripletLoss with these parameters:

  {
      "distance_metric": "TripletDistanceMetric.EUCLIDEAN",
      "triplet_margin": 5
  }
  

Training Hyperparameters

Non-Default Hyperparameters

• per_device_train_batch_size: 12
• per_device_eval_batch_size: 12
• multi_dataset_batch_sampler: round_robin

All Hyperparameters

Click to expand

• overwrite_output_dir: False
• do_predict: False
• eval_strategy: no
• prediction_loss_only: True
• per_device_train_batch_size: 12
• per_device_eval_batch_size: 12
• 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: 3
• 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
• 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}
• parallelism_config: None
• deepspeed: None
• label_smoothing_factor: 0.0
• optim: adamw_torch_fused
• optim_args: None
• adafactor: False
• group_by_length: False
• length_column_name: length
• project: huggingface
• trackio_space_id: trackio
• ddp_find_unused_parameters: None
• ddp_bucket_cap_mb: None
• ddp_broadcast_buffers: False
• dataloader_pin_memory: True
• dataloader_persistent_workers: False
• skip_memory_metrics: True
• use_legacy_prediction_loop: False
• push_to_hub: False
• resume_from_checkpoint: None
• hub_model_id: None
• hub_strategy: every_save
• hub_private_repo: None
• hub_always_push: False
• hub_revision: None
• gradient_checkpointing: False
• gradient_checkpointing_kwargs: None
• include_inputs_for_metrics: False
• include_for_metrics: []
• eval_do_concat_batches: True
• fp16_backend: auto
• push_to_hub_model_id: None
• push_to_hub_organization: None
• mp_parameters:
• auto_find_batch_size: False
• full_determinism: False
• torchdynamo: None
• ray_scope: last
• ddp_timeout: 1800
• torch_compile: False
• torch_compile_backend: None
• torch_compile_mode: None
• include_tokens_per_second: False
• include_num_input_tokens_seen: no
• neftune_noise_alpha: None
• optim_target_modules: None
• batch_eval_metrics: False
• eval_on_start: False
• use_liger_kernel: False
• liger_kernel_config: None
• eval_use_gather_object: False
• average_tokens_across_devices: True
• prompts: None
• batch_sampler: batch_sampler
• multi_dataset_batch_sampler: round_robin
• router_mapping: {}
• learning_rate_mapping: {}

Framework Versions

• Python: 3.12.12
• Sentence Transformers: 5.1.2
• Transformers: 4.57.1
• PyTorch: 2.8.0+cu126
• Accelerate: 1.11.0
• Datasets: 4.0.0
• Tokenizers: 0.22.1

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",
}

TripletLoss

@misc{hermans2017defense,
    title={In Defense of the Triplet Loss for Person Re-Identification},
    author={Alexander Hermans and Lucas Beyer and Bastian Leibe},
    year={2017},
    eprint={1703.07737},
    archivePrefix={arXiv},
    primaryClass={cs.CV}
}