Hugging Face's logo

tomaarsen
/
csr-mxbai-embed-large-v1-nq-cos-sim-scale-20-gamma-0.1-detach-2

Feature Extraction
sentence-transformers
Safetensors
English
bert
sparse-encoder
sparse
csr
Generated from Trainer
dataset_size:99000
loss:CSRLoss
loss:SparseMultipleNegativesRankingLoss
Eval Results
text-embeddings-inference
Model card Files
xet
Community

Sparse CSR model trained on Natural Questions

This is a CSR Sparse Encoder model finetuned from mixedbread-ai/mxbai-embed-large-v1 on the natural-questions dataset using the sentence-transformers library. It maps sentences & paragraphs to a 4096-dimensional sparse vector space with 256 maximum active dimensions and can be used for semantic search and sparse retrieval.

Model Details

Model Description

  • Model Type: CSR Sparse Encoder
  • Base model: mixedbread-ai/mxbai-embed-large-v1
  • Maximum Sequence Length: 512 tokens
  • Output Dimensionality: 4096 dimensions (trained with 256 maximum active dimensions)
  • Similarity Function: Cosine Similarity
  • Training Dataset:
  • Language: en
  • License: apache-2.0

Model Sources

Full Model Architecture 

SparseEncoder(
  (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel 
  (1): Pooling({'word_embedding_dimension': 1024, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, '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): CSRSparsity({'input_dim': 1024, 'hidden_dim': 4096, 'k': 256, 'k_aux': 512, 'normalize': False, 'dead_threshold': 30})
)

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 SparseEncoder

# Download from the 🤗 Hub
model = SparseEncoder("tomaarsen/csr-mxbai-embed-large-v1-nq-cos-sim-scale-20-gamma-0.1-detach-2")
# 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, 4096] [3, 4096]

# Get the similarity scores for the embeddings
similarities = model.similarity(query_embeddings, document_embeddings)
print(similarities)
# tensor([[0.6870, 0.1735, 0.1552]])

Evaluation

Metrics

Sparse Information Retrieval

Metric Value
cosine_accuracy@1 0.332
cosine_accuracy@3 0.477
cosine_accuracy@5 0.555
cosine_accuracy@10 0.651
cosine_precision@1 0.332
cosine_precision@3 0.159
cosine_precision@5 0.111
cosine_precision@10 0.0651
cosine_recall@1 0.332
cosine_recall@3 0.477
cosine_recall@5 0.555
cosine_recall@10 0.651
cosine_ndcg@10 0.4818
cosine_mrr@10 0.4288
cosine_map@100 0.4369
query_active_dims 4.0
query_sparsity_ratio 0.999
corpus_active_dims 4.0
corpus_sparsity_ratio 0.999

Sparse Information Retrieval

Metric Value
cosine_accuracy@1 0.513
cosine_accuracy@3 0.7
cosine_accuracy@5 0.762
cosine_accuracy@10 0.822
cosine_precision@1 0.513
cosine_precision@3 0.2333
cosine_precision@5 0.1524
cosine_precision@10 0.0822
cosine_recall@1 0.513
cosine_recall@3 0.7
cosine_recall@5 0.762
cosine_recall@10 0.822
cosine_ndcg@10 0.6689
cosine_mrr@10 0.6197
cosine_map@100 0.6254
query_active_dims 8.0
query_sparsity_ratio 0.998
corpus_active_dims 8.0
corpus_sparsity_ratio 0.998

Sparse Information Retrieval

Metric Value
cosine_accuracy@1 0.675
cosine_accuracy@3 0.852
cosine_accuracy@5 0.889
cosine_accuracy@10 0.929
cosine_precision@1 0.675
cosine_precision@3 0.284
cosine_precision@5 0.1778
cosine_precision@10 0.0929
cosine_recall@1 0.675
cosine_recall@3 0.852
cosine_recall@5 0.889
cosine_recall@10 0.929
cosine_ndcg@10 0.8088
cosine_mrr@10 0.7696
cosine_map@100 0.7727
query_active_dims 16.0
query_sparsity_ratio 0.9961
corpus_active_dims 16.0
corpus_sparsity_ratio 0.9961

Sparse Information Retrieval

Metric Value
cosine_accuracy@1 0.817
cosine_accuracy@3 0.926
cosine_accuracy@5 0.955
cosine_accuracy@10 0.975
cosine_precision@1 0.817
cosine_precision@3 0.3087
cosine_precision@5 0.191
cosine_precision@10 0.0975
cosine_recall@1 0.817
cosine_recall@3 0.926
cosine_recall@5 0.955
cosine_recall@10 0.975
cosine_ndcg@10 0.9006
cosine_mrr@10 0.8762
cosine_map@100 0.8772
query_active_dims 32.0
query_sparsity_ratio 0.9922
corpus_active_dims 32.0
corpus_sparsity_ratio 0.9922

Sparse Information Retrieval

Metric Value
cosine_accuracy@1 0.88
cosine_accuracy@3 0.956
cosine_accuracy@5 0.973
cosine_accuracy@10 0.983
cosine_precision@1 0.88
cosine_precision@3 0.3187
cosine_precision@5 0.1946
cosine_precision@10 0.0983
cosine_recall@1 0.88
cosine_recall@3 0.956
cosine_recall@5 0.973
cosine_recall@10 0.983
cosine_ndcg@10 0.9359
cosine_mrr@10 0.9203
cosine_map@100 0.921
query_active_dims 64.0
query_sparsity_ratio 0.9844
corpus_active_dims 64.0
corpus_sparsity_ratio 0.9844

Sparse Information Retrieval

Metric Value
cosine_accuracy@1 0.924
cosine_accuracy@3 0.981
cosine_accuracy@5 0.985
cosine_accuracy@10 0.992
cosine_precision@1 0.924
cosine_precision@3 0.327
cosine_precision@5 0.197
cosine_precision@10 0.0992
cosine_recall@1 0.924
cosine_recall@3 0.981
cosine_recall@5 0.985
cosine_recall@10 0.992
cosine_ndcg@10 0.9624
cosine_mrr@10 0.9524
cosine_map@100 0.9528
query_active_dims 128.0
query_sparsity_ratio 0.9688
corpus_active_dims 128.0
corpus_sparsity_ratio 0.9688

Sparse Information Retrieval

Metric Value
cosine_accuracy@1 0.932
cosine_accuracy@3 0.987
cosine_accuracy@5 0.989
cosine_accuracy@10 0.994
cosine_precision@1 0.932
cosine_precision@3 0.329
cosine_precision@5 0.1978
cosine_precision@10 0.0994
cosine_recall@1 0.932
cosine_recall@3 0.987
cosine_recall@5 0.989
cosine_recall@10 0.994
cosine_ndcg@10 0.9678
cosine_mrr@10 0.9589
cosine_map@100 0.9591
query_active_dims 256.0
query_sparsity_ratio 0.9375
corpus_active_dims 256.0
corpus_sparsity_ratio 0.9375

Training Details

Training Dataset

natural-questions

  • Dataset: natural-questions at f9e894e
  • Size: 99,000 training samples
  • Columns: query and answer
  • Approximate statistics based on the first 1000 samples:
    query answer
    type string string
    details
    • min: 10 tokens
    • mean: 11.71 tokens
    • max: 26 tokens
    • min: 4 tokens
    • mean: 131.81 tokens
    • max: 450 tokens
  • Samples:
    query answer
    who played the father in papa don't preach Alex McArthur Alex McArthur (born March 6, 1957) is an American actor.
    where was the location of the battle of hastings 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.
    how many puppies can a dog give birth to 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]
  • Loss: CSRLoss with these parameters:
    {
    "beta": 0.1,
    "gamma": 0.1,
    "loss": "SparseMultipleNegativesRankingLoss(scale=20.0, similarity_fct='cos_sim')"
}

Evaluation Dataset

natural-questions

  • Dataset: natural-questions at f9e894e
  • Size: 1,000 evaluation samples
  • Columns: query and answer
  • Approximate statistics based on the first 1000 samples:
    query answer
    type string string
    details
    • min: 10 tokens
    • mean: 11.69 tokens
    • max: 23 tokens
    • min: 15 tokens
    • mean: 134.01 tokens
    • max: 512 tokens
  • Samples:
    query answer
    where is the tiber river located in italy 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.
    what kind of car does jay gatsby drive 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.
    who sings if i can dream about you 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]
  • Loss: CSRLoss with these parameters:
    {
    "beta": 0.1,
    "gamma": 0.1,
    "loss": "SparseMultipleNegativesRankingLoss(scale=20.0, similarity_fct='cos_sim')"
}

Training Hyperparameters

Non-Default Hyperparameters

  • eval_strategy: steps
  • per_device_train_batch_size: 64
  • per_device_eval_batch_size: 64
  • learning_rate: 4e-05
  • num_train_epochs: 1
  • bf16: True
  • batch_sampler: no_duplicates

All Hyperparameters

Click to expand
  • overwrite_output_dir: False
  • do_predict: False
  • eval_strategy: steps
  • prediction_loss_only: True
  • per_device_train_batch_size: 64
  • per_device_eval_batch_size: 64
  • 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: 4e-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: 0.0
  • 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: True
  • fp16: False
  • 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}
  • 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
  • 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
  • eval_use_gather_object: False
  • average_tokens_across_devices: False
  • prompts: None
  • batch_sampler: no_duplicates
  • multi_dataset_batch_sampler: proportional
  • router_mapping: {}
  • learning_rate_mapping: {}

Training Logs

Epoch Step Training Loss Validation Loss nq_eval_4_cosine_ndcg@10 nq_eval_8_cosine_ndcg@10 nq_eval_16_cosine_ndcg@10 nq_eval_32_cosine_ndcg@10 nq_eval_64_cosine_ndcg@10 nq_eval_128_cosine_ndcg@10 nq_eval_256_cosine_ndcg@10
-1 -1 - - 0.2797 0.4593 0.7019 0.8753 0.9323 0.9620 0.9714
0.0646 100 0.3149 - - - - - - - -
0.1293 200 0.2765 - - - - - - - -
0.1939 300 0.2651 0.2500 0.3976 0.5760 0.7712 0.8849 0.9314 0.9551 0.9650
0.2586 400 0.2572 - - - - - - - -
0.3232 500 0.2517 - - - - - - - -
0.3878 600 0.2484 0.2364 0.4423 0.6333 0.7956 0.8963 0.9350 0.9570 0.9670
0.4525 700 0.2454 - - - - - - - -
0.5171 800 0.2431 - - - - - - - -
0.5818 900 0.2411 0.2300 0.4755 0.6660 0.7986 0.9035 0.9370 0.9582 0.9695
0.6464 1000 0.2397 - - - - - - - -
0.7111 1100 0.2378 - - - - - - - -
0.7757 1200 0.2375 0.2268 0.4763 0.6699 0.8040 0.8987 0.9355 0.9592 0.9673
0.8403 1300 0.2371 - - - - - - - -
0.9050 1400 0.2358 - - - - - - - -
0.9696 1500 0.2359 0.2256 0.4813 0.6709 0.8088 0.9003 0.9348 0.9622 0.9687
-1 -1 - - 0.4818 0.6689 0.8088 0.9006 0.9359 0.9624 0.9678

Environmental Impact

Carbon emissions were measured using CodeCarbon.

  • Energy Consumed: 0.116 kWh
  • Carbon Emitted: 0.045 kg of CO2
  • Hours Used: 0.296 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: 4.2.0.dev0
  • Transformers: 4.52.4
  • PyTorch: 2.6.0+cu124
  • Accelerate: 1.5.1
  • Datasets: 2.21.0
  • Tokenizers: 0.21.1

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",
}

CSRLoss 

@misc{wen2025matryoshkarevisitingsparsecoding,
      title={Beyond Matryoshka: Revisiting Sparse Coding for Adaptive Representation},
      author={Tiansheng Wen and Yifei Wang and Zequn Zeng and Zhong Peng and Yudi Su and Xinyang Liu and Bo Chen and Hongwei Liu and Stefanie Jegelka and Chenyu You},
      year={2025},
      eprint={2503.01776},
      archivePrefix={arXiv},
      primaryClass={cs.LG},
      url={https://arxiv.org/abs/2503.01776},
}

SparseMultipleNegativesRankingLoss 

@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}
}
Downloads last month
11
Safetensors
Model size
335M params
Tensor type
F32
·
Inference Providers NEW
Feature Extraction
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for tomaarsen/csr-mxbai-embed-large-v1-nq-cos-sim-scale-20-gamma-0.1-detach-2

Base model

mixedbread-ai/mxbai-embed-large-v1
Finetuned
(36)
this model

Dataset used to train tomaarsen/csr-mxbai-embed-large-v1-nq-cos-sim-scale-20-gamma-0.1-detach-2

Evaluation results

View on Papers With Code