hetbhagatji09/cs-job-resume-model

SentenceTransformer based on sentence-transformers/all-mpnet-base-v2

This is a sentence-transformers model finetuned from sentence-transformers/all-mpnet-base-v2 on the job-resume-embedding-finetuning dataset. It maps sentences & paragraphs to a 768-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-mpnet-base-v2
• Maximum Sequence Length: 384 tokens
• Output Dimensionality: 768 dimensions
• Similarity Function: Cosine Similarity
• Training Dataset:
  • job-resume-embedding-finetuning

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': 384, 'do_lower_case': False, 'architecture': 'MPNetModel'})
  (1): Pooling({'word_embedding_dimension': 768, '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("hetbhagatji09/cs-job-resume-model")
# Run inference
queries = [
    "Full Stack Engineer required. We are looking for an engineer with 1+ years of experience. Responsibilities include building and maintaining systems using Python, Express, React, JavaScript. Familiarity with Unit Testing, Agile is a plus. Experience with scalable systems and good engineering practices required.Python;Express;React;JavaScript",
]
documents = [
    'Summary: 5+ years experience. Skills: Express, CI/CD, React, JavaScript, Git, APIs. Projects: Worked on a project that implemented Express and CI/CD to deliver production-ready features, collaborated in Agile teams. Experience: 5 years developing systems using Express, CI/CD, React, JavaScript.Express;CI/CD;React;JavaScript',
    'Summary: Experience in Android Studio, Kotlin, Java and related tools.Android Studio;Kotlin;Java',
    'Summary: 6+ years experience. Skills: SASS, TypeScript, Tailwind, JavaScript, REST, APIs. Projects: Worked on a project that implemented SASS and TypeScript to deliver production-ready features, collaborated in Agile teams. Experience: 6 years developing systems using SASS, TypeScript, Tailwind, JavaScript.SASS;TypeScript;Tailwind;JavaScript',
]
query_embeddings = model.encode_query(queries)
document_embeddings = model.encode_document(documents)
print(query_embeddings.shape, document_embeddings.shape)
# [1, 768] [3, 768]

# Get the similarity scores for the embeddings
similarities = model.similarity(query_embeddings, document_embeddings)
print(similarities)
# tensor([[0.7931, 0.3914, 0.7911]])

Evaluation

Metrics

Triplet

• Datasets: ai-job-validation and ai-job-test
• Evaluated with TripletEvaluator

Metric	ai-job-validation	ai-job-test
cosine_accuracy	0.75	0.7333

Training Details

Training Dataset

job-resume-embedding-finetuning

• Dataset: job-resume-embedding-finetuning at d15c797
• Size: 480 training samples
• Columns: query, job_description_pos, and job_description_neg
• Approximate statistics based on the first 480 samples:

  	query	job_description_pos	job_description_neg
  type	string	string	string
  details	min: 33 tokens mean: 67.54 tokens max: 85 tokens	min: 22 tokens mean: 76.39 tokens max: 113 tokens	min: 22 tokens mean: 76.92 tokens max: 113 tokens

• Samples:

  query	job_description_pos	job_description_neg
  Frontend Developer required. We are looking for an engineer with 5+ years of experience. Responsibilities include building and maintaining systems using CSS, SASS, Tailwind, React. Familiarity with APIs, Unit Testing is a plus. Experience with scalable systems and good engineering practices required.CSS;SASS;Tailwind;React	Summary: 2+ years experience. Skills: Flutter, Kotlin, REST APIs, iOS SDK, TDD, APIs. Projects: Worked on a project that implemented Flutter and Kotlin to deliver production-ready features, collaborated in Agile teams. Experience: 2 years developing systems using Flutter, Kotlin, REST APIs, iOS SDK.Flutter;Kotlin;REST APIs;iOS SDK	Summary: 2+ years experience. Skills: Spark, NumPy, ETL, PyTorch, Agile, Linux. Projects: Worked on a project that implemented Spark and NumPy to deliver production-ready features, collaborated in Agile teams. Experience: 2 years developing systems using Spark, NumPy, ETL, PyTorch.Spark;NumPy;ETL;PyTorch
  React Native Developer required. We are looking for an engineer with 4+ years of experience. Responsibilities include building and maintaining systems using Flutter, Android SDK, Objective-C, Kotlin. Familiarity with Unit Testing, REST is a plus. Experience with scalable systems and good engineering practices required.Flutter;Android SDK;Objective-C;Kotlin	Summary: 5+ years experience. Skills: Prometheus, Jenkins, CI/CD, Terraform, Git, CI/CD. Projects: Worked on a project that implemented Prometheus and Jenkins to deliver production-ready features, collaborated in Agile teams. Experience: 5 years developing systems using Prometheus, Jenkins, CI/CD, Terraform.Prometheus;Jenkins;CI/CD;Terraform	Summary: 5+ years experience. Skills: Flask, REST APIs, Python, SQL, Unit Testing, TDD. Projects: Worked on a project that implemented Flask and REST APIs to deliver production-ready features, collaborated in Agile teams. Experience: 5 years developing systems using Flask, REST APIs, Python, SQL.Flask;REST APIs;Python;SQL
  Data Analyst required. Looking for expertise in SQL, PowerBI, Excel, Visualization, ETL.SQL;PowerBI;Excel;Visualization;ETL	Summary: Experience in PowerBI, Excel, Visualization and related tools.PowerBI;Excel;Visualization	Summary: 1+ years experience. Skills: Docker, MySQL, Django, Kubernetes, TDD, Agile. Projects: Worked on a project that implemented Docker and MySQL to deliver production-ready features, collaborated in Agile teams. Experience: 1 years developing systems using Docker, MySQL, Django, Kubernetes.Docker;MySQL;Django;Kubernetes

• Loss: MultipleNegativesRankingLoss with these parameters:

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

Evaluation Dataset

job-resume-embedding-finetuning

• Dataset: job-resume-embedding-finetuning at d15c797
• Size: 60 evaluation samples
• Columns: query, job_description_pos, and job_description_neg
• Approximate statistics based on the first 60 samples:

  	query	job_description_pos	job_description_neg
  type	string	string	string
  details	min: 33 tokens mean: 68.63 tokens max: 83 tokens	min: 22 tokens mean: 77.83 tokens max: 105 tokens	min: 22 tokens mean: 76.6 tokens max: 100 tokens

• Samples:

  query	job_description_pos	job_description_neg
  JavaScript Engineer required. We are looking for an engineer with 3+ years of experience. Responsibilities include building and maintaining systems using HTML, React, CSS, JavaScript. Familiarity with APIs, REST is a plus. Experience with scalable systems and good engineering practices required.HTML;React;CSS;JavaScript	Summary: 7+ years experience. Skills: React, Babel, HTML, Tailwind, Git, TDD. Projects: Worked on a project that implemented React and Babel to deliver production-ready features, collaborated in Agile teams. Experience: 7 years developing systems using React, Babel, HTML, Tailwind.React;Babel;HTML;Tailwind	Summary: 7+ years experience. Skills: Flask, Python, Django, PostgreSQL, APIs, Linux. Projects: Worked on a project that implemented Flask and Python to deliver production-ready features, collaborated in Agile teams. Experience: 7 years developing systems using Flask, Python, Django, PostgreSQL.Flask;Python;Django;PostgreSQL
  Android Developer required. Looking for expertise in Kotlin, Java, Android Studio, XML, Jetpack.Kotlin;Java;Android Studio;XML;Jetpack	Summary: Experience in Jetpack, XML, Android Studio and related tools.Jetpack;XML;Android Studio	Summary: 3+ years experience. Skills: Node.js, Python, PostgreSQL, Docker, Git, REST. Projects: Worked on a project that implemented Node.js and Python to deliver production-ready features, collaborated in Agile teams. Experience: 3 years developing systems using Node.js, Python, PostgreSQL, Docker.Node.js;Python;PostgreSQL;Docker
  Backend Developer required. Looking for expertise in Python, Django, REST APIs, Databases, Caching.Python;Django;REST APIs;Databases;Caching	Summary: Experience in Django, Caching, Databases and related tools.Django;Caching;Databases	Summary: 2+ years experience. Skills: Grafana, AWS, Docker, CI/CD, CI/CD, Linux. Projects: Worked on a project that implemented Grafana and AWS to deliver production-ready features, collaborated in Agile teams. Experience: 2 years developing systems using Grafana, AWS, Docker, CI/CD.Grafana;AWS;Docker;CI/CD

• Loss: MultipleNegativesRankingLoss with these parameters:

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

Training Hyperparameters

Non-Default Hyperparameters

• eval_strategy: steps
• per_device_train_batch_size: 16
• per_device_eval_batch_size: 16
• learning_rate: 2e-05
• num_train_epochs: 1
• warmup_ratio: 0.1
• batch_sampler: no_duplicates

All Hyperparameters

Click to expand

• overwrite_output_dir: False
• do_predict: False
• eval_strategy: steps
• prediction_loss_only: True
• per_device_train_batch_size: 16
• per_device_eval_batch_size: 16
• 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: 2e-05
• weight_decay: 0.0
• adam_beta1: 0.9
• adam_beta2: 0.999
• adam_epsilon: 1e-08
• max_grad_norm: 1.0
• num_train_epochs: 1
• max_steps: -1
• lr_scheduler_type: linear
• lr_scheduler_kwargs: {}
• warmup_ratio: 0.1
• 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: no_duplicates
• multi_dataset_batch_sampler: proportional
• router_mapping: {}
• learning_rate_mapping: {}

Training Logs

Epoch	Step	ai-job-validation_cosine_accuracy	ai-job-test_cosine_accuracy
-1	-1	0.75	0.7333

Framework Versions

• Python: 3.12.12
• Sentence Transformers: 5.1.2
• Transformers: 4.57.2
• PyTorch: 2.9.0+cu126
• Accelerate: 1.12.0
• 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",
}

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}
}