You can deploy this model and start earning money today!

PurpleStatic: Static Embeddings

This is a sentence-transformers model trained on the BatuhanECB/FinModernBERT-pairs-sec-synthetic-v1, Heliosoph/Quora-Question-Pairs, owenkaplinsky/wildchat-paraphrases, mjbommar/ogbert-v1-contrastive and mjbommar/opengloss-v1.3-contrastive-examples datasets. It maps sentences & paragraphs to a 1024-dimensional dense vector space and can be used for retrieval.

Model Details

Model Description

Model Type: Sentence Transformer

Maximum Sequence Length: inf tokens
Output Dimensionality: 1024 dimensions
Similarity Function: Cosine Similarity
Supported Modality: Text
Training Datasets:
- BatuhanECB/FinModernBERT-pairs-sec-synthetic-v1
- Heliosoph/Quora-Question-Pairs
- owenkaplinsky/wildchat-paraphrases
- mjbommar/ogbert-v1-contrastive
- mjbommar/opengloss-v1.3-contrastive-examples
Language: en
License: wtfpl

Model Sources

Documentation: Sentence Transformers Documentation
Repository: Sentence Transformers on GitHub
Hugging Face: Sentence Transformers on Hugging Face

Full Model Architecture

SentenceTransformer(
  (0): StaticEmbedding({})
)

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.

python

from sentence_transformers import SentenceTransformer

# Download from the 🤗 Hub
model = SentenceTransformer("LocalWisdom/PurpleStatic")
# Run inference
sentences = [
    'How do you write a song?',
    'How do I write a song?',
    'How did Portugal become an independent country from Spain?',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 1024]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities)
# tensor([[1.0000, 0.8566, 0.1409],
#         [0.8566, 1.0000, 0.1259],
#         [0.1409, 0.1259, 1.0000]])

Training Details

Training Datasets

BatuhanECB/FinModernBERT-pairs-sec-synthetic-v1

Dataset: BatuhanECB/FinModernBERT-pairs-sec-synthetic-v1
Size: 5,694 training samples
Columns: anchor and positive
Approximate statistics based on the first 100 samples:
anchor positive
type string string
modality text text
details
min: 47 characters
mean: 135.34 characters
max: 352 characters
min: 70 characters
mean: 146.17 characters
max: 322 characters

Samples:

anchor	positive
`Of our total net revenue of $10.8 billion in the fiscal year ended October 31, 2000, we generated 44.2% in the United States and 55.8% internationally.`	`In the fiscal year concluding October 31, 2000, the company produced 44.2% of its $10.8 billion total net revenue within the United States and 55.8% from international markets.`
`Our sales strategy is to sell to and service our largest accounts (hospital and corporate business) directly while employing third-party distributors and manufacturer's representatives for smaller or more geographically dispersed countries.`	`We utilize a sales approach where we directly manage and sell to our major hospital and corporate clients, while relying on external distributors and manufacturer agents to reach smaller markets or those in remote locations.`
`In August 2000, we announced a restructuring of our healthcare solutions business.`	`The company declared a reorganization of its healthcare solutions division in August 2000.`

Loss: MatryoshkaLoss with these parameters:
json
1{ 2 "loss": "MultipleNegativesRankingLoss", 3 "matryoshka_dims": [ 4 1024, 5 768, 6 512, 7 256, 8 128, 9 64, 10 32 11 ], 12 "matryoshka_weights": [ 13 1, 14 1, 15 1, 16 1, 17 1, 18 1, 19 1 20 ], 21 "n_dims_per_step": -1 22}

Heliosoph/Quora-Question-Pairs

Dataset: Heliosoph/Quora-Question-Pairs
Size: 149,263 training samples
Columns: anchor and positive
Approximate statistics based on the first 100 samples:
anchor positive
type string string
modality text text
details
min: 16 characters
mean: 54.75 characters
max: 139 characters
min: 21 characters
mean: 54.34 characters
max: 127 characters

Samples:

anchor	positive
`Astrology: I am a Capricorn Sun Cap moon and cap rising...what does that say about me?`	`I'm a triple Capricorn (Sun, Moon and ascendant in Capricorn) What does this say about me?`
`How can I be a good geologist?`	`What should I do to be a great geologist?`
`How do I read and find my YouTube comments?`	`How can I see all my Youtube comments?`

Loss: MatryoshkaLoss with these parameters:
json
1{ 2 "loss": "MultipleNegativesRankingLoss", 3 "matryoshka_dims": [ 4 1024, 5 768, 6 512, 7 256, 8 128, 9 64, 10 32 11 ], 12 "matryoshka_weights": [ 13 1, 14 1, 15 1, 16 1, 17 1, 18 1, 19 1 20 ], 21 "n_dims_per_step": -1 22}

owenkaplinsky/wildchat-paraphrases

Dataset: owenkaplinsky/wildchat-paraphrases
Size: 1,383,750 training samples
Columns: anchor and positive
Approximate statistics based on the first 100 samples:
anchor positive
type string string
modality text text
details
min: 20 characters
mean: 133.6 characters
max: 733 characters
min: 23 characters
mean: 129.4 characters
max: 639 characters

Samples:

anchor	positive
`name current finance minister of pakistan`	`identify the present finance minister of pakistan`
`name current finance minister of pakistan`	`who is pakistan's finance minister right now`
`name current finance minister of pakistan`	`state the name of the current pakistani minister of finance`

Loss: MatryoshkaLoss with these parameters:
json
1{ 2 "loss": "MultipleNegativesRankingLoss", 3 "matryoshka_dims": [ 4 1024, 5 768, 6 512, 7 256, 8 128, 9 64, 10 32 11 ], 12 "matryoshka_weights": [ 13 1, 14 1, 15 1, 16 1, 17 1, 18 1, 19 1 20 ], 21 "n_dims_per_step": -1 22}

mjbommar/ogbert-v1-contrastive

Dataset: mjbommar/ogbert-v1-contrastive
Size: 2,673,774 training samples
Columns: anchor and positives
Approximate statistics based on the first 100 samples:
anchor positives
type string string
modality text text
details
min: 4 characters
mean: 50.25 characters
max: 178 characters
min: 4 characters
mean: 36.68 characters
max: 121 characters

Samples:

anchor	positives
`The arrangement of halftone dots or grid that encodes tonal values in a halftone image.`	`The halftone dot grid encodes tonal levels.`
`A formal subset of managers designated to handle day-to-day operations and implement board decisions.`	`The executive team meets monthly to review progress and adjust plans.`
`niche market segment`	`submarket`

Loss: MatryoshkaLoss with these parameters:
json
1{ 2 "loss": "MultipleNegativesRankingLoss", 3 "matryoshka_dims": [ 4 1024, 5 768, 6 512, 7 256, 8 128, 9 64, 10 32 11 ], 12 "matryoshka_weights": [ 13 1, 14 1, 15 1, 16 1, 17 1, 18 1, 19 1 20 ], 21 "n_dims_per_step": -1 22}

mjbommar/opengloss-v1.3-contrastive-examples

Dataset: mjbommar/opengloss-v1.3-contrastive-examples
Size: 161,496 training samples
Columns: anchor, positives, negatives_1, and negatives_2

Approximate statistics based on the first 100 samples:

	anchor	positives	negatives_1	negatives_2
type	string	string	string	string
modality	text	text	text	text
details	min: 37 characters mean: 70.41 characters max: 145 characters	min: 36 characters mean: 71.77 characters max: 146 characters	min: 33 characters mean: 72.34 characters max: 145 characters	min: 35 characters mean: 71.88 characters max: 146 characters

Samples:

anchor	positives	negatives_1	negatives_2
`Field interviews revealed a stony demeanor even when pressed for clarification.`	`Field interviews revealed a stoic demeanor even when pressed for clarification.`	`Field interviews revealed a warm demeanor even when pressed for clarification.`	`Field interviews revealed an empathetic demeanor even when pressed for clarification.`
`The board followed formal protocol during the review.`	`The board followed official protocol during the review.`	`The board followed casual protocol during the review.`	`The board followed informal protocol during the review.`
`The athlete carefully inspected the luge before the final run.`	`The athlete carefully inspected the toboggan before the final run.`	`The athlete carefully inspected the sled before the final run.`	`The athlete carefully inspected the bobsled before the final run.`

Loss: MatryoshkaLoss with these parameters:
json
1{ 2 "loss": "MultipleNegativesRankingLoss", 3 "matryoshka_dims": [ 4 1024, 5 768, 6 512, 7 256, 8 128, 9 64, 10 32 11 ], 12 "matryoshka_weights": [ 13 1, 14 1, 15 1, 16 1, 17 1, 18 1, 19 1 20 ], 21 "n_dims_per_step": -1 22}

Training Hyperparameters

Non-Default Hyperparameters

per_device_train_batch_size: 4096
num_train_epochs: 20
learning_rate: 0.0001
warmup_steps: 0.1
bf16: True
batch_sampler: no_duplicates

All Hyperparameters

Click to expand

per_device_train_batch_size: 4096
num_train_epochs: 20
max_steps: -1
learning_rate: 0.0001
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: 1
average_tokens_across_devices: True
max_grad_norm: 1.0
label_smoothing_factor: 0.0
bf16: True
fp16: False
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: None
trackio_bucket_id: None
trackio_static_space_id: None
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_static_graph: None
ddp_backend: None
ddp_timeout: 1800
fsdp: None
fsdp_config: None
deepspeed: None
debug: []
skip_memory_metrics: True
do_predict: False
resume_from_checkpoint: None
warmup_ratio: None
local_rank: -1
prompts: None
batch_sampler: no_duplicates
multi_dataset_batch_sampler: proportional
router_mapping: {}
learning_rate_mapping: {}

Training Logs

Epoch	Step	Training Loss
0.0009	1	61.4605
0.9346	1000	45.8318
0.0009	1	60.6387
0.9346	1000	45.0978
1.8692	2000	44.8278
2.8037	3000	43.0278
3.7383	4000	41.6984
0.0009	1	55.3998
4.6729	5000	40.7913
5.6075	6000	40.1543
6.5421	7000	38.1761
7.4766	8000	38.8003
8.4112	9000	38.2068
9.3458	10000	37.4088
10.2804	11000	36.5805
11.2150	12000	37.1526
12.1495	13000	36.0028
13.0841	14000	35.2225
14.0187	15000	36.2388
14.9533	16000	35.1998
15.8879	17000	35.2619
16.8224	18000	35.1943
17.7570	19000	36.0396
18.6916	20000	34.2574
19.6262	21000	35.1139

Training Time

Training: 2.1 hours

Framework Versions

Python: 3.13.11
Sentence Transformers: 5.6.1
Transformers: 5.14.1
PyTorch: 2.13.0+cu130
Accelerate: 1.14.0
Datasets: 5.0.0
Tokenizers: 0.22.2

Citation

BibTeX

Sentence Transformers

bibtex

@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",
}

MatryoshkaLoss

bibtex

@misc{kusupati2024matryoshka,
    title={Matryoshka Representation Learning},
    author={Aditya Kusupati and Gantavya Bhatt and Aniket Rege and Matthew Wallingford and Aditya Sinha and Vivek Ramanujan and William Howard-Snyder and Kaifeng Chen and Sham Kakade and Prateek Jain and Ali Farhadi},
    year={2024},
    eprint={2205.13147},
    archivePrefix={arXiv},
    primaryClass={cs.LG}
}

MultipleNegativesRankingLoss

bibtex

@misc{oord2019representationlearningcontrastivepredictive,
      title={Representation Learning with Contrastive Predictive Coding},
      author={Aaron van den Oord and Yazhe Li and Oriol Vinyals},
      year={2019},
      eprint={1807.03748},
      archivePrefix={arXiv},
      primaryClass={cs.LG},
      url={https://arxiv.org/abs/1807.03748},
}