README.md

metadata

language:
  - en
license: apache-2.0
tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - generated_from_trainer
  - dataset_size:321
  - loss:MatryoshkaLoss
  - loss:MultipleNegativesRankingLoss
base_model: nomic-ai/modernbert-embed-base
widget:
  - source_sentence: Since what year have they been married?
    sentences:
      - >-
        Graph: Team Coco Knowledge Graph

        Node ID: 2015_conan_cuba

        Category: events

        Name: Conan in Cuba

        Type: Event


        Description: Conan O'Brien traveled to Havana to film a historic
        episode—the first by an American late-night host in over 50 years—part
        of his 'Conan Without Borders' specials.


        Relationships:

        - Host conan_obrien

        - Occurred during conan_tbs
      - >-
        Description: Liza Powel O'Brien is an American playwright and podcast
        host. She met Conan O'Brien in 2000 while working at an advertising
        agency, and they married in 2002. She has written numerous plays staged
        at theaters like the Geffen Playhouse and Ojai Playwrights Conference,
        and in 2022 she launched the history podcast "Significant Others" on
        Conan's Team Coco network.
      - |-
        Relationships:
        - Spouse conan_obrien (Strength: very strong)
          Description: Married since 2002; they have two children together.
        - Podcast host team_coco (Strength: moderate)
          Description: Hosts the "Significant Others" podcast under the Team Coco banner.
  - source_sentence: Which team produced Conan's final late night episode?
    sentences:
      - >-
        Graph: Team Coco Knowledge Graph

        Node ID: 2021_conan_finale

        Category: events

        Name: Conan's Final Late Night Episode

        Type: Event


        Description: The final episode of 'Conan' on TBS, marking the end of
        Conan O'Brien's 28-year run as a late-night host with heartfelt goodbyes
        and memorable comedy moments.


        Relationships:

        - Honoree conan_obrien

        - Participant andy_richter

        - Producer team_coco
      - >-
        References:

        - ([Conan O'Brien -
        Wikipedia](https://en.wikipedia.org/wiki/Conan_O%27Brien))

        - ([Andy Richter Net Worth | Celebrity Net
        Worth](https://www.celebritynetworth.com))
      - 'Description: Airing on SiriusXM''s Team Coco Radio channel.'
  - source_sentence: What type of document is referenced for the tour?
    sentences:
      - |-
        Relationships:
        - Late-night host conan_obrien (Strength: core talent)
          Description: Conan's break in late night came through NBC.
        - Production partner conaco (Strength: strong)
          Description: NBC worked with Conaco on Conan's shows.

        Awards and Recognitions:
        - Legacy of late-night programming
      - |-
        Major Events:
        - 1993 Joined 'Late Night' with Conan
        - 2009 Transitioned to 'The Tonight Show'
        - 2010 Concluded run as Conan's bandleader
      - >-
        References:

        - ([The Legally Prohibited from Being Funny on Television Tour -
        Wikipedia](https://en.wikipedia.org/wiki/The_Legally_Prohibited_from_Being_Funny_on_Television_Tour))
  - source_sentence: In what year did Triumph the Insult Comic Dog debut?
    sentences:
      - |-
        Relationships:
        - Host-guest (Prankster) conan_obrien (Strength: moderate)
          Description: Repeatedly played the 'Mac and Me' gag, to Conan's feigned exasperation.

        Major Events:
        - 2004 First Mac and Me Gag on 'Late Night'
        - 2021 Final TBS Show Prank cameo
      - >-
        Awards and Recognitions:

        - MFA in Fiction Writing from Columbia University

        - Playwright with works at the Geffen Playhouse and Ojai Playwrights
        Conference

        - Host of the "Significant Others" podcast (2022–present)
      - >-
        Graph: Team Coco Knowledge Graph

        Node ID: triumph_insult_comic_dog

        Category: creative works

        Name: Triumph the Insult Comic Dog

        Type: Puppet character


        Description: A recurring canine puppet character, voiced by Robert
        Smigel, that debuted on Conan's 'Late Night' in 1997, known for roasting
        celebrities and absurd humor.


        Relationships:

        - Creator/performer robert_smigel

        - Host platform conan_obrien
  - source_sentence: Who are the hosts of The Conan & Jordan Show?
    sentences:
      - |-
        Awards and Recognitions:
        - 7 Primetime Emmy nominations for writing on Conan's shows
        - 10 WGA Award nominations (with 2 wins)
        - 2 Daytime Emmy nominations for Animated Program performance

        Major Events:
        - 1993 Late Night Debut – Joined Conan's first show as sidekick.
        - 2000 Departure – Left 'Late Night' to pursue acting.
        - 2010 Tour & TBS Move – Reunited with Conan on the live tour and TBS.
      - >-
        Graph: Team Coco Knowledge Graph

        Node ID: the_conan_and_jordan_show

        Category: shows

        Name: The Conan & Jordan Show (radio program)

        Type: Show


        Description: A spin-off audio series on SiriusXM's Team Coco Radio,
        launched in 2023, featuring Conan O'Brien and Jordan Schlansky
        continuing their comedic odd-couple dynamic.
      - >-
        Major Events:

        - 2010 Premiere – 'Conan' debuted on TBS.

        - 2015 'Conan Without Borders' – International travel specials aired.

        - 2021 Finale – Conan ended his TBS run.


        References:

        - ([Conan O'Brien -
        Wikipedia](https://en.wikipedia.org/wiki/Conan_O%27Brien))
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: Fine-tuned with [QuicKB](https://github.com/ALucek/QuicKB)
    results:
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: dim 768
          type: dim_768
        metrics:
          - type: cosine_accuracy@1
            value: 0.7222222222222222
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.8611111111111112
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.9166666666666666
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.9444444444444444
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.7222222222222222
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.2870370370370371
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.18333333333333338
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.09444444444444446
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.7222222222222222
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.8611111111111112
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.9166666666666666
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.9444444444444444
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.8363985989991439
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.800925925925926
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.8041634291634291
            name: Cosine Map@100
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: dim 512
          type: dim_512
        metrics:
          - type: cosine_accuracy@1
            value: 0.6944444444444444
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.8888888888888888
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.9166666666666666
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.9722222222222222
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.6944444444444444
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.29629629629629634
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.18333333333333335
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.09722222222222224
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.6944444444444444
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.8888888888888888
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.9166666666666666
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.9722222222222222
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.8349701465406345
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.7909722222222222
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.791703216374269
            name: Cosine Map@100
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: dim 256
          type: dim_256
        metrics:
          - type: cosine_accuracy@1
            value: 0.6666666666666666
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.8611111111111112
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.9166666666666666
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.9444444444444444
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.6666666666666666
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.28703703703703703
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.18333333333333335
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.09444444444444446
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.6666666666666666
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.8611111111111112
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.9166666666666666
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.9444444444444444
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.8074890903790802
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.7627314814814814
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.7662037037037037
            name: Cosine Map@100
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: dim 128
          type: dim_128
        metrics:
          - type: cosine_accuracy@1
            value: 0.6388888888888888
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.8611111111111112
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.9166666666666666
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.9444444444444444
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.6388888888888888
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.2870370370370371
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.18333333333333338
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.09444444444444446
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.6388888888888888
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.8611111111111112
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.9166666666666666
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.9444444444444444
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.803777679552595
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.7574074074074074
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.7597654530591711
            name: Cosine Map@100
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: dim 64
          type: dim_64
        metrics:
          - type: cosine_accuracy@1
            value: 0.6111111111111112
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.7777777777777778
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.8333333333333334
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.9166666666666666
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.6111111111111112
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.2592592592592593
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.16666666666666669
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.09166666666666669
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.6111111111111112
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.7777777777777778
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.8333333333333334
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.9166666666666666
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.7608354868794361
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.7111441798941799
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.7139831037236697
            name: Cosine Map@100

Fine-tuned with QuicKB

This is a sentence-transformers model finetuned from nomic-ai/modernbert-embed-base. 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: nomic-ai/modernbert-embed-base
• Maximum Sequence Length: 1024 tokens
• Output Dimensionality: 768 dimensions
• Similarity Function: Cosine Similarity
• 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': 1024, 'do_lower_case': False}) with Transformer model: ModernBertModel 
  (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})
  (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("densonsmith/modernbert-embed-quickb")
# Run inference
sentences = [
    'Who are the hosts of The Conan & Jordan Show?',
    "Graph: Team Coco Knowledge Graph\nNode ID: the_conan_and_jordan_show\nCategory: shows\nName: The Conan & Jordan Show (radio program)\nType: Show\n\nDescription: A spin-off audio series on SiriusXM's Team Coco Radio, launched in 2023, featuring Conan O'Brien and Jordan Schlansky continuing their comedic odd-couple dynamic.",
    "Awards and Recognitions:\n- 7 Primetime Emmy nominations for writing on Conan's shows\n- 10 WGA Award nominations (with 2 wins)\n- 2 Daytime Emmy nominations for Animated Program performance\n\nMajor Events:\n- 1993 Late Night Debut – Joined Conan's first show as sidekick.\n- 2000 Departure – Left 'Late Night' to pursue acting.\n- 2010 Tour & TBS Move – Reunited with Conan on the live tour and TBS.",
]
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

• Datasets: dim_768, dim_512, dim_256, dim_128 and dim_64
• Evaluated with InformationRetrievalEvaluator

Metric	dim_768	dim_512	dim_256	dim_128	dim_64
cosine_accuracy@1	0.7222	0.6944	0.6667	0.6389	0.6111
cosine_accuracy@3	0.8611	0.8889	0.8611	0.8611	0.7778
cosine_accuracy@5	0.9167	0.9167	0.9167	0.9167	0.8333
cosine_accuracy@10	0.9444	0.9722	0.9444	0.9444	0.9167
cosine_precision@1	0.7222	0.6944	0.6667	0.6389	0.6111
cosine_precision@3	0.287	0.2963	0.287	0.287	0.2593
cosine_precision@5	0.1833	0.1833	0.1833	0.1833	0.1667
cosine_precision@10	0.0944	0.0972	0.0944	0.0944	0.0917
cosine_recall@1	0.7222	0.6944	0.6667	0.6389	0.6111
cosine_recall@3	0.8611	0.8889	0.8611	0.8611	0.7778
cosine_recall@5	0.9167	0.9167	0.9167	0.9167	0.8333
cosine_recall@10	0.9444	0.9722	0.9444	0.9444	0.9167
cosine_ndcg@10	0.8364	0.835	0.8075	0.8038	0.7608
cosine_mrr@10	0.8009	0.791	0.7627	0.7574	0.7111
cosine_map@100	0.8042	0.7917	0.7662	0.7598	0.714

Training Details

Training Dataset

Unnamed Dataset

• Size: 321 training samples
• Columns: anchor and positive
• Approximate statistics based on the first 321 samples:

  	anchor	positive
  type	string	string
  details	min: 7 tokens mean: 14.03 tokens max: 24 tokens	min: 15 tokens mean: 74.79 tokens max: 117 tokens

• Samples:

  anchor	positive
  What brand did Jeff Ross help establish?	Graph: Team Coco Knowledge Graph Node ID: jeff_ross_producer Category: people Name: Jeff Ross (Producer) Type: Person Description: Jeff Ross is a television producer who has served as Conan O'Brien's executive producer since 1993. He is a key business partner in Conan's media ventures and helped establish the Team Coco brand.
  In what year did Conan O'Brien launch the travel show 'Conan O'Brien Must Go'?	Description: Conan O'Brien is an American television host, comedian, writer, actor, and producer, best known for hosting late-night shows including "Late Night with Conan O'Brien", "The Tonight Show with Conan O'Brien", and "Conan". He also hosts the podcast "Conan O'Brien Needs a Friend" and, in 2024, launched the travel show "Conan O'Brien Must Go" on Max.
  What is the strength of the network TBS?	- Network tbs (Strength: parent) Description: TBS provided the platform for the show.

• 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: 4
• gradient_accumulation_steps: 16
• learning_rate: 2e-05
• num_train_epochs: 4
• 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: 4
• per_device_eval_batch_size: 8
• 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: 4
• 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
• dispatch_batches: None
• split_batches: 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
1.0	6	-	0.7909	0.8034	0.7711	0.7992	0.6908
1.7901	10	16.3044	-	-	-	-	-
2.0	12	-	0.8364	0.8294	0.8022	0.8038	0.7691
3.0	18	-	0.8364	0.8313	0.8059	0.7938	0.7599
3.3951	20	5.6348	0.8364	0.8350	0.8075	0.8038	0.7608

• The bold row denotes the saved checkpoint.

Framework Versions

• Python: 3.12.4
• Sentence Transformers: 3.4.0
• Transformers: 4.48.1
• PyTorch: 2.5.1+cu124
• Accelerate: 1.3.0
• Datasets: 3.2.0
• 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}
}