CoolFace
Modelpublic

seank333111/inference-free-splade-distilbert-base-uncased-nq

sourceHugging Faceapache-2.0updated 1y agoView on Hugging Face
0likes
Model Card

Inference-free SPLADE distilbert-base-uncased trained on Natural-Questions tuples

This is a Asymmetric Inference-free SPLADE Sparse Encoder model finetuned from distilbert/distilbert-base-uncased on the natural-questions dataset using the sentence-transformers library. It maps sentences & paragraphs to a 30522-dimensional sparse vector space and can be used for semantic search and sparse retrieval.

Model Details

Model Description

  • —Model Type: Asymmetric Inference-free SPLADE Sparse Encoder
  • —Base model: distilbert/distilbert-base-uncased <!-- at revision 12040accade4e8a0f71eabdb258fecc2e7e948be -->
  • —Maximum Sequence Length: 512 tokens
  • —Output Dimensionality: 30522 dimensions
  • —Similarity Function: Dot Product
  • —Training Dataset:
  • —natural-questions
  • —Language: en
  • —License: apache-2.0

Model Sources

Full Model Architecture

SparseEncoder(
  (0): Router(
    (query_0_SparseStaticEmbedding): SparseStaticEmbedding({'frozen': False}, dim=30522, tokenizer=DistilBertTokenizerFast)
    (document_0_MLMTransformer): MLMTransformer({'max_seq_length': 512, 'do_lower_case': False, 'architecture': 'DistilBertForMaskedLM'})
    (document_1_SpladePooling): SpladePooling({'pooling_strategy': 'max', 'activation_function': 'relu', 'word_embedding_dimension': 30522})
  )
)

Usage

Direct Usage (Sentence Transformers)

First install the Sentence Transformers library:

bash
pip install -U sentence-transformers

Then you can load this model and run inference.

python
from sentence_transformers import SparseEncoder

# Download from the 🤗 Hub
model = SparseEncoder("seank333111/inference-free-splade-distilbert-base-uncased-nq")
# Run inference
queries = [
    "who is cornelius in the book of acts",
]
documents = [
    'Cornelius the Centurion Cornelius (Greek: Κορνήλιος) was a Roman centurion who is considered by Christians to be one of the first Gentiles to convert to the faith, as related in Acts of the Apostles.',
    "Joe Ranft Ranft reunited with Lasseter when he was hired by Pixar in 1991 as their head of story.[1] There he worked on all of their films produced up to 2006; this included Toy Story (for which he received an Academy Award nomination) and A Bug's Life, as the co-story writer and others as story supervisor. His final film was Cars. He also voiced characters in many of the films, including Heimlich the caterpillar in A Bug's Life, Wheezy the penguin in Toy Story 2, and Jacques the shrimp in Finding Nemo.[1]",
    'Wonderful Tonight "Wonderful Tonight" is a ballad written by Eric Clapton. It was included on Clapton\'s 1977 album Slowhand. Clapton wrote the song about Pattie Boyd.[1] The female vocal harmonies on the song are provided by Marcella Detroit (then Marcy Levy) and Yvonne Elliman.',
]
query_embeddings = model.encode_query(queries)
document_embeddings = model.encode_document(documents)
print(query_embeddings.shape, document_embeddings.shape)
# [1, 30522] [3, 30522]

# Get the similarity scores for the embeddings
similarities = model.similarity(query_embeddings, document_embeddings)
print(similarities)
# tensor([[5.9751, 0.2390, 0.0000]])

<!--

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

Sparse Information Retrieval
MetricNanoMSMARCONanoNFCorpusNanoNQ
dot_accuracy@10.320.440.38
dot_accuracy@30.520.480.62
dot_accuracy@50.60.540.68
dot_accuracy@100.80.580.74
dot_precision@10.320.440.38
dot_precision@30.17330.35330.2067
dot_precision@50.120.3280.136
dot_precision@100.080.2460.076
dot_recall@10.320.0430.37
dot_recall@30.520.07250.58
dot_recall@50.60.09290.64
dot_recall@100.80.11630.71
dot_ndcg@100.52940.31290.5477
dot_mrr@100.4470.47590.5072
dot_map@1000.45470.13750.4973
queryactivedims6.384.769.44
querysparsityratio0.99980.99980.9997
corpusactivedims56.056169.886651.1154
corpussparsityratio0.99820.99770.9983
Sparse Nano BEIR
json
  {
      "dataset_names": [
          "msmarco",
          "nfcorpus",
          "nq"
      ]
  }
MetricValue
dot_accuracy@10.38
dot_accuracy@30.54
dot_accuracy@50.6067
dot_accuracy@100.7067
dot_precision@10.38
dot_precision@30.2444
dot_precision@50.1947
dot_precision@100.134
dot_recall@10.2443
dot_recall@30.3908
dot_recall@50.4443
dot_recall@100.5421
dot_ndcg@100.4634
dot_mrr@100.4767
dot_map@1000.3632
queryactivedims6.86
querysparsityratio0.9998
corpusactivedims57.2813
corpussparsityratio0.9981

<!--

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

natural-questions
  • —Dataset: natural-questions at f9e894e
  • —Size: 99,000 training samples
  • —Columns: <code>query</code> and <code>answer</code>
  • —Approximate statistics based on the first 1000 samples: | | query | answer | |:--------|:-----------------------------------------------------------------------------------|:------------------------------------------------------------------------------------| | type | string | string | | details | <ul><li>min: 10 tokens</li><li>mean: 11.71 tokens</li><li>max: 26 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 131.81 tokens</li><li>max: 450 tokens</li></ul> |
  • —Samples: | query | answer | |:--------------------------------------------------------------|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| | <code>who played the father in papa don't preach</code> | <code>Alex McArthur Alex McArthur (born March 6, 1957) is an American actor.</code> | | <code>where was the location of the battle of hastings</code> | <code>Battle of Hastings The Battle of Hastings[a] was fought on 14 October 1066 between the Norman-French army of William, the Duke of Normandy, and an English army under the Anglo-Saxon King Harold Godwinson, beginning the Norman conquest of England. It took place approximately 7 miles (11 kilometres) northwest of Hastings, close to the present-day town of Battle, East Sussex, and was a decisive Norman victory.</code> | | <code>how many puppies can a dog give birth to</code> | <code>Canine reproduction The largest litter size to date was set by a Neapolitan Mastiff in Manea, Cambridgeshire, UK on November 29, 2004; the litter was 24 puppies.[22]</code> |
  • —Loss: <code>SpladeLoss</code> with these parameters:
json
  {
      "loss": "SparseMultipleNegativesRankingLoss(scale=1.0, similarity_fct='dot_score')",
      "document_regularizer_weight": 0.003,
      "query_regularizer_weight": 0
  }

Evaluation Dataset

natural-questions
  • —Dataset: natural-questions at f9e894e
  • —Size: 1,000 evaluation samples
  • —Columns: <code>query</code> and <code>answer</code>
  • —Approximate statistics based on the first 1000 samples: | | query | answer | |:--------|:-----------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------| | type | string | string | | details | <ul><li>min: 10 tokens</li><li>mean: 11.69 tokens</li><li>max: 23 tokens</li></ul> | <ul><li>min: 15 tokens</li><li>mean: 134.01 tokens</li><li>max: 512 tokens</li></ul> |
  • —Samples: | query | answer | |:-------------------------------------------------------|:-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| | <code>where is the tiber river located in italy</code> | <code>Tiber The Tiber (/ˈtaɪbər/, Latin: Tiberis,[1] Italian: Tevere [ˈteːvere])[2] is the third-longest river in Italy, rising in the Apennine Mountains in Emilia-Romagna and flowing 406 kilometres (252 mi) through Tuscany, Umbria and Lazio, where it is joined by the river Aniene, to the Tyrrhenian Sea, between Ostia and Fiumicino.[3] It drains a basin estimated at 17,375 square kilometres (6,709 sq mi). The river has achieved lasting fame as the main watercourse of the city of Rome, founded on its eastern banks.</code> | | <code>what kind of car does jay gatsby drive</code> | <code>Jay Gatsby At the Buchanan home, Jordan Baker, Nick, Jay, and the Buchanans decide to visit New York City. Tom borrows Gatsby's yellow Rolls Royce to drive up to the city. On the way to New York City, Tom makes a detour at a gas station in "the Valley of Ashes", a run-down part of Long Island. The owner, George Wilson, shares his concern that his wife, Myrtle, may be having an affair. This unnerves Tom, who has been having an affair with Myrtle, and he leaves in a hurry.</code> | | <code>who sings if i can dream about you</code> | <code>I Can Dream About You "I Can Dream About You" is a song performed by American singer Dan Hartman on the soundtrack album of the film Streets of Fire. Released in 1984 as a single from the soundtrack, and included on Hartman's album I Can Dream About You, it reached number 6 on the Billboard Hot 100.[1]</code> |
  • —Loss: <code>SpladeLoss</code> with these parameters:
json
  {
      "loss": "SparseMultipleNegativesRankingLoss(scale=1.0, similarity_fct='dot_score')",
      "document_regularizer_weight": 0.003,
      "query_regularizer_weight": 0
  }

Training Hyperparameters

Non-Default Hyperparameters
  • —eval_strategy: steps
  • —per_device_train_batch_size: 16
  • —per_device_eval_batch_size: 16
  • —learning_rate: 2e-05
  • —num_train_epochs: 1
  • —warmup_ratio: 0.1
  • —fp16: True
  • —batch_sampler: no_duplicates
  • —router_mapping: {'query': 'query', 'answer': 'document'}
  • —learning_rate_mapping: {'SparseStaticEmbedding\\.weight': 0.001}
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: 2e-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: False
  • —ignore_data_skip: False
  • —fsdp: []
  • —fsdp_min_num_params: 0
  • —fsdp_config: {'minnumparams': 0, 'xla': False, 'xlafsdpv2': False, 'xlafsdpgrad_ckpt': False}
  • —fsdp_transformer_layer_cls_to_wrap: None
  • —accelerator_config: {'splitbatches': False, 'dispatchbatches': None, 'evenbatches': True, 'useseedablesampler': True, 'nonblocking': False, 'gradientaccumulationkwargs': 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: 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: False
  • —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: False
  • —prompts: None
  • —batch_sampler: no_duplicates
  • —multi_dataset_batch_sampler: proportional
  • —router_mapping: {'query': 'query', 'answer': 'document'}
  • —learning_rate_mapping: {'SparseStaticEmbedding\\.weight': 0.001}

</details>

Training Logs

EpochStepTraining LossValidation LossNanoMSMARCO_dot_ndcg@10NanoNFCorpus_dot_ndcg@10NanoNQ_dot_ndcg@10NanoBEIR_mean_dot_ndcg@10
0.03232000.2418-----
0.06464000.0857-----
0.09706000.072-----
0.12938000.062-----
0.161610000.06240.08670.52130.33260.52960.4612
0.193912000.0684-----
0.226214000.0776-----
0.258616000.0824-----
0.290918000.0826-----
0.323220000.0820.10280.51080.32300.51690.4502
0.355522000.0869-----
0.387824000.0866-----
0.420226000.0848-----
0.452528000.0816-----
0.484830000.07690.09140.56670.31490.57860.4867
0.517132000.0745-----
0.549534000.0831-----
0.581836000.0764-----
0.614138000.0806-----
0.646440000.07420.08850.55120.32210.52620.4665
0.678742000.0739-----
0.711144000.0674-----
0.743446000.0675-----
0.775748000.0741-----
0.808050000.06860.08270.55140.31460.56320.4764
0.840352000.0745-----
0.872754000.0687-----
0.905056000.0637-----
0.937358000.0637-----
0.969660000.06480.07850.52920.31170.54800.4630
-1-1--0.52940.31290.54770.4634

Framework Versions

  • —Python: 3.11.13
  • —Sentence Transformers: 5.0.0
  • —Transformers: 4.53.0
  • —PyTorch: 2.6.0+cu124
  • —Accelerate: 1.8.1
  • —Datasets: 3.6.0
  • —Tokenizers: 0.21.2

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",
}
SpladeLoss
bibtex
@misc{formal2022distillationhardnegativesampling,
      title={From Distillation to Hard Negative Sampling: Making Sparse Neural IR Models More Effective},
      author={Thibault Formal and Carlos Lassance and Benjamin Piwowarski and Stéphane Clinchant},
      year={2022},
      eprint={2205.04733},
      archivePrefix={arXiv},
      primaryClass={cs.IR},
      url={https://arxiv.org/abs/2205.04733},
}
SparseMultipleNegativesRankingLoss
bibtex
@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}
}
FlopsLoss
bibtex
@article{paria2020minimizing,
    title={Minimizing flops to learn efficient sparse representations},
    author={Paria, Biswajit and Yeh, Chih-Kuan and Yen, Ian EH and Xu, Ning and Ravikumar, Pradeep and P{'o}czos, Barnab{'a}s},
    journal={arXiv preprint arXiv:2004.05665},
    year={2020}
}

<!--

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. -->