all-mpnet-base-v2-qaitrain500-500

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

This is a sentence-transformers model finetuned from sentence-transformers/all-mpnet-base-v2. 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 <!-- at revision e8c3b32edf5434bc2275fc9bab85f82640a19130 -->
• Maximum Sequence Length: 384 tokens
• Output Dimensionality: 768 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': 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("ozgur-celik/all-mpnet-base-v2-qaitrain500-500")
# Run inference
sentences = [
    'How long should a patient wait for soft tissue to heal after a tooth extraction before undergoing regenerative surgery for ridge augmentation?',
    '# Vertical periodontal regeneration\nin combination with ridge\naugmentation\n\ninterproximal bone loss, the smile line, and esthetic\nexpectations should be considered. In cases where\nthe decision is difficult to make, even after the clin-\nician has evaluated these criteria, it can also be de-\ncided during the regenerative surgery. In some cas-\nes, the clinician should consider whether there will\nbe a soft tissue defect when the extraction is per-\nformed during the regenerative surgery, and then\nthe flap design has to be at least one tooth larger. In\ncases where the extraction is performed before the\nidge augmentation, a complete soft tissue healing\ntime of about 2 months should be allowed before\nthe regenerative surgery.\nIn this chapter, technical details of interproximal\nbone and soft tissue regeneration are reviewed\nthrough a representative case of vertical periodon-\ntal regeneration in combination with ridge augmen-\ntation. The 55-year-old, healthy, male patient was\ntreated with an immediate implant at site 12 a dec-\nade previously at another clinic. The patient experi-\nenced bleeding and purulent exudate around the\nimplant and sensitivity of the neighboring lateral\nincisor shortly after implant placement. He sought\ntreatment due to an abscess around the implant.',
    'Fig 9   Ridge preservation via placement of a biomaterial to reduce shrink-\nage following tooth extraction.',
]
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, 0.6634, 0.3224],
#         [0.6634, 1.0000, 0.3342],
#         [0.3224, 0.3342, 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: 793 training samples
• Columns: <code>anchor</code>, <code>positive</code>, <code>negative_1</code>, <code>negative_2</code>, <code>negative_3</code>, and <code>negative_4</code>
• Approximate statistics based on the first 793 samples:

  	anchor	positive	negative_1	negative_2	negative_3	negative_4
  type	string	string	string	string	string	string
  details	<ul><li>min: 9 tokens</li><li>mean: 26.75 tokens</li><li>max: 70 tokens</li></ul>	<ul><li>min: 13 tokens</li><li>mean: 220.18 tokens</li><li>max: 384 tokens</li></ul>	<ul><li>min: 7 tokens</li><li>mean: 130.22 tokens</li><li>max: 384 tokens</li></ul>	<ul><li>min: 9 tokens</li><li>mean: 124.06 tokens</li><li>max: 384 tokens</li></ul>	<ul><li>min: 9 tokens</li><li>mean: 129.57 tokens</li><li>max: 384 tokens</li></ul>	<ul><li>min: 8 tokens</li><li>mean: 132.48 tokens</li><li>max: 384 tokens</li></ul>

• Samples:

  anchor	positive	negative_1	negative_2	negative_3	negative_4
  <code>What specific term does Larsson use to describe the personality-dependent, additional sucking urge observed in children who engage in non-nutritive sucking behaviors?</code>	<code># B) Abbau schädlicher Gewohnheiten (Habits)<br><br>llerdings lutschen nicht alle diese Kinder am Daumen, während viele Kin-<br>der auch in offensichtlich nicht belastender Umwelt dieses Verhalten durch-<br>us zeigen. Dies führte zur Annahme, dass persönlichkeitsabhängige Ursa-<br>chen für das Zustandekommen des Habits zumindest mitveranwortlich <br>ind. Larsson spricht hier von einem »surplus sucking urge« (zusätzlichen <br>Saugbedürfnis), das manche Kinder haben und das evtl. mit dem zu tun<br>hat, was viele Eltern als »besondere Anhänglichkeit« oder » Verschmustheit«<br>bezeichnen.</code>	<code># ugar and childhood obesity<br><br>same but the amount of sugar was reduced, positive effects such as lowered blood sugar,<br>lowered LDL cholesterol, lowered triglycerides, improved liver function, and lowered<br>insulin levels became apparent quickly. In addition, the subjects under a low-sugar diet<br>reacted much more strongly to satiety stimuli. This shows that “one calorie is not equal<br>to one calorie."27<br>Obesity and its accompanying symptoms are now among the most pressing health <br>issues worldwide. In most cases, it is children who suffer from obesity for the rest of their<br>lives, because, contrary to popular belief, people do not grow out of being overweight;<br>rather it is a serious disease. While diet is not the only contributing factor to obesity, it is<br>our responsibility as pediatric dentists to address it for the sake of our young patients’<br>health. Specifically, we can raise parents' awareness of this subject and expose and<br>thereby prevent possible dietary traps. These include too frequent ...</code>	<code># 8.5.1 Gingival recessions<br><br>Patient-related factors include oral hygiene habits<br>and general factors that affect wound healing after oral<br>surgery, including the patient's age and general medic-<br>al factors such as preexisting medical conditions like<br>diabetes, current medications like immunosuppres-<br>sants, and external factors like smoking and stress.<br>Tooth- and defect-related factors of prognostic rele-<br>vance include tooth malpositions, the presence of cer-<br>vical defects, and the initial recession depth as well as<br>the vertical level of the papillae adjacent to the reces-<br>sion defect. Technique-related factors include, for ex-<br>ample, the type of flap used, the amount of soft tissue<br>trauma during the procedure, and the manual skill of<br>the clinician. While patient- as well as tooth- and de-<br>fect-related factors can be controlled to some extent<br>by careful case and defect selection, it is above all the<br>technique-related factors that give the clinician the op-<br>portunity to directly influence ...</code>	<code># WHEN BRUSHING IS A STRUGGLE<br><br>At routine checkups, many parents report that brushing their child’s teeth<br>is a daily struggle and they are helplessly seeking tips and tricks to avoid a<br>“wrestling match.” What worked entirely fine when the child was an infant has<br>uddenly become an ordeal for all concerned. Parents do not always manage<br>to motivate their little ones to brush or have their teeth brushed with patience<br>and fun by including play. Especially with the youngest children, discussions<br>or positive reinforcement with different reward systems are only possible to<br>a limited extent.<br>Nonetheless, a solution must be found, because not brushing for days<br>or weeks is not an option in terms of the child’s well-being and oral health.<br>The solution is simple: Parents just have to persevere. The more calmly and<br>confidently parents act, the quicker this period of refusal from children is over.<br>Refusal to brush may be a child’s way of expressing desire for independence,<br>which can turn other everyd...</code>	<code># REFERENCES<br><br>23. Roberts GJ, Cleaton-Jones PE, Fatti LP, et al. Patterns of breast and bottle feeding and their associ-<br>ation with dental caries in 1- to 4-year-old South African children. 1. Dental caries prevalence and<br>experience. Community Dent Health 1993;10:405-413.<br>24. Koletzko B, Brönstrup A, Cremer M, et al. Säuglingsernährung und Ernährung der stillenden Mutter:</code>
  <code>What type of implant is recommended for a narrow-diameter implant case according to the Esthetic Risk Assessment?</code>	<code># Table 1 Esthetic Risk Assessment (ERA)<br><br> * If three-dimensional imaging is available with the tooth in place<br>1 Standard-diameter implant, regular connection<br>2 Narrow-diameter implant, narrow connection<br>1 Standard-diameter implant, regular connection<br>2 Narrow-diameter implant, narrow connection</code>	<code># Single-tooth gap<br><br>The implant rehabilitation of a single-tooth gap in<br>the anterior mandible, following the loss of one<br>mandibular incisor, requires not only a special set<br>of instruments, but also a particularly high level of<br>precision from the implantologist. In most cases, the<br>resultant gap is very narrow and the available space<br>between the roots of the neighboring teeth extreme-<br>ly limited. Iatrogenic injury to the neighboring teeth<br>can only be avoided with detailed preoperative radi-<br>ologic investigations and by performing the surgical<br>procedure with great care. If the residual ridge has<br>healed, the freshly inserted implant can be loaded<br>directly with a prosthesis, which is highly advanta-<br>geous for both the patient and the dentist.<br>Because of the limited space, implants of reduced<br>diameter, ie, narrow platform (NP) implants such as<br>NobelActive (diameter 3.0 and 3.3 mm) and Nobel-<br>Direct (diameter 3.0 mm) from Nobel Biocare, or<br>Touareg (diameter 3.0 mm) from Adin or the K.S.I.<br>Bau...</code>	<code># 2.3.1<br>Application of Computer<br>Technology in Surgical Implant<br>Dentistry<br><br>Computer-guided (static) surgery. The use of a static sur-<br>gical template that reproduces the virtual implant posi-<br>tion directly from computerized tomographic data with-<br>out allowing the intraoperative modification of implant<br>position.<br>Computer-navigated (dynamic) surgery. The use of a sur-<br>gical navigation system that reproduces the virtual im-<br>plant position directly from computerized tomography<br>and allows intraoperative changes in implant position.<br>The group recommended that, with appropriate training,<br>experience, and pre-surgical planning, these systems<br>might be clinically beneficial in the following clinical sit-<br>uations:<br>Complex anatomy<br>•<br>•<br>Minimally invasive surgery<br>.<br>Optimization of implant placement<br>in critical esthetic cases<br>.<br>Immediate loading</code>	<code># The Relationship Between Peri-implant<br>Esthetics and the Biologic Width<br><br>The presence of a papilla between teeth and implants <br>and between implants is fundamental to an accept-<br>able esthetic result. When single implants are placed<br>between healthy teeth, the interproximal soft tissues<br>are maintained by adjacent bone crests. The position of<br>the bone crest must be analyzed through an ultrasound</code>	<code># Treatment guidelines<br><br>Esthetic outcomes can be achieved at post-extraction<br>sites irrespective of the timing of implant placement.<br>Different placement times, however, present with spe-<br>cific treatment challenges and variable predictability of<br>esthetic outcomes.<br>With immediate placement, a high level of clinical com-<br>petence and experience in performing the treatment is<br>needed. Careful case selection is required to achieve sat-<br>isfactory esthetic outcomes. The following clinical condi-<br>tions should be satisfied:</code>
  <code>Which specific shade of composite material was utilized to simulate the incisal halo effect on the left central incisor during the restorative procedure described in the Manauta case?</code>	<code>Q: You invented the centripetal technique in the year 1994. Is it only for posteriors?<br>n search of a solution to overcome the challenges of restoring the<br>proximal cavities of posterior teeth and in order to facilitate an easier<br>and quicker technique with a more effective result, the idea of the<br>centripetal buildup was born.<br>The idea was to define and delimit the proximal surface with a<br>thin layer of composite that is actually contoured with the aid of a<br>precontoured matrix band and then to fill up the inner part of the<br>cavity with a composite resin restorative material. This process<br>allows for the utilization of different translucencies, transparencies,<br>and colors of the composite resins according to the area that is<br>being restored, meaning that the enamel that is more translucent <br>and has a more pronounced opalescence will be restored with a<br>certain type of composite, whereas the dentin part will be restored<br>with a more chromatic dentin shade.<br>The initial idea was to implement this te...</code>	<code># The incisal hook<br>technique<br><br>The workflow selected in this case was first a morphological<br>restoration of the palatal areas together with an increase<br>in the vertical dimension and design of the incisal edges<br>(type 1 palatal veneer).<br>563</code>	<code>Fig 4-33h Left lateral incisor. Folded protective<br>matrices in place for enamel etching, followed by<br>drying.</code>	<code># LITERATUR<br><br>2 Chiche GJ, Pinault A. Artistic and scientific principles<br>applied to esthetic dentistry. In: Chiche GJ, Pinault A<br>(eds). Esthetics of Anterior Fixed Prosthodontics. Chi-<br>cago: Quintessence, 1994:13-32</code>	<code># References<br><br>Pfeiffer J. Dental CAD/CAM technologies: the optical impression (I). Int<br>299.<br>J Comput Dent 1998;1:29-33.</code>

• Loss: <code>MultipleNegativesRankingLoss</code> with these parameters:

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

Training Hyperparameters

Non-Default Hyperparameters

• eval_strategy: steps
• learning_rate: 2e-05
• num_train_epochs: 2
• warmup_ratio: 0.1
• data_seed: 42
• dataloader_pin_memory: False
• hub_model_id: ozgur-celik/all-mpnet-base-v2-qaitrain500-500
• hub_private_repo: True
• eval_on_start: True
• batch_sampler: no_duplicates

All Hyperparameters

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

• overwrite_output_dir: False
• do_predict: False
• eval_strategy: steps
• prediction_loss_only: True
• per_device_train_batch_size: 8
• per_device_eval_batch_size: 8
• 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: 2
• 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: 42
• jit_mode_eval: False
• use_ipex: 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}
• tp_size: 0
• 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: False
• dataloader_persistent_workers: False
• skip_memory_metrics: True
• use_legacy_prediction_loop: False
• push_to_hub: False
• resume_from_checkpoint: None
• hub_model_id: ozgur-celik/all-mpnet-base-v2-qaitrain500-500
• hub_strategy: every_save
• hub_private_repo: True
• hub_always_push: False
• 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: False
• neftune_noise_alpha: None
• optim_target_modules: None
• batch_eval_metrics: False
• eval_on_start: True
• use_liger_kernel: False
• eval_use_gather_object: False
• average_tokens_across_devices: False
• prompts: None
• batch_sampler: no_duplicates
• multi_dataset_batch_sampler: proportional
• router_mapping: {}
• learning_rate_mapping: {}

</details>

Training Logs

Framework Versions

• Python: 3.12.3
• Sentence Transformers: 5.2.2
• Transformers: 4.51.3
• PyTorch: 2.8.0+cu128
• Accelerate: 1.14.0
• Datasets: 5.0.0
• Tokenizers: 0.21.4

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}
}

<!-- ## 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.* -->