README.md

metadata

base_model: sentence-transformers/all-mpnet-base-v2
library_name: sentence-transformers
pipeline_tag: sentence-similarity
tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - generated_from_trainer
  - dataset_size:768201
  - loss:MultipleNegativesRankingLoss
widget:
  - source_sentence: >-
      The present disclosure provides systems and methods to optimize data
      backup in a distributed enterprise system by firstly generating a set of
      unique files from all the files available in the enterprise. A backup set
      comprising files to be backed up are then generated from the set of unique
      files and backup is scheduled in the order in which the files to be backed
      up are identified. Unique files are generated based on file sharing
      patterns and communications among users that enable generating a social
      network graph from which one or more communities can be detected and
      deduplication can be performed on the files hosted by client systems in
      these communities thereby conserving resources.
    sentences:
      - BURNER
      - >-
        SYSTEMS AND METHODS FOR OPTIMIZED DATA BACKUP IN A DISTRIBUTED
        ENTERPRISE SYSTEM
      - Power conversion apparatus
  - source_sentence: >-
      The present invention relates to a use of polypeptide compounds having
      dual agonist effect on glucagon-like peptide-1 receptor (GLP-1R) and
      glucagon receptor (GCGR). The polypeptide compounds are characterized by
      high enzymolysis stability, high potency and no adverse reaction, and
      capable of substantially improving hepatic fibrosis caused by hepatitis B
      virus (HBV) and hepatitis C virus (HCV) and severity of fibrotic
      conditions accompanied with liver diseases. The dual target agonist
      polypeptide derivatives are capable of preventing or treating hepatic
      fibrosis diseases associated with viral hepatitis.
    sentences:
      - >-
        GLP-1R/GCGR DUAL-TARGET AGONIST PEPTIDE DERIVATIVES FOR TREATMENT OF
        VIRAL HEPATITIS-RELATED HEPATIC FIBROSIS
      - MAGNETIC FILTER CARTRIDGE AND FILTER ASSEMBLY
      - USER TERMINAL AND WIRELESS COMMUNICATION METHOD
  - source_sentence: >-
      A latch includes a latch housing including a first housing portion and a
      second housing portion separable from the first housing portion. The
      second housing portion includes a keeper. A first arm member is in
      rotational communication with the first housing portion. The first arm
      member is configured to rotate about a first axis between a first position
      and a second position. A second arm member is in rotational communication
      with the first arm member. A latch load pin is in rotational communication
      with the first arm member about a second axis. The latch load pin is
      configured to mate with the keeper with the first arm member in the first
      position. The second arm member in the first position is configured to be
      fixed relative to the first arm member as the first arm member rotates
      from the first position toward the second position.
    sentences:
      - UNLOCKING METHODS AND RELATED PRODUCTS
      - LATCH AND METHOD FOR OPERATING SAID LATCH
      - >-
        PANEL-SHAPED MOLDED ARTICLE AND PRODUCTION METHOD FOR PANEL-SHAPED
        MOLDED ARTICLE
  - source_sentence: >-
      The present invention aims to provide a production method of low-fat and
      low-protein yogurt with smooth taste, suppressed syneresis and superior
      shape retainability, comprising adding protein glutaminase and starch to
      raw milk.
    sentences:
      - YOGURT PRODUCTION METHOD
      - Aircraft electric motor system
      - Floor panel, flooring system and method for laying flooring system
  - source_sentence: >-
      A computer-implemented method determines an orientation parameter value of
      a prosthetic component. The method includes receiving a first desired
      separation distance (d1) between a tibial prosthetic component (120) and a
      femoral prosthetic component (110) at a first flexion position (521) of a
      knee joint (100) and estimating a first estimated separation distance (g1)
      between the tibial prosthetic component and the femoral prosthetic
      component at the first flexion position of the knee joint for at least one
      potential orientation of the femoral prosthet¬ic component. The method
      also includes determining a first orientation para¬meter value of the
      femoral prosthetic component by comparing the first estimated separation
      distance to the first desired separation distance and out¬putting the
      first orientation parameter value via a user interface (400).
    sentences:
      - Mobile device and antenna structure
      - >-
        TWO-WAY VALVE FOR CONTROLLING A TEMPERATURE OF A COOLANT FOR AN INTERNAL
        COMBUSTION ENGINE
      - SYSTEMS AND METHOD FOR PROSTHETIC COMPONENT ORIENTATION

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 json 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 tokens
• Similarity Function: Cosine Similarity
• Training Dataset:
  • json

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}) with Transformer model: 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("stephenhib/all-mpnet-base-v2-patabs-1epoc-batch32-100")
# Run inference
sentences = [
    'A computer-implemented method determines an orientation parameter value of a prosthetic component. The method includes receiving a first desired separation distance (d1) between a tibial prosthetic component (120) and a femoral prosthetic component (110) at a first flexion position (521) of a knee joint (100) and estimating a first estimated separation distance (g1) between the tibial prosthetic component and the femoral prosthetic component at the first flexion position of the knee joint for at least one potential orientation of the femoral prosthet¬ic component. The method also includes determining a first orientation para¬meter value of the femoral prosthetic component by comparing the first estimated separation distance to the first desired separation distance and out¬putting the first orientation parameter value via a user interface (400).',
    'SYSTEMS AND METHOD FOR PROSTHETIC COMPONENT ORIENTATION',
    'TWO-WAY VALVE FOR CONTROLLING A TEMPERATURE OF A COOLANT FOR AN INTERNAL COMBUSTION ENGINE',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 768]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities.shape)
# [3, 3]

Training Details

Training Dataset

json

• Dataset: json
• Size: 768,201 training samples
• Columns: positive and anchor
• Approximate statistics based on the first 1000 samples:

  	positive	anchor
  type	string	string
  details	min: 13 tokens mean: 163.82 tokens max: 384 tokens	min: 3 tokens mean: 12.34 tokens max: 73 tokens

• Samples:

  positive	anchor
  According to an example aspect of the present invention, there is provided an apparatus and method to control mining vehicles, in particular as electric mining vehicles, taking into account the state of charge the batteries of said mining vehicles.	MINING VEHICLE CONTROL
  The invention is related to a new soft heterophasic random propylene copolymer with improved optical properties, as well as the process by which the heterophasic random propylene copolymer is produced.	SOFT HETEROPHASIC RANDOM PROPYLENE COPOLYMER WITH IMPROVED CLARITY
  The present invention relates to a valve assembly 10 for controlling a volute connecting opening 324 of a multi-channel turbine 500. The valve assembly 10 comprises a housing portion 300, a valve body 100 and an internal lever 200. The housing portion 300 defines a first volute channel 312, a second volute channel 314 and a volute connecting region 320. The housing portion 300 further comprises a cavity 340. The cavity 340 is separated from the volutes 312, 314 and can be accessed from outside the housing portion 300 via a housing opening 342 which extends from outside the housing portion 300 into the cavity 340. The volute connection region 320 is located between the first volute channel 312 and the second volute channel 314 and defines a volute connecting opening 324. The valve body 100 is inserted in the cavity 340 of the housing portion 300 and comprises at least one fin 120. The internal lever 200 is coupled with the valve body 100 and configured to pivotably move the valve body 100 between a first position and a second position. In the first position of the valve body 100, the fin 120 blocks the volute connecting opening 324. Thus, exhaust gases are substantially prevented from overflowing from the first volute channel 312 to the second volute channel 314 and vice versa. In the second position of the valve body 100 the fin 120 clears the volute connecting opening 324. Thus, exhaust gases are enabled to overflow from the first volute channel 312 to the second volute channel 314 and vice versa.	VALVE ASSEMBLY FOR MULTI-CHANNEL TURBINE

• Loss: MultipleNegativesRankingLoss with these parameters:

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

Training Hyperparameters

Non-Default Hyperparameters

• eval_strategy: steps
• per_device_train_batch_size: 4
• per_device_eval_batch_size: 2
• learning_rate: 2e-05
• num_train_epochs: 1
• warmup_ratio: 0.1
• bf16: True
• 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: 4
• per_device_eval_batch_size: 2
• 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
• use_ipex: False
• bf16: True
• 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}
• 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
• batch_sampler: no_duplicates
• multi_dataset_batch_sampler: proportional

Framework Versions

• Python: 3.11.9
• Sentence Transformers: 3.2.0
• Transformers: 4.45.2
• PyTorch: 2.5.0+cu124
• Accelerate: 1.0.1
• Datasets: 3.0.1
• Tokenizers: 0.20.1

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}
}