all-mpnet-base-v2-sample

MPNet base trained on AllNLI triplets

This is a sentence-transformers model finetuned from intfloat/e5-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: intfloat/e5-base-v2 <!-- at revision 1c644c92ad3ba1efdad3f1451a637716616a20e8 -->
• Maximum Sequence Length: 512 tokens
• Output Dimensionality: 768 dimensions
• Similarity Function: Cosine Similarity

<!-- - **Training Dataset:** Unknown -->

• Language: en
• License: apache-2.0

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': 512, 'do_lower_case': False}) with Transformer model: BertModel 
  (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("sentence_transformers_model_id")
# Run inference
sentences = [
    'Is the Danish National Hospital Register a valuable study base for epidemiologic research in febrile seizures?',
    'The Danish National Hospital Register is a valuable tool for epidemiologic research in febrile seizures.',
    'Ans. is c i.e., Presence of depression Good prognostic factors Acute onset late onset onset after 35 years of age Presence of precipitating stressor Good premorbid adjustment catatonic best prognosis Paranoid 2nd best sho duration 6 months Married Positive symptoms Presence of depression family history of mood disorder first episode pyknic fat physique female sex good treatment compliance good response to treatment good social suppo presence of confusion or perplexity normal brain CT Scan outpatient treatment.',
]
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]

<!-- ### 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.* -->

Evaluation

Metrics

Triplet

• Datasets: eval-dataset and test-dataset
• Evaluated with <code>TripletEvaluator</code>

<!-- ## 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: 800 training samples
• Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>label</code>
• Approximate statistics based on the first 800 samples:

  	sentence1	sentence2	label
  type	string	string	float
  details	<ul><li>min: 5 tokens</li><li>mean: 22.88 tokens</li><li>max: 205 tokens</li></ul>	<ul><li>min: 4 tokens</li><li>mean: 81.77 tokens</li><li>max: 512 tokens</li></ul>	<ul><li>min: 1.0</li><li>mean: 1.0</li><li>max: 1.0</li></ul>

• Samples:

  sentence1	sentence2	label
  <code>Triad of biotin deficiency is</code>	<code>Dermatitis, glossitis, Alopecia 407 H 314 Basic pathology 8th Biotin deficiency clinical features Adult Mental changes depression, hallucination , paresthesia, anorexia, nausea, A scaling, seborrheic and erythematous rash may occur around the eye, nose, mouth, as well as extremities 407 H Infant hypotonia, lethargy, apathy, alopecia and a characteristic rash that includes the ears.Symptoms of biotin deficiency includes Anaemia, loss of apepite dermatitis, glossitis 150 U. Satyanarayan Symptoms of biotin deficiency Dermatitis spectacle eyed appearance due to circumocular alopecia, pallor of skin membrane, depression, Lassitude, somnolence, anemia and hypercholesterolaemia 173 Rana Shinde 6th</code>	<code>1.0</code>
  <code>Drug responsible for the below condition</code>	<code>Thalidomide given to pregnant lady can lead to hypoplasia of limbs called as Phocomelia .</code>	<code>1.0</code>
  <code>Is benefit from procarbazine , lomustine , and vincristine in oligodendroglial tumors associated with mutation of IDH?</code>	<code>IDH mutational status identified patients with oligodendroglial tumors who did and did not benefit from alkylating agent chemotherapy with RT. Although patients with codeleted tumors lived longest, patients with noncodeleted IDH mutated tumors also lived longer after CRT.</code>	<code>1.0</code>

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

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

Evaluation Dataset

Unnamed Dataset

• Size: 100 evaluation samples
• Columns: <code>question</code>, <code>answer</code>, and <code>hard_negative</code>
• Approximate statistics based on the first 100 samples:

  	question	answer	hard_negative
  type	string	string	NoneType
  details	<ul><li>min: 5 tokens</li><li>mean: 22.52 tokens</li><li>max: 103 tokens</li></ul>	<ul><li>min: 10 tokens</li><li>mean: 83.51 tokens</li><li>max: 403 tokens</li></ul>	<ul><li></li></ul>

• Samples:

  question	answer	hard_negative
  <code>Hutchinsons secondaries In skull are due to tumors in</code>	<code>Adrenal neuroblastomas are malig8nant neoplasms arising from sympathetic neuroblsts in Medulla of adrenal gland Neuroblastoma is a cancer that develops from immature nerve cells found in several areas of the body.Neuroblastoma most commonly arises in and around the adrenalglands, which have similar origins to nerve cells and sit atop the kidneys.</code>	<code>None</code>
  <code>Proliferative glomerular deposits in the kidney are found in</code>	<code>IgA nephropathy or Berger s disease immune complex mediated glomerulonephritis defined by the presence of diffuse mesangial IgA deposits often associated with mesangial hypercellularity. Male preponderance, peak incidence in the second and third decades of life.Clinical and laboratory findings Two most common presentations recurrent episodes of macroscopic hematuria during or immediately following an upper respiratory infection often accompanied by proteinuria or persistent asymptomatic microscopic hematuriaIgA deposited in the mesangium is typically polymeric and of the IgA1 subclass. IgM, IgG, C3, or immunoglobulin light chains may be codistributed with IgAPresence of elevated serum IgA levels in 20 50 of patients, IgA deposition in skin biopsies in 15 55 of patients, elevated levels of secretory IgA and IgA fibronectin complexesIgA nephropathy is a benign disease mostly, 5 30 of patients go into a complete remission, with others having hematuria but well preserved renal functionAbou...</code>	<code>None</code>
  <code>Does meconium aspiration induce oxidative injury in the hippocampus of newborn piglets?</code>	<code>Our data thus suggest that oxidative injury associated with pulmonary, but not systemic, hemodynamic disturbances may contribute to hippocampal damage after meconium aspiration in newborns.</code>	<code>None</code>

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

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

Training Hyperparameters

Non-Default Hyperparameters

• do_predict: True
• eval_strategy: steps
• per_device_train_batch_size: 16
• per_device_eval_batch_size: 16
• num_train_epochs: 1
• warmup_ratio: 0.1
• fp16: True
• load_best_model_at_end: True
• batch_sampler: no_duplicates

All Hyperparameters

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

• overwrite_output_dir: False
• do_predict: True
• 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: 5e-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: 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: True
• 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
• 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
• 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
• average_tokens_across_devices: False
• prompts: None
• batch_sampler: no_duplicates
• multi_dataset_batch_sampler: proportional

</details>

Training Logs

Framework Versions

• Python: 3.11.10
• Sentence Transformers: 3.3.0
• Transformers: 4.46.2
• 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",
}

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.* -->