distilbert-base-uncased-sts-qat

SentenceTransformer based on distilbert/distilbert-base-uncased

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 <!-- at revision 12040accade4e8a0f71eabdb258fecc2e7e948be -->
• Maximum Sequence Length: 512 tokens
• Output Dimensionality: 768 dimensions
• Similarity Function: Cosine Similarity
• Training Dataset:
  • stsb
• Language: en

<!-- - **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': 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.

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]])

<!-- ### 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

Semantic Similarity

• Datasets: sts-dev-float32 and sts-test-float32
• Evaluated with <code>EmbeddingSimilarityEvaluator</code> with these parameters:

  {
      "precision": "float32"
  }
  

Semantic Similarity

• Datasets: sts-dev-int8 and sts-test-int8
• Evaluated with <code>EmbeddingSimilarityEvaluator</code> with these parameters:

  {
      "precision": "int8"
  }
  

Semantic Similarity

• Datasets: sts-dev-binary and sts-test-binary
• Evaluated with <code>EmbeddingSimilarityEvaluator</code> with these parameters:

  {
      "precision": "binary"
  }
  

<!-- ## 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

stsb

• Dataset: stsb at ab7a5ac
• Size: 5,749 training samples
• Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>score</code>
• Approximate statistics based on the first 1000 samples:

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

• Samples:

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

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

  {
      "loss": "CoSENTLoss",
      "quantization_precisions": [
          "float32",
          "int8",
          "binary"
      ],
      "quantization_weights": [
          1,
          1,
          1
      ],
      "n_precisions_per_step": -1
  }
  

Evaluation Dataset

stsb

• Dataset: stsb at ab7a5ac
• Size: 1,500 evaluation samples
• Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>score</code>
• Approximate statistics based on the first 1000 samples:

  	sentence1	sentence2	score
  type	string	string	float
  details	<ul><li>min: 5 tokens</li><li>mean: 15.1 tokens</li><li>max: 45 tokens</li></ul>	<ul><li>min: 6 tokens</li><li>mean: 15.11 tokens</li><li>max: 53 tokens</li></ul>	<ul><li>min: 0.0</li><li>mean: 0.42</li><li>max: 1.0</li></ul>

• Samples:

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

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

  {
      "loss": "CoSENTLoss",
      "quantization_precisions": [
          "float32",
          "int8",
          "binary"
      ],
      "quantization_weights": [
          1,
          1,
          1
      ],
      "n_precisions_per_step": -1
  }
  

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

<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: 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: {}

</details>

Training Logs

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

@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

@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

@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}
}

<!-- ## 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.* -->