README.md

metadata

language:
  - en
license: apache-2.0
tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - generated_from_trainer
  - dataset_size:6300
  - loss:MatryoshkaLoss
  - loss:MultipleNegativesRankingLoss
base_model: BAAI/bge-base-en
widget:
  - source_sentence: >-
      Employee health, safety and wellness are top priorities at Hasbro. We
      support our colleagues’ well-being, which includes mental, physical and
      financial wellness, through a number of programs, including: robust
      employee assistance programs, childcare solutions, and a commitment to
      flexible work arrangements.
    sentences:
      - >-
        What percentage of the total annual net trade sales did the sales
        returns reserve represent for the company during each of the fiscal
        years 2023, 2022, and 2021?
      - How does Hasbro support the wellness of its employees?
      - >-
        What was the conclusion of the Company's review regarding the impact of
        the American Rescue Plan, the Consolidated Appropriations Act, 2021, and
        related tax provisions on its business for the fiscal year ended June
        30, 2023?
  - source_sentence: >-
      The Company has a minority market share in the global smartphone, personal
      computer and tablet markets. The Company faces substantial competition in
      these markets from companies that have significant technical, marketing,
      distribution and other resources, as well as established hardware,
      software and digital content supplier relationships. In addition, some of
      the Company’s competitors have broader product lines, lower-priced
      products and a larger installed base of active devices. Competition has
      been particularly intense as competitors have aggressively cut prices and
      lowered product margins.
    sentences:
      - >-
        When did The Hershey Company declare the dividend that was paid on March
        15, 2023?
      - >-
        What factors contribute to the Company facing substantial competition in
        the markets for smartphones, personal computers, and tablets?
      - How is goodwill impairment analyzed?
  - source_sentence: >-
      During fiscal 2022, there were cash payments of $6.7 billion for
      repurchases of common stock through open market purchases.
    sentences:
      - >-
        What was the value of cash payments for common stock repurchases through
        open market purchases during fiscal 2022?
      - >-
        How much did the Compute & Networking segment's gross margin decrease in
        fiscal year 2023?
      - What different methods does Amazon use to engage and retain employees?
  - source_sentence: >-
      Walmart Luminate provides a suite of data products for merchants and
      suppliers.
    sentences:
      - >-
        What pages do the Consolidated Financial Statements and their
        accompanying Notes and reports appear on in the document?
      - >-
        What was the percentage change in NYSE total cash handled volume from
        2022 to 2023?
      - What is the function of Walmart Luminate?
  - source_sentence: >-
      Item 8. Financial Statements and Supplementary Data. The Consolidated
      Financial Statements, together with the Notes thereto and the report
      thereon dated February 16, 2024, of PricewaterhouseCoopers LLP, the Firm’s
      independent registered public accounting firm (PCAOB ID 238).
    sentences:
      - What type of data does Item 8 in a financial document contain?
      - >-
        How did the assumptions and estimates used for assessing the fair value
        of reporting units potentially impact the company's financial
        statements?
      - >-
        What factors are considered when making estimates for financial
        statements?
pipeline_tag: sentence-similarity
library_name: sentence-transformers
metrics:
  - cosine_accuracy@1
  - cosine_accuracy@3
  - cosine_accuracy@5
  - cosine_accuracy@10
  - cosine_precision@1
  - cosine_precision@3
  - cosine_precision@5
  - cosine_precision@10
  - cosine_recall@1
  - cosine_recall@3
  - cosine_recall@5
  - cosine_recall@10
  - cosine_ndcg@10
  - cosine_mrr@10
  - cosine_map@100
model-index:
  - name: BGE base Financial Matryoshka
    results:
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: dim 768
          type: dim_768
        metrics:
          - type: cosine_accuracy@1
            value: 0.20411392405063292
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.39082278481012656
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.45569620253164556
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.5427215189873418
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.20411392405063292
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.1302742616033755
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.0911392405063291
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.054272151898734175
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.20411392405063292
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.39082278481012656
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.45569620253164556
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.5427215189873418
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.3712962481916349
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.31667482921438606
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.32569334518419213
            name: Cosine Map@100
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: dim 512
          type: dim_512
        metrics:
          - type: cosine_accuracy@1
            value: 0.1787974683544304
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.38449367088607594
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.44936708860759494
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.5221518987341772
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.1787974683544304
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.1281645569620253
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.08987341772151898
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.05221518987341772
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.1787974683544304
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.38449367088607594
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.44936708860759494
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.5221518987341772
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.35214780800723905
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.2974972372915411
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.30719274754259535
            name: Cosine Map@100
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: dim 256
          type: dim_256
        metrics:
          - type: cosine_accuracy@1
            value: 0.17563291139240506
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.33860759493670883
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.3924050632911392
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.49683544303797467
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.17563291139240506
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.11286919831223628
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.07848101265822786
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.04968354430379747
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.17563291139240506
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.33860759493670883
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.3924050632911392
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.49683544303797467
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.32777016757909155
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.2748675155716295
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.2839854758498125
            name: Cosine Map@100
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: dim 128
          type: dim_128
        metrics:
          - type: cosine_accuracy@1
            value: 0.13449367088607594
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.27689873417721517
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.34335443037974683
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.40189873417721517
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.13449367088607594
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.09229957805907173
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.06867088607594937
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.04018987341772152
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.13449367088607594
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.27689873417721517
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.34335443037974683
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.40189873417721517
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.2642535058721437
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.2206462226240707
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.2315340997045677
            name: Cosine Map@100
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: dim 64
          type: dim_64
        metrics:
          - type: cosine_accuracy@1
            value: 0.08544303797468354
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.19462025316455697
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.24841772151898733
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.31645569620253167
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.08544303797468354
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.06487341772151899
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.04968354430379747
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.031645569620253174
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.08544303797468354
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.19462025316455697
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.24841772151898733
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.31645569620253167
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.19364593797751115
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.15531381856540089
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.16408720453627956
            name: Cosine Map@100

BGE base Financial Matryoshka

This is a sentence-transformers model finetuned from BAAI/bge-base-en on the json 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: BAAI/bge-base-en
• Maximum Sequence Length: 512 tokens
• Output Dimensionality: 768 dimensions
• Similarity Function: Cosine Similarity
• Training Dataset:
  • json
• Language: en
• License: apache-2.0

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': True}) with Transformer model: BertModel 
  (1): Pooling({'word_embedding_dimension': 768, '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): Normalize()
)

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("RK-1235/bge-base-FIR-matryoshka-BASELINE-10epochs-FT")
# Run inference
sentences = [
    'Item 8. Financial Statements and Supplementary Data. The Consolidated Financial Statements, together with the Notes thereto and the report thereon dated February 16, 2024, of PricewaterhouseCoopers LLP, the Firm’s independent registered public accounting firm (PCAOB ID 238).',
    'What type of data does Item 8 in a financial document contain?',
    "How did the assumptions and estimates used for assessing the fair value of reporting units potentially impact the company's financial statements?",
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 768]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities.shape)
# [3, 3]

Evaluation

Metrics

Information Retrieval

• Dataset: dim_768
• Evaluated with InformationRetrievalEvaluator with these parameters:

  {
      "truncate_dim": 768
  }
  

Metric	Value
cosine_accuracy@1	0.2041
cosine_accuracy@3	0.3908
cosine_accuracy@5	0.4557
cosine_accuracy@10	0.5427
cosine_precision@1	0.2041
cosine_precision@3	0.1303
cosine_precision@5	0.0911
cosine_precision@10	0.0543
cosine_recall@1	0.2041
cosine_recall@3	0.3908
cosine_recall@5	0.4557
cosine_recall@10	0.5427
cosine_ndcg@10	0.3713
cosine_mrr@10	0.3167
cosine_map@100	0.3257

Information Retrieval

• Dataset: dim_512
• Evaluated with InformationRetrievalEvaluator with these parameters:

  {
      "truncate_dim": 512
  }
  

Metric	Value
cosine_accuracy@1	0.1788
cosine_accuracy@3	0.3845
cosine_accuracy@5	0.4494
cosine_accuracy@10	0.5222
cosine_precision@1	0.1788
cosine_precision@3	0.1282
cosine_precision@5	0.0899
cosine_precision@10	0.0522
cosine_recall@1	0.1788
cosine_recall@3	0.3845
cosine_recall@5	0.4494
cosine_recall@10	0.5222
cosine_ndcg@10	0.3521
cosine_mrr@10	0.2975
cosine_map@100	0.3072

Information Retrieval

• Dataset: dim_256
• Evaluated with InformationRetrievalEvaluator with these parameters:

  {
      "truncate_dim": 256
  }
  

Metric	Value
cosine_accuracy@1	0.1756
cosine_accuracy@3	0.3386
cosine_accuracy@5	0.3924
cosine_accuracy@10	0.4968
cosine_precision@1	0.1756
cosine_precision@3	0.1129
cosine_precision@5	0.0785
cosine_precision@10	0.0497
cosine_recall@1	0.1756
cosine_recall@3	0.3386
cosine_recall@5	0.3924
cosine_recall@10	0.4968
cosine_ndcg@10	0.3278
cosine_mrr@10	0.2749
cosine_map@100	0.284

Information Retrieval

• Dataset: dim_128
• Evaluated with InformationRetrievalEvaluator with these parameters:

  {
      "truncate_dim": 128
  }
  

Metric	Value
cosine_accuracy@1	0.1345
cosine_accuracy@3	0.2769
cosine_accuracy@5	0.3434
cosine_accuracy@10	0.4019
cosine_precision@1	0.1345
cosine_precision@3	0.0923
cosine_precision@5	0.0687
cosine_precision@10	0.0402
cosine_recall@1	0.1345
cosine_recall@3	0.2769
cosine_recall@5	0.3434
cosine_recall@10	0.4019
cosine_ndcg@10	0.2643
cosine_mrr@10	0.2206
cosine_map@100	0.2315

Information Retrieval

• Dataset: dim_64
• Evaluated with InformationRetrievalEvaluator with these parameters:

  {
      "truncate_dim": 64
  }
  

Metric	Value
cosine_accuracy@1	0.0854
cosine_accuracy@3	0.1946
cosine_accuracy@5	0.2484
cosine_accuracy@10	0.3165
cosine_precision@1	0.0854
cosine_precision@3	0.0649
cosine_precision@5	0.0497
cosine_precision@10	0.0316
cosine_recall@1	0.0854
cosine_recall@3	0.1946
cosine_recall@5	0.2484
cosine_recall@10	0.3165
cosine_ndcg@10	0.1936
cosine_mrr@10	0.1553
cosine_map@100	0.1641

Training Details

Training Dataset

json

• Dataset: json
• Size: 6,300 training samples
• Columns: positive and anchor
• Approximate statistics based on the first 1000 samples:

  	positive	anchor
  type	string	string
  details	min: 6 tokens mean: 46.06 tokens max: 371 tokens	min: 8 tokens mean: 20.8 tokens max: 51 tokens

• Samples:

  positive	anchor
  As of December 31, 2023, a 5 percent change in the contingent consideration liabilities would result in a change in income before income taxes of $5.2 million.	How would a 5% change in the contingent consideration liabilities impact income before taxes as of December 31, 2023?
  NIKE, Inc.'s principal business activity involves the design, development, and worldwide marketing and selling of athletic footwear, apparel, equipment, accessories, and services.	What is the principal business activity of NIKE, Inc.?
  During 2023, changes in foreign currencies relative to the U.S. dollar negatively impacted net sales by approximately $3,484, 156 basis points, compared to 2022, attributable to our Canadian and Other International operations.	What was the overall impact of foreign currencies on net sales in 2023?

• Loss: MatryoshkaLoss with these parameters:

  {
      "loss": "MultipleNegativesRankingLoss",
      "matryoshka_dims": [
          768,
          512,
          256,
          128,
          64
      ],
      "matryoshka_weights": [
          1,
          1,
          1,
          1,
          1
      ],
      "n_dims_per_step": -1
  }
  

Training Hyperparameters

Non-Default Hyperparameters

• eval_strategy: epoch
• per_device_train_batch_size: 32
• per_device_eval_batch_size: 16
• gradient_accumulation_steps: 16
• learning_rate: 2e-05
• num_train_epochs: 10
• lr_scheduler_type: cosine
• warmup_ratio: 0.1
• bf16: True
• tf32: True
• load_best_model_at_end: True
• optim: adamw_torch_fused
• batch_sampler: no_duplicates

All Hyperparameters

Click to expand

• overwrite_output_dir: False
• do_predict: False
• eval_strategy: epoch
• prediction_loss_only: True
• per_device_train_batch_size: 32
• per_device_eval_batch_size: 16
• per_gpu_train_batch_size: None
• per_gpu_eval_batch_size: None
• gradient_accumulation_steps: 16
• 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: 10
• max_steps: -1
• lr_scheduler_type: cosine
• 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: True
• fp16: False
• fp16_opt_level: O1
• half_precision_backend: auto
• bf16_full_eval: False
• fp16_full_eval: False
• tf32: True
• 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: True
• 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_fused
• 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

Training Logs

Epoch	Step	Training Loss	dim_768_cosine_ndcg@10	dim_512_cosine_ndcg@10	dim_256_cosine_ndcg@10	dim_128_cosine_ndcg@10	dim_64_cosine_ndcg@10
0.8122	10	89.0763	-	-	-	-	-
1.0	13	-	0.4022	0.3835	0.3505	0.2911	0.1835
1.5685	20	36.7538	-	-	-	-	-
2.0	26	-	0.3725	0.3591	0.3218	0.2753	0.1978
2.3249	30	17.7869	-	-	-	-	-
3.0	39	-	0.3680	0.3558	0.3284	0.2638	0.2000
3.0812	40	10.5904	-	-	-	-	-
3.8934	50	7.9568	-	-	-	-	-
4.0	52	-	0.3634	0.3487	0.3245	0.2589	0.1999
4.6497	60	5.5002	-	-	-	-	-
5.0	65	-	0.3648	0.3551	0.3211	0.2595	0.1968
5.4061	70	5.3314	-	-	-	-	-
6.0	78	-	0.3693	0.3548	0.3257	0.2621	0.1977
6.1624	80	4.6165	-	-	-	-	-
6.9746	90	4.7811	-	-	-	-	-
7.0	91	-	0.3698	0.3532	0.3293	0.2637	0.1954
7.7310	100	3.978	-	-	-	-	-
8.0	104	-	0.3713	0.3523	0.3273	0.2637	0.1952
8.4873	110	4.1624	-	-	-	-	-
9.0	117	-	0.3707	0.3517	0.3264	0.2639	0.1949
9.2437	120	3.4956	-	-	-	-	-
10.0	130	3.9661	0.3713	0.3521	0.3278	0.2643	0.1936

• The bold row denotes the saved checkpoint.

Framework Versions

• Python: 3.10.12
• Sentence Transformers: 4.1.0
• Transformers: 4.52.2
• PyTorch: 2.6.0+cu124
• Accelerate: 1.7.0
• Datasets: 3.6.0
• 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",
}

MatryoshkaLoss

@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

@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}
}