Add new SentenceTransformer model

c2c473a verified 1 day ago

24 kB

tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - dense
  - generated_from_trainer
  - dataset_size:33200
  - loss:MultipleNegativesRankingLoss
base_model: google/embeddinggemma-300m
widget:
  - source_sentence: Are stroke patients' reports of home blood pressure readings reliable?
    sentences:
      - The first Whitehall study.
      - >-
        A total of 1027 monitor and 716 booklet readings were recorded. Ninety
        per cent of booklet recordings were exactly the same as the BP monitor
        readings. Average booklet readings were 0.6 mmHg systolic [95%
        confidence interval (95% CI) -0.6 to 1.8] and 0.3 mmHg diastolic (95% CI
        -0.3 to 0.8) lower than those on the monitor.
      - >-
        Protocol 1: a) office blood pressure measurement and Home1 were
        significantly higher than ambulatory blood pressure monitoring, except
        for systolic and diastolic office blood pressure measurement taken by
        the patient or a family member, systolic blood pressure taken by a
        nurse, and diastolic blood pressure taken by a physician. b) ambulatory
        blood pressure monitoring and HBPM1 were similar. Protocol 2: a) HBPM2
        and Home2 were similar. b) Home2 was significantly lower than Home1,
        except for diastolic blood pressure taken by a nurse or the patient.
        There were significant relationships between: a) diastolic blood
        pressure measured by the patient and the thickness of the
        interventricular septum, posterior wall, and left ventricular mass; and
        b) ambulatory and HBPM2 diastolic and systolic blood pressure taken by a
        physician (home2) and left ventricular mass. Therefore, the data
        indicate that home blood pressure measurement and ambulatory blood
        pressure monitoring had good prognostic values relative to "office
        measurement."
  - source_sentence: Do socioeconomic differences in mortality persist after retirement?
    sentences:
      - >-
        to compare the mortality rates of elderly demented and nondemented
        subjects and the differential association of midlife risk factors with
        mortality according to dementia status.
      - Death.
      - >-
        To investigate polysomnographic and anthropomorphic factors predicting
        need of high optimal continuous positive airway pressure (CPAP).
  - source_sentence: >-
      Does a history of unintended pregnancy lessen the likelihood of desire for
      sterilization reversal?
    sentences:
      - >-
        Evolutionary life history theory predicts that, in the absence of
        contraception, any enhancement of maternal condition can increase human
        fertility. Energetic trade-offs are likely to be resolved in favour of
        maximizing reproductive success rather than health or longevity. Here we
        find support for the hypothesis that development initiatives designed to
        improve maternal and child welfare may also incur costs associated with
        increased family sizes if they do not include a family planning
        component.
      - >-
        This study used national, cross-sectional data collected by the
        2006-2010 National Survey of Family Growth. The study sample included
        women ages 15-44 who were surgically sterile from a tubal sterilization
        at the time of interview. Multivariable logistic regression was used to
        examine the relationship between a history of unintended pregnancy and
        desire for sterilization reversal while controlling for potential
        confounders.
      - >-
        Anti-HTLV-I antibodies were positive in both the serum and the CSF in
        all of the patients. Biopsied sample from spinal cord lesions showed
        inflammatory changes in Patient 1. Patient 2 had a demyelinating type of
        sensorimotor polyneuropathy. Two of the three patients examined showed
        high risk of developing HAM/TSP in virologic and immunologic aspects.
  - source_sentence: >-
      Are behavioural risk factors to be blamed for the conversion from optimal
      blood pressure to hypertensive status in Black South Africans?
    sentences:
      - >-
        Longitudinal cohort studies in sub-Saharan Africa are urgently needed to
        understand cardiovascular disease development. We, therefore, explored
        health behaviours and conventional risk factors of African individuals
        with optimal blood pressure (BP) (≤ 120/80 mm Hg), and their 5-year
        prediction for the development of hypertension.
      - >-
        The primary aim was to assess long-term blood pressure in 110 patients
        with Type 2 diabetes who had achieved optimal blood pressure control
        during attendance at a protocol-based nurse-led hypertension intensive
        intervention clinic 7 years previously. The secondary aim was to assess
        modifiable cardiovascular risk factor status.
      - >-
        The Prospective Urban Rural Epidemiology study in the North West
        Province, South Africa, started in 2005 and included African volunteers
        (n = 1994; aged>30 years) from a sample of 6000 randomly selected
        households in rural and urban areas.
  - source_sentence: Can you deliver accurate tidal volume by manual resuscitator?
    sentences:
      - >-
        One of the problems with manual resuscitators is the difficulty in
        achieving accurate volume delivery. The volume delivered to the patient
        varies by the physical characteristics of the person and method. This
        study was designed to compare tidal volumes delivered by the squeezing
        method, physical characteristics and education and practice levels.
      - >-
        Sections from paraffin-embedded blocks of surgically resected specimens
        of GBC (69 cases), XGC (65), chronic cholecystitis (18) and control
        gallbladder (10) were stained with the monoclonal antibodies to p53 and
        PCNA, and a polyclonal antibody to beta-catenin. p53 expression was
        scored as the percentage of nuclei stained. PCNA expression was scored
        as the product of the percentage of nuclei stained and the intensity of
        the staining (1-3). A cut-off value of 80 for this score was taken as a
        positive result. Beta-catenin expression was scored as type of
        expression-membranous, cytoplasmic or nuclear staining.
      - >-
        Although current resuscitation guidelines are rescuer focused, the
        opportunity exists to develop patient-centered resuscitation strategies
        that optimize the hemodynamic response of the individual in the hopes to
        improve survival.
datasets:
  - pavanmantha/pubmed-30k
pipeline_tag: sentence-similarity
library_name: sentence-transformers

SentenceTransformer based on google/embeddinggemma-300m

This is a sentence-transformers model finetuned from google/embeddinggemma-300m on the pubmed-30k 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: google/embeddinggemma-300m
Maximum Sequence Length: 2048 tokens
Output Dimensionality: 768 dimensions
Similarity Function: Cosine Similarity
Training Dataset:
- pubmed-30k

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': 2048, 'do_lower_case': False, 'architecture': 'Gemma3TextModel'})
  (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): Dense({'in_features': 768, 'out_features': 3072, 'bias': False, 'activation_function': 'torch.nn.modules.linear.Identity'})
  (3): Dense({'in_features': 3072, 'out_features': 768, 'bias': False, 'activation_function': 'torch.nn.modules.linear.Identity'})
  (4): 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("pavanmantha/embeddinggemma-pubmed")
# Run inference
queries = [
    "Can you deliver accurate tidal volume by manual resuscitator?",
]
documents = [
    'One of the problems with manual resuscitators is the difficulty in achieving accurate volume delivery. The volume delivered to the patient varies by the physical characteristics of the person and method. This study was designed to compare tidal volumes delivered by the squeezing method, physical characteristics and education and practice levels.',
    'Although current resuscitation guidelines are rescuer focused, the opportunity exists to develop patient-centered resuscitation strategies that optimize the hemodynamic response of the individual in the hopes to improve survival.',
    'Sections from paraffin-embedded blocks of surgically resected specimens of GBC (69 cases), XGC (65), chronic cholecystitis (18) and control gallbladder (10) were stained with the monoclonal antibodies to p53 and PCNA, and a polyclonal antibody to beta-catenin. p53 expression was scored as the percentage of nuclei stained. PCNA expression was scored as the product of the percentage of nuclei stained and the intensity of the staining (1-3). A cut-off value of 80 for this score was taken as a positive result. Beta-catenin expression was scored as type of expression-membranous, cytoplasmic or nuclear staining.',
]
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([[ 0.9156,  0.2237, -0.1894]])

Training Details

Training Dataset

pubmed-30k

Dataset: pubmed-30k at 6a7c15c
Size: 33,200 training samples
Columns: anchor, positive, and negative

Approximate statistics based on the first 1000 samples:

	anchor	positive	negative
type	string	string	string
details	min: 11 tokens mean: 17.74 tokens max: 36 tokens	min: 4 tokens mean: 85.76 tokens max: 301 tokens	min: 5 tokens mean: 82.14 tokens max: 409 tokens

Samples:

anchor	positive	negative
`Does a history of unintended pregnancy lessen the likelihood of desire for sterilization reversal?`	`Unintended pregnancy has been significantly associated with subsequent female sterilization. Whether women who are sterilized after experiencing an unintended pregnancy are less likely to express desire for sterilization reversal is unknown.`	`Changes in serum hormone levels induced by combined contraceptives.`
`Does a history of unintended pregnancy lessen the likelihood of desire for sterilization reversal?`	`Unintended pregnancy has been significantly associated with subsequent female sterilization. Whether women who are sterilized after experiencing an unintended pregnancy are less likely to express desire for sterilization reversal is unknown.`	Evolutionary life history theory predicts that, in the absence of contraception, any enhancement of maternal condition can increase human fertility. Energetic trade-offs are likely to be resolved in favour of maximizing reproductive success rather than health or longevity. Here we find support for the hypothesis that development initiatives designed to improve maternal and child welfare may also incur costs associated with increased family sizes if they do not include a family planning component.
`Does a history of unintended pregnancy lessen the likelihood of desire for sterilization reversal?`	`Unintended pregnancy has been significantly associated with subsequent female sterilization. Whether women who are sterilized after experiencing an unintended pregnancy are less likely to express desire for sterilization reversal is unknown.`	Out of 663 cycles resulting in oocyte retrieval, 299 produced a clinical pregnancy (45.1%). Women who achieved a clinical pregnancy had a significantly shorter stimulation length (11.9 vs. 12.1 days, p = 0.047). Polycystic ovary syndrome (PCOS) was the only etiology of infertility that was significantly associated with a higher chance for clinical pregnancy and was a significant confounder for the association of duration and success of treatment. Women with 13 days or longer of stimulation had a 34 % lower chance of clinical pregnancy as compared to those who had a shorter cycle (OR 0.66, 95% CI:0.46-0.95) after adjustment for age, ovarian reserve, number of oocytes retrieved, embryos transferred and PCOS diagnosis.

Loss: MultipleNegativesRankingLoss with these parameters:

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

Training Hyperparameters

Non-Default Hyperparameters

per_device_train_batch_size: 16
learning_rate: 2e-05
warmup_steps: 0.1
gradient_accumulation_steps: 4
fp16: True
warmup_ratio: 0.1
prompts: task: sentence similarity | query:

All Hyperparameters

Click to expand

per_device_train_batch_size: 16
num_train_epochs: 3
max_steps: -1
learning_rate: 2e-05
lr_scheduler_type: linear
lr_scheduler_kwargs: None
warmup_steps: 0.1
optim: adamw_torch_fused
optim_args: None
weight_decay: 0.0
adam_beta1: 0.9
adam_beta2: 0.999
adam_epsilon: 1e-08
optim_target_modules: None
gradient_accumulation_steps: 4
average_tokens_across_devices: True
max_grad_norm: 1.0
label_smoothing_factor: 0.0
bf16: False
fp16: True
bf16_full_eval: False
fp16_full_eval: False
tf32: None
gradient_checkpointing: False
gradient_checkpointing_kwargs: None
torch_compile: False
torch_compile_backend: None
torch_compile_mode: None
use_liger_kernel: False
liger_kernel_config: None
use_cache: False
neftune_noise_alpha: None
torch_empty_cache_steps: None
auto_find_batch_size: False
log_on_each_node: True
logging_nan_inf_filter: True
include_num_input_tokens_seen: no
log_level: passive
log_level_replica: warning
disable_tqdm: False
project: huggingface
trackio_space_id: trackio
eval_strategy: no
per_device_eval_batch_size: 8
prediction_loss_only: True
eval_on_start: False
eval_do_concat_batches: True
eval_use_gather_object: False
eval_accumulation_steps: None
include_for_metrics: []
batch_eval_metrics: False
save_only_model: False
save_on_each_node: False
enable_jit_checkpoint: False
push_to_hub: False
hub_private_repo: None
hub_model_id: None
hub_strategy: every_save
hub_always_push: False
hub_revision: None
load_best_model_at_end: False
ignore_data_skip: False
restore_callback_states_from_checkpoint: False
full_determinism: False
seed: 42
data_seed: None
use_cpu: False
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
dataloader_drop_last: False
dataloader_num_workers: 0
dataloader_pin_memory: True
dataloader_persistent_workers: False
dataloader_prefetch_factor: None
remove_unused_columns: True
label_names: None
train_sampling_strategy: random
length_column_name: length
ddp_find_unused_parameters: None
ddp_bucket_cap_mb: None
ddp_broadcast_buffers: False
ddp_backend: None
ddp_timeout: 1800
fsdp: []
fsdp_config: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
deepspeed: None
debug: []
skip_memory_metrics: True
do_predict: False
resume_from_checkpoint: None
warmup_ratio: 0.1
local_rank: -1
prompts: task: sentence similarity | query:
batch_sampler: batch_sampler
multi_dataset_batch_sampler: proportional
router_mapping: {}
learning_rate_mapping: {}

Training Logs

Epoch	Step	Training Loss
0.1928	100	0.2086
0.3855	200	0.0872
0.5783	300	0.0623
0.7711	400	0.0569
0.9639	500	0.0487
1.1561	600	0.0423
1.3489	700	0.0412
1.5417	800	0.0407
1.7345	900	0.0341
1.9272	1000	0.0384
2.1195	1100	0.0316
2.3123	1200	0.0290
2.5051	1300	0.0314
2.6978	1400	0.0303
2.8906	1500	0.0245

Framework Versions

Python: 3.11.11
Sentence Transformers: 5.2.3
Transformers: 5.2.0
PyTorch: 2.8.0.dev20250319+cu128
Accelerate: 1.12.0
Datasets: 4.5.0
Tokenizers: 0.22.2

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}
}