You can deploy this model and start earning money today!

Views

No views yet

SentenceTransformer based on distilbert/distilbert-base-uncased

Name: distilbert-base-uncased-sts-qat
Availability: InStock

This is a sentence-transformers model finetuned from distilbert/distilbert-base-uncased on the stsb 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: distilbert/distilbert-base-uncased
Maximum Sequence Length: 512 tokens
Output Dimensionality: 768 dimensions
Similarity Function: Cosine Similarity
Training Dataset:
- stsb
Language: en

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, 'architecture': 'DistilBertModel'})
  (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})
)

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("tomaarsen/distilbert-base-uncased-sts-qat")
# Run inference
sentences = [
    'While Queen may refer to both Queen regent (sovereign) or Queen consort, the King has always been the sovereign.',
    'There is a very good reason not to refer to the Queen\'s spouse as "King" - because they aren\'t the King.',
    'A man sitting on the floor in a room is strumming a guitar.',
]
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, 0.7457, 0.3474],
#         [0.7457, 1.0000, 0.3284],
#         [0.3474, 0.3284, 1.0000]])

Evaluation

Metrics

Semantic Similarity

Datasets: sts-dev-float32 and sts-test-float32
Evaluated with EmbeddingSimilarityEvaluator with these parameters:
json
1{ 2 "precision": "float32" 3}

Metric	sts-dev-float32	sts-test-float32
pearson_cosine	0.8591	0.8364
spearman_cosine	0.8743	0.853

Semantic Similarity

Datasets: sts-dev-int8 and sts-test-int8
Evaluated with EmbeddingSimilarityEvaluator with these parameters:
json
1{ 2 "precision": "int8" 3}

Metric	sts-dev-int8	sts-test-int8
pearson_cosine	0.8614	0.8332
spearman_cosine	0.8694	0.8428

Semantic Similarity

Datasets: sts-dev-binary and sts-test-binary
Evaluated with EmbeddingSimilarityEvaluator with these parameters:
json
1{ 2 "precision": "binary" 3}

Metric	sts-dev-binary	sts-test-binary
pearson_cosine	0.8623	0.8459
spearman_cosine	0.8629	0.8427

Training Details

Training Dataset

stsb

Dataset: stsb at ab7a5ac
Size: 5,749 training samples
Columns: sentence1, sentence2, and score
Approximate statistics based on the first 1000 samples:
sentence1 sentence2 score
type string string float
details
min: 6 tokens
mean: 10.0 tokens
max: 28 tokens
min: 5 tokens
mean: 9.95 tokens
max: 25 tokens
min: 0.0
mean: 0.45
max: 1.0

Samples:

sentence1	sentence2	score
`A plane is taking off.`	`An air plane is taking off.`	`1.0`
`A man is playing a large flute.`	`A man is playing a flute.`	`0.76`
`A man is spreading shreded cheese on a pizza.`	`A man is spreading shredded cheese on an uncooked pizza.`	`0.76`

Loss: QuantizationAwareLoss with these parameters:
json
1{ 2 "loss": "CoSENTLoss", 3 "quantization_precisions": [ 4 "float32", 5 "int8", 6 "binary" 7 ], 8 "quantization_weights": [ 9 1, 10 1, 11 1 12 ], 13 "n_precisions_per_step": -1 14}

Evaluation Dataset

stsb

Dataset: stsb at ab7a5ac
Size: 1,500 evaluation samples
Columns: sentence1, sentence2, and score
Approximate statistics based on the first 1000 samples:
sentence1 sentence2 score
type string string float
details
min: 5 tokens
mean: 15.1 tokens
max: 45 tokens
min: 6 tokens
mean: 15.11 tokens
max: 53 tokens
min: 0.0
mean: 0.42
max: 1.0

Samples:

sentence1	sentence2	score
`A man with a hard hat is dancing.`	`A man wearing a hard hat is dancing.`	`1.0`
`A young child is riding a horse.`	`A child is riding a horse.`	`0.95`
`A man is feeding a mouse to a snake.`	`The man is feeding a mouse to the snake.`	`1.0`

Loss: QuantizationAwareLoss with these parameters:
json
1{ 2 "loss": "CoSENTLoss", 3 "quantization_precisions": [ 4 "float32", 5 "int8", 6 "binary" 7 ], 8 "quantization_weights": [ 9 1, 10 1, 11 1 12 ], 13 "n_precisions_per_step": -1 14}

Training Hyperparameters

Non-Default Hyperparameters

eval_strategy: steps
per_device_train_batch_size: 16
per_device_eval_batch_size: 16
num_train_epochs: 4
warmup_ratio: 0.1
fp16: True

All Hyperparameters

Click to expand

overwrite_output_dir: False
do_predict: False
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: 4
max_steps: -1
lr_scheduler_type: linear
lr_scheduler_kwargs: None
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
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: 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}
parallelism_config: None
deepspeed: None
label_smoothing_factor: 0.0
optim: adamw_torch_fused
optim_args: None
adafactor: False
group_by_length: False
length_column_name: length
project: huggingface
trackio_space_id: trackio
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: None
hub_always_push: False
hub_revision: None
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: no
neftune_noise_alpha: None
optim_target_modules: None
batch_eval_metrics: False
eval_on_start: False
use_liger_kernel: False
liger_kernel_config: None
eval_use_gather_object: False
average_tokens_across_devices: True
prompts: None
batch_sampler: batch_sampler
multi_dataset_batch_sampler: proportional
router_mapping: {}
learning_rate_mapping: {}

Training Logs

Epoch	Step	Training Loss	Validation Loss	sts-dev-float32_spearman_cosine	sts-dev-int8_spearman_cosine	sts-dev-binary_spearman_cosine	sts-test-float32_spearman_cosine	sts-test-int8_spearman_cosine	sts-test-binary_spearman_cosine
0.2778	100	14.0507	13.0984	0.8387	0.8364	0.8180	-	-	-
0.5556	200	13.1676	13.3219	0.8458	0.8448	0.8154	-	-	-
0.8333	300	13.0647	13.3489	0.8579	0.8536	0.8277	-	-	-
1.1111	400	12.6803	13.3948	0.8565	0.8511	0.8342	-	-	-
1.3889	500	12.1771	13.2454	0.8628	0.8595	0.8431	-	-	-
1.6667	600	12.2542	13.6541	0.8644	0.8578	0.8484	-	-	-
1.9444	700	12.3987	13.3847	0.8604	0.8545	0.8360	-	-	-
2.2222	800	11.5288	14.3915	0.8656	0.8600	0.8530	-	-	-
2.5	900	11.3617	14.4596	0.8671	0.8609	0.8518	-	-	-
2.7778	1000	11.6528	14.5843	0.8702	0.8645	0.8567	-	-	-
3.0556	1100	11.2609	14.6896	0.8726	0.8667	0.8578	-	-	-
3.3333	1200	10.7624	15.6848	0.8728	0.8673	0.8601	-	-	-
3.6111	1300	10.7987	15.7553	0.8732	0.8671	0.8625	-	-	-
3.8889	1400	10.6542	15.7735	0.8743	0.8694	0.8629	-	-	-
-1	-1	-	-	-	-	-	0.8530	0.8428	0.8427

Environmental Impact

Carbon emissions were measured using CodeCarbon.

Energy Consumed: 0.013 kWh
Carbon Emitted: 0.003 kg of CO2
Hours Used: 0.07 hours

Training Hardware

On Cloud: No
GPU Model: 1 x NVIDIA GeForce RTX 3090
CPU Model: 13th Gen Intel(R) Core(TM) i7-13700K
RAM Size: 31.78 GB

Framework Versions

Python: 3.11.6
Sentence Transformers: 5.3.0.dev0
Transformers: 4.57.6
PyTorch: 2.10.0+cu126
Accelerate: 1.12.0
Datasets: 4.3.0
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",
}

QuantizationAwareLoss

bibtex

@article{jacob2018quantization,
    title={Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference},
    author={Jacob, Benoit and Kligys, Skirmantas and Chen, Bo and Zhu, Menglong and Tang, Matthew and Howard, Andrew and Adam, Hartwig and Kalenichenko, Dmitry},
    journal={arXiv preprint arXiv:1712.05877},
    year={2018}
}

CoSENTLoss

bibtex

@article{10531646,
    author={Huang, Xiang and Peng, Hao and Zou, Dongcheng and Liu, Zhiwei and Li, Jianxin and Liu, Kay and Wu, Jia and Su, Jianlin and Yu, Philip S.},
    journal={IEEE/ACM Transactions on Audio, Speech, and Language Processing},
    title={CoSENT: Consistent Sentence Embedding via Similarity Ranking},
    year={2024},
    doi={10.1109/TASLP.2024.3402087}
}

	sentence1	sentence2	score
type	string	string	float
details	min: 6 tokens mean: 10.0 tokens max: 28 tokens	min: 5 tokens mean: 9.95 tokens max: 25 tokens	min: 0.0 mean: 0.45 max: 1.0