OpenCV-finetuned

SentenceTransformer based on HZeroxium/paraphrase-multilingual-MiniLM-L12-v2-job-cv-multi-dataset

This is a sentence-transformers model finetuned from HZeroxium/paraphrase-multilingual-MiniLM-L12-v2-job-cv-multi-dataset. 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: HZeroxium/paraphrase-multilingual-MiniLM-L12-v2-job-cv-multi-dataset <!-- at revision ea93cb8ae081ad4ffd8154c2ca3518592984e86d -->
• Maximum Sequence Length: 350 tokens
• Output Dimensionality: 384 dimensions
• Similarity Function: Cosine Similarity

<!-- - **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({'max_seq_length': 350, 'do_lower_case': False}) with Transformer model: 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})
)

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 role of the sales associate in lids retail',
    'job description Generate Sales Produce sales gains, by providing customer service. To meet or exceed Company Objectives in all individual statistics. Learn to provide consistent, documented appraisal of an associate’s sales performance. Provide support by giving feedback on areas of strength and opportunity while keeping in line with Company Objectives. Adhere to current visual guidelines includes: proper merchandising, signage and store cleanliness. Maintain a professional appearance consistent with Company Dress Code Policy. Control Expenses Protect Company assets within guidelines of LIDS Retail policies. Assist in preparation of store work schedules that provide proper store coverage and are within the Company guidelines for wage control. Follow all policies to accurately manage store inventory including receiving, transferring, completing price change and conducting product counts. Complete accurate product counts in a consistent and timely manner. Perform proper documentation and record keeping per LIDS Retail policies as well as state and federal laws. Open and close the store as required following the procedures per the Operations P&P Manual. Supervise Associates Participate in LIDS Training Programs, adhere to set goals (for sales and tasks) and regular follow up. Assist in recruiting and training store personnel on proper store operations and procedures. Encourage store associates’ direct compliance of established company policies, procedures and guidelines including (but not limited to) safekeeping of company inventory, funds and property. Perform work of subordinates as needed. Communicate with employees at all levels of the company. Other duties as assigned. Requirements Education and/or Experience High school diploma or equivalent plus one year relative experience. Established ability to produce sales results while minimizing loss. Strong interpersonal skills and the ability to communicate verbally in a clear professional manner. Ability to operate a computer, as well as maneuver relative software programs. Ability to lift up to 50 pounds. Ability to climb a ladder and work with hands overhead. Standing required for up to 100% of the work time. Ability to work unsupervised.',
    'job description Generate Sales Produce sales gains, by providing customer service. Meet or Exceed Company Objectives in all measurable areas of the business. Provide consistent assessment of each associate’s sales performance and work within the store to give feedback on areas of strength and opportunity while keeping in line with Company objectives. Adhere to current visual guidelines including proper merchandising, signage and store cleanliness. Maintain strong product knowledge for use in selling, merchandising, and giving feedback as requested. Ensure that all associates maintain a professional appearance consistent with company dress code policy. Control Expenses Protect Company assets within guidelines of LIDS Retail policies. Prepare store schedules and provide for proper store coverage at all times, within the guidelines for wage control set by the company. Follow all policies to accurately manage store inventory including receiving, transferring, completing price changes and conducting product counts. Perform proper documentation and record keeping per LIDS Retail policies, complying with all state and federal laws. Open and close the store as required following the procedures per the Operations P&P Manual. Supervise Associates Manage store associates through thorough use of LIDS Training Programs, goal setting (for sales and tasks), and regular follow up. Recruit, develop, and train store personnel to achieve Operations Objectives as well as adhere to Operational policies and guidelines. Administer the progressive steps of discipline to include verbal and written warnings. In addition, the Store Manager carries out employment terminations following approval from the District Sales Manager and Human Resources. Encourage direct compliance of all store associates established company policies, procedures and guidelines including, but not limited to, safekeeping of company inventory, funds and property. Performs work of subordinates, as needed. Communicate with employees at all levels of the company. Other duties as assigned. Requirements Education and/or Experience Four-year degree from a college or university in business or a related field; or two-year degree and one year related experience; or equivalent combination of education and experience. Established ability to produce sales results, while minimizing loss. Proven supervisory skills, with capacity to deliver training material and assess retention. Strong interpersonal skills and the ability to communicate verbally in a clear and professional manner. Ability to operate a computer, as well as maneuver relative software programs. Ability to lift up to 50 pounds. Ability to climb a ladder and work with hands overhead. Standing required for up to 100% of the work time. Ability to work unsupervised. Ability and willingness to travel overnight for training and/or business meetings.',
]
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]

<!-- ### 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: 160,000 training samples
• Columns: <code>sentence_0</code>, <code>sentence_1</code>, <code>sentence_2</code>, and <code>label</code>
• Approximate statistics based on the first 1000 samples:

  	sentence_0	sentence_1	sentence_2	label
  type	string	string	string	float
  details	<ul><li>min: 4 tokens</li><li>mean: 10.78 tokens</li><li>max: 22 tokens</li></ul>	<ul><li>min: 183 tokens</li><li>mean: 347.5 tokens</li><li>max: 350 tokens</li></ul>	<ul><li>min: 125 tokens</li><li>mean: 345.31 tokens</li><li>max: 350 tokens</li></ul>	<ul><li>min: -13.0</li><li>mean: 6.32</li><li>max: 20.18</li></ul>

• Samples:

  sentence_0	sentence_1	sentence_2	label
  <code>von maur customer service responsibilities</code>	<code>job description Overview Von Maur was founded in 1872 with two simple goals – provide a wide selection of quality merchandise and establish excellent customer service principles by treating every customer like family. Since then, Von Maur has deliberately and steadily grown and expanded the variety of services offered to our customers. Our wide range of customer services include free delivery, complimentary gift wrapping, no questions asked customer return policy, alterations, and an interest free charge card. Today, 33 Von Maur stores are scattered across 15 states: Alabama, Georgia, Illinois, Indiana, Iowa, Kansas, Kentucky, Michigan, Minnesota, Missouri, Nebraska, New York, Ohio, Oklahoma and Wisconsin; and we’re still expanding. Our corporate headquarters and e-commerce facility are located in Davenport, Iowa. The integrity and values that have pleased our customers for generations also make Von Maur a wonderful place to work. We value the diversity of our employees and each associ...</code>	<code>job description Date: August 19, 2019 Job Status: Non-Exempt; Full Time Position Title: Customer Service Representative Supervision Received: Position reports to the Location Manager Supervisory Responsibilities: None Job Summary: A CSR interacts directly with new and existing customers to establish and maintain relationships. Customers look to our Customer Service Representatives to assist them with issues and/or place them into the accounts that best suit their needs. CSRs respond to customer inquiries via telephone and face-to-face meetings. Will be required to work into a Saturday rotation. Essential Functions, Duties and Responsibilities include, but are not limited to: Open new accounts for existing and new customers Assist customers with routine account related requests such as: Funds transfers Stop payments Inquiries about ATM and Debit Card usage and limits Inquiries about checking and savings account transactions Inquiries about bank deposit products and service charges Inqui...</code>	<code>10.52873420715332</code>
  <code>what skills to include when enacting a software solution architect</code>	<code>job description AllyO tackles workplace engagement challenges with candidates and employees, from hi to goodbye, using AI for end-to-end HR management solutions. We strive to disrupt how HR is traditionally run, do yourself a favor and text “hello” to 650-297-8805 to be part of this movement. You’re probably wondering if you should text or not. You should. Why? 1. It is AllyO’s product. It is the company you are applying to and you should know our product. 2. It’s not sketchy and we won’t spam text or call you - unless you want us to. 3. We live in a society where we want things instantaneously. Find out if you qualify within minutes and have the opportunity to schedule your own phone interview. 4. Nothing confusing, just text “hello” to 650-297-8805 and see how easy it is to apply. The Solutions Architect is a critical position that has 7 major components at AllyO: 1. Product knowledge: A solutions architect acquires and continuously learns deep product knowledge to creatively solve c...</code>	<code>job description Language Required English Responsibilities The Solutions Architect advises customers, partners and channel partners how to build and implement strategic solutions on a complex scale. Additionally, the Solutions Architect acts as a conduit between the field systems engineering team and Veeam cross-functional product groups. This senior technical role is heavily involved in application virtualization, storage, and multi-cloud infrastructures. The position has a focus on designing availability solutions, including data protection and monitoring using Veeam products. The Solutions Architect also serves as an escalation point for partner solutions as well as the Pre-Sales Organization. The National Solutions Architect – Enterprise Applications position will be responsible for thoroughly understanding the unique challenges of the largest organizations and be able to position and successfully architect appropriate Veeam solutions in these complex / demanding environments. The ...</code>	<code>-1.6041113138198853</code>
  <code>what is the role of an identity specialist on thycotic</code>	<code>job description Are you interested in working in a dynamic environment that offers opportunities for professional growth and new responsibilities? If so, Deloitte & Touche LLP could be the place for you. This is an unparalleled time of change with new information security challenges arising each day. Our team of Cyber risk professionals bring industry experience, confidence, and technical knowledge to help our clients tackle those unique challenges. Identity and Access Management (IAM) solutions leverage Deloitte’s IAM Methods 2.0 methodology to help clients control which employees, customers, partners and suppliers access sensitive corporate resources, and streamline the process of managing the explosion in “digital identities.” Work you’ll do As Identity and Access Management (IAM) solutions team Senior Consultant, you will: Demonstrate advanced understanding of business processes, internal control risk management, IT controls and related standards Identify and evaluate complex b...</code>	<code>job description RMSI is the leading professional retail merchandising company in the US with over 12,000 employees and growing every day. Our company success is attributed to hard-working associates who value honesty, integrity, pride and commitment to quality and service. Join our company and be a part of our winning team! We currently have an opening for a full-time Schematic Analyst. The Schematic Analyst is responsible for the creation and maintenance of product shelf schematics through software programs for selected categories. What does a Schematic Analyst do? Create, revise and maintain schematics/product placement for multiple categories Collaboration/working with the Sales Management teams on a daily basis. Responsible for driving timeline deliverables according to timelines for schematic execution. Responsible for creating reports to validate schematic accuracy. Facilitate communication between Marketing Department and Retail Operations. Ensure approved. criteria and best pra...</code>	<code>3.4105067253112793</code>

• Loss: <code>gpl.toolkit.loss.MarginDistillationLoss</code>

Training Hyperparameters

Non-Default Hyperparameters

• per_device_train_batch_size: 32
• per_device_eval_batch_size: 32
• num_train_epochs: 1
• max_steps: 250
• fp16: True
• multi_dataset_batch_sampler: round_robin

All Hyperparameters

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

• overwrite_output_dir: False
• do_predict: False
• eval_strategy: no
• prediction_loss_only: True
• per_device_train_batch_size: 32
• per_device_eval_batch_size: 32
• 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: 1
• max_steps: 250
• 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: True
• 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
• prompts: None
• batch_sampler: batch_sampler
• multi_dataset_batch_sampler: round_robin

</details>

Framework Versions

• Python: 3.10.12
• Sentence Transformers: 3.3.1
• Transformers: 4.45.2
• PyTorch: 2.5.1+cu124
• 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",
}

<!-- ## 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.* -->