metadata

language:
  - en
library_name: sentence-transformers
tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - dataset_size:10K<n<100K
  - loss:MatryoshkaLoss
  - loss:MultipleNegativesRankingLoss
base_model: distilbert/distilroberta-base
metrics:
  - pearson_cosine
  - spearman_cosine
  - pearson_manhattan
  - spearman_manhattan
  - pearson_euclidean
  - spearman_euclidean
  - pearson_dot
  - spearman_dot
  - pearson_max
  - spearman_max
widget:
  - source_sentence: I hate to.
    sentences:
      - um well i hate to yes i do
      - The dogs are sleeping.
      - The child is running
  - source_sentence: He gave in.
    sentences:
      - Then he gave in.
      - Two men stand outdoors.
      - A girl is outdoors.
  - source_sentence: um pardon me
    sentences:
      - Excuse me.
      - The man has shorts on.
      - The child is running
  - source_sentence: He shrugged.
    sentences:
      - Then he shrugged.
      - A woman pulls a child.
      - There are three workers
  - source_sentence: Loire Valley
    sentences:
      - The Valley of Loire.
      - The people are adults.
      - There are three workers
pipeline_tag: sentence-similarity
model-index:
  - name: SentenceTransformer based on distilbert/distilroberta-base
    results:
      - task:
          type: semantic-similarity
          name: Semantic Similarity
        dataset:
          name: sts dev 768
          type: sts-dev-768
        metrics:
          - type: pearson_cosine
            value: 0.8170160257039426
            name: Pearson Cosine
          - type: spearman_cosine
            value: 0.8255975460077839
            name: Spearman Cosine
          - type: pearson_manhattan
            value: 0.8085164465261383
            name: Pearson Manhattan
          - type: spearman_manhattan
            value: 0.8093268377073419
            name: Spearman Manhattan
          - type: pearson_euclidean
            value: 0.8090075094521302
            name: Pearson Euclidean
          - type: spearman_euclidean
            value: 0.8098830595985685
            name: Spearman Euclidean
          - type: pearson_dot
            value: 0.5787845464363458
            name: Pearson Dot
          - type: spearman_dot
            value: 0.6050816410949579
            name: Spearman Dot
          - type: pearson_max
            value: 0.8170160257039426
            name: Pearson Max
          - type: spearman_max
            value: 0.8255975460077839
            name: Spearman Max
      - task:
          type: semantic-similarity
          name: Semantic Similarity
        dataset:
          name: sts dev 512
          type: sts-dev-512
        metrics:
          - type: pearson_cosine
            value: 0.8217137626363546
            name: Pearson Cosine
          - type: spearman_cosine
            value: 0.8277309683690247
            name: Spearman Cosine
          - type: pearson_manhattan
            value: 0.8085782690288572
            name: Pearson Manhattan
          - type: spearman_manhattan
            value: 0.8090394046170676
            name: Spearman Manhattan
          - type: pearson_euclidean
            value: 0.8096391371860112
            name: Pearson Euclidean
          - type: spearman_euclidean
            value: 0.8097335476296557
            name: Spearman Euclidean
          - type: pearson_dot
            value: 0.6360180046118354
            name: Pearson Dot
          - type: spearman_dot
            value: 0.6594419705525
            name: Spearman Dot
          - type: pearson_max
            value: 0.8217137626363546
            name: Pearson Max
          - type: spearman_max
            value: 0.8277309683690247
            name: Spearman Max
      - task:
          type: semantic-similarity
          name: Semantic Similarity
        dataset:
          name: sts dev 256
          type: sts-dev-256
        metrics:
          - type: pearson_cosine
            value: 0.8178918632167268
            name: Pearson Cosine
          - type: spearman_cosine
            value: 0.8257042835854954
            name: Spearman Cosine
          - type: pearson_manhattan
            value: 0.8072136828107425
            name: Pearson Manhattan
          - type: spearman_manhattan
            value: 0.8080863714656285
            name: Spearman Manhattan
          - type: pearson_euclidean
            value: 0.8075560498740989
            name: Pearson Euclidean
          - type: spearman_euclidean
            value: 0.8082369652944293
            name: Spearman Euclidean
          - type: pearson_dot
            value: 0.6315912070915749
            name: Pearson Dot
          - type: spearman_dot
            value: 0.6530916665342353
            name: Spearman Dot
          - type: pearson_max
            value: 0.8178918632167268
            name: Pearson Max
          - type: spearman_max
            value: 0.8257042835854954
            name: Spearman Max
      - task:
          type: semantic-similarity
          name: Semantic Similarity
        dataset:
          name: sts dev 128
          type: sts-dev-128
        metrics:
          - type: pearson_cosine
            value: 0.8083653645114982
            name: Pearson Cosine
          - type: spearman_cosine
            value: 0.8195265949387541
            name: Spearman Cosine
          - type: pearson_manhattan
            value: 0.8017122988316997
            name: Pearson Manhattan
          - type: spearman_manhattan
            value: 0.8044101635226892
            name: Spearman Manhattan
          - type: pearson_euclidean
            value: 0.8004513898889509
            name: Pearson Euclidean
          - type: spearman_euclidean
            value: 0.8032518581337287
            name: Spearman Euclidean
          - type: pearson_dot
            value: 0.6054920626583514
            name: Pearson Dot
          - type: spearman_dot
            value: 0.632383085342124
            name: Spearman Dot
          - type: pearson_max
            value: 0.8083653645114982
            name: Pearson Max
          - type: spearman_max
            value: 0.8195265949387541
            name: Spearman Max
      - task:
          type: semantic-similarity
          name: Semantic Similarity
        dataset:
          name: sts dev 64
          type: sts-dev-64
        metrics:
          - type: pearson_cosine
            value: 0.796901729599783
            name: Pearson Cosine
          - type: spearman_cosine
            value: 0.8138253855008615
            name: Spearman Cosine
          - type: pearson_manhattan
            value: 0.7907415690444286
            name: Pearson Manhattan
          - type: spearman_manhattan
            value: 0.7953162414756638
            name: Spearman Manhattan
          - type: pearson_euclidean
            value: 0.7886601701724113
            name: Pearson Euclidean
          - type: spearman_euclidean
            value: 0.7935316804874565
            name: Spearman Euclidean
          - type: pearson_dot
            value: 0.5369879256914492
            name: Pearson Dot
          - type: spearman_dot
            value: 0.5528888392757544
            name: Spearman Dot
          - type: pearson_max
            value: 0.796901729599783
            name: Pearson Max
          - type: spearman_max
            value: 0.8138253855008615
            name: Spearman Max
      - task:
          type: semantic-similarity
          name: Semantic Similarity
        dataset:
          name: sts test 768
          type: sts-test-768
        metrics:
          - type: pearson_cosine
            value: 0.7830303669378891
            name: Pearson Cosine
          - type: spearman_cosine
            value: 0.7773625997426432
            name: Spearman Cosine
          - type: pearson_manhattan
            value: 0.7760379804905847
            name: Pearson Manhattan
          - type: spearman_manhattan
            value: 0.7571500188418279
            name: Spearman Manhattan
          - type: pearson_euclidean
            value: 0.776793987384272
            name: Pearson Euclidean
          - type: spearman_euclidean
            value: 0.7576769993000992
            name: Spearman Euclidean
          - type: pearson_dot
            value: 0.5696917713192656
            name: Pearson Dot
          - type: spearman_dot
            value: 0.5537799075128554
            name: Spearman Dot
          - type: pearson_max
            value: 0.7830303669378891
            name: Pearson Max
          - type: spearman_max
            value: 0.7773625997426432
            name: Spearman Max
      - task:
          type: semantic-similarity
          name: Semantic Similarity
        dataset:
          name: sts test 512
          type: sts-test-512
        metrics:
          - type: pearson_cosine
            value: 0.7907973459486692
            name: Pearson Cosine
          - type: spearman_cosine
            value: 0.7782644020369065
            name: Spearman Cosine
          - type: pearson_manhattan
            value: 0.7764511872615909
            name: Pearson Manhattan
          - type: spearman_manhattan
            value: 0.7566408579053339
            name: Spearman Manhattan
          - type: pearson_euclidean
            value: 0.7782953766500842
            name: Pearson Euclidean
          - type: spearman_euclidean
            value: 0.7586949913092054
            name: Spearman Euclidean
          - type: pearson_dot
            value: 0.6258186284156914
            name: Pearson Dot
          - type: spearman_dot
            value: 0.6181773438089058
            name: Spearman Dot
          - type: pearson_max
            value: 0.7907973459486692
            name: Pearson Max
          - type: spearman_max
            value: 0.7782644020369065
            name: Spearman Max
      - task:
          type: semantic-similarity
          name: Semantic Similarity
        dataset:
          name: sts test 256
          type: sts-test-256
        metrics:
          - type: pearson_cosine
            value: 0.790808685432137
            name: Pearson Cosine
          - type: spearman_cosine
            value: 0.7795179076946794
            name: Spearman Cosine
          - type: pearson_manhattan
            value: 0.7755456692602101
            name: Pearson Manhattan
          - type: spearman_manhattan
            value: 0.7562532907515199
            name: Spearman Manhattan
          - type: pearson_euclidean
            value: 0.7781380668198093
            name: Pearson Euclidean
          - type: spearman_euclidean
            value: 0.7588258189898521
            name: Spearman Euclidean
          - type: pearson_dot
            value: 0.6154250444753552
            name: Pearson Dot
          - type: spearman_dot
            value: 0.6086811490786919
            name: Spearman Dot
          - type: pearson_max
            value: 0.790808685432137
            name: Pearson Max
          - type: spearman_max
            value: 0.7795179076946794
            name: Spearman Max
      - task:
          type: semantic-similarity
          name: Semantic Similarity
        dataset:
          name: sts test 128
          type: sts-test-128
        metrics:
          - type: pearson_cosine
            value: 0.7834894934855864
            name: Pearson Cosine
          - type: spearman_cosine
            value: 0.774163149418093
            name: Spearman Cosine
          - type: pearson_manhattan
            value: 0.7698790484447937
            name: Pearson Manhattan
          - type: spearman_manhattan
            value: 0.7517016204558167
            name: Spearman Manhattan
          - type: pearson_euclidean
            value: 0.7725214617886543
            name: Pearson Euclidean
          - type: spearman_euclidean
            value: 0.7540743359385147
            name: Spearman Euclidean
          - type: pearson_dot
            value: 0.5993484722642376
            name: Pearson Dot
          - type: spearman_dot
            value: 0.5948446351721051
            name: Spearman Dot
          - type: pearson_max
            value: 0.7834894934855864
            name: Pearson Max
          - type: spearman_max
            value: 0.774163149418093
            name: Spearman Max
      - task:
          type: semantic-similarity
          name: Semantic Similarity
        dataset:
          name: sts test 64
          type: sts-test-64
        metrics:
          - type: pearson_cosine
            value: 0.76979297806493
            name: Pearson Cosine
          - type: spearman_cosine
            value: 0.7694166074528175
            name: Spearman Cosine
          - type: pearson_manhattan
            value: 0.7566840706659232
            name: Pearson Manhattan
          - type: spearman_manhattan
            value: 0.7416860573345465
            name: Spearman Manhattan
          - type: pearson_euclidean
            value: 0.7597470663104835
            name: Pearson Euclidean
          - type: spearman_euclidean
            value: 0.744530141432067
            name: Spearman Euclidean
          - type: pearson_dot
            value: 0.5373925875692315
            name: Pearson Dot
          - type: spearman_dot
            value: 0.5338006780754848
            name: Spearman Dot
          - type: pearson_max
            value: 0.76979297806493
            name: Pearson Max
          - type: spearman_max
            value: 0.7694166074528175
            name: Spearman Max

SentenceTransformer based on distilbert/distilroberta-base

This is a sentence-transformers model finetuned from distilbert/distilroberta-base on the sentence-transformers/all-nli 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/distilroberta-base
Maximum Sequence Length: 512 tokens
Output Dimensionality: 768 tokens
Similarity Function: Cosine Similarity
Training Dataset:
- sentence-transformers/all-nli
Language: en

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}) with Transformer model: RobertaModel 
  (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("eagle0504/distilroberta-base-nli-matryoshka")
# Run inference
sentences = [
    'Loire Valley',
    'The Valley of Loire.',
    'The people are adults.',
]
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

Semantic Similarity

Dataset: sts-dev-768
Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_cosine	0.817
spearman_cosine	0.8256
pearson_manhattan	0.8085
spearman_manhattan	0.8093
pearson_euclidean	0.809
spearman_euclidean	0.8099
pearson_dot	0.5788
spearman_dot	0.6051
pearson_max	0.817
spearman_max	0.8256

Semantic Similarity

Dataset: sts-dev-512
Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_cosine	0.8217
spearman_cosine	0.8277
pearson_manhattan	0.8086
spearman_manhattan	0.809
pearson_euclidean	0.8096
spearman_euclidean	0.8097
pearson_dot	0.636
spearman_dot	0.6594
pearson_max	0.8217
spearman_max	0.8277

Semantic Similarity

Dataset: sts-dev-256
Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_cosine	0.8179
spearman_cosine	0.8257
pearson_manhattan	0.8072
spearman_manhattan	0.8081
pearson_euclidean	0.8076
spearman_euclidean	0.8082
pearson_dot	0.6316
spearman_dot	0.6531
pearson_max	0.8179
spearman_max	0.8257

Semantic Similarity

Dataset: sts-dev-128
Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_cosine	0.8084
spearman_cosine	0.8195
pearson_manhattan	0.8017
spearman_manhattan	0.8044
pearson_euclidean	0.8005
spearman_euclidean	0.8033
pearson_dot	0.6055
spearman_dot	0.6324
pearson_max	0.8084
spearman_max	0.8195

Semantic Similarity

Dataset: sts-dev-64
Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_cosine	0.7969
spearman_cosine	0.8138
pearson_manhattan	0.7907
spearman_manhattan	0.7953
pearson_euclidean	0.7887
spearman_euclidean	0.7935
pearson_dot	0.537
spearman_dot	0.5529
pearson_max	0.7969
spearman_max	0.8138

Semantic Similarity

Dataset: sts-test-768
Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_cosine	0.783
spearman_cosine	0.7774
pearson_manhattan	0.776
spearman_manhattan	0.7572
pearson_euclidean	0.7768
spearman_euclidean	0.7577
pearson_dot	0.5697
spearman_dot	0.5538
pearson_max	0.783
spearman_max	0.7774

Semantic Similarity

Dataset: sts-test-512
Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_cosine	0.7908
spearman_cosine	0.7783
pearson_manhattan	0.7765
spearman_manhattan	0.7566
pearson_euclidean	0.7783
spearman_euclidean	0.7587
pearson_dot	0.6258
spearman_dot	0.6182
pearson_max	0.7908
spearman_max	0.7783

Semantic Similarity

Dataset: sts-test-256
Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_cosine	0.7908
spearman_cosine	0.7795
pearson_manhattan	0.7755
spearman_manhattan	0.7563
pearson_euclidean	0.7781
spearman_euclidean	0.7588
pearson_dot	0.6154
spearman_dot	0.6087
pearson_max	0.7908
spearman_max	0.7795

Semantic Similarity

Dataset: sts-test-128
Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_cosine	0.7835
spearman_cosine	0.7742
pearson_manhattan	0.7699
spearman_manhattan	0.7517
pearson_euclidean	0.7725
spearman_euclidean	0.7541
pearson_dot	0.5993
spearman_dot	0.5948
pearson_max	0.7835
spearman_max	0.7742

Semantic Similarity

Dataset: sts-test-64
Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_cosine	0.7698
spearman_cosine	0.7694
pearson_manhattan	0.7567
spearman_manhattan	0.7417
pearson_euclidean	0.7597
spearman_euclidean	0.7445
pearson_dot	0.5374
spearman_dot	0.5338
pearson_max	0.7698
spearman_max	0.7694

Training Details

Training Dataset

sentence-transformers/all-nli

Dataset: sentence-transformers/all-nli at d482672
Size: 10,000 training samples
Columns: anchor, positive, and negative

Approximate statistics based on the first 1000 samples:

	anchor	positive	negative
type	string	string	string
details	min: 4 tokens mean: 18.26 tokens max: 88 tokens	min: 4 tokens mean: 11.6 tokens max: 36 tokens	min: 4 tokens mean: 12.09 tokens max: 38 tokens

Samples:

anchor	positive	negative
`Side view of a female triathlete during the run.`	`A woman runs`	`A man sits`
`Confused person standing in the middle of the trolley tracks trying to figure out the signs.`	`A person is on the tracks.`	`A man sits in an airplane.`
`A woman in a black shirt, jean shorts and white tennis shoes is bowling.`	`A woman is bowling in casual clothes`	`A woman bowling wins an outfit of clothes`

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
}

Evaluation Dataset

sentence-transformers/all-nli

Dataset: sentence-transformers/all-nli at d482672
Size: 6,584 evaluation samples
Columns: anchor, positive, and negative

Approximate statistics based on the first 1000 samples:

	anchor	positive	negative
type	string	string	string
details	min: 6 tokens mean: 18.02 tokens max: 66 tokens	min: 5 tokens mean: 9.81 tokens max: 29 tokens	min: 5 tokens mean: 10.37 tokens max: 29 tokens

Samples:

anchor	positive	negative
`Two women are embracing while holding to go packages.`	`Two woman are holding packages.`	`The men are fighting outside a deli.`
`Two young children in blue jerseys, one with the number 9 and one with the number 2 are standing on wooden steps in a bathroom and washing their hands in a sink.`	`Two kids in numbered jerseys wash their hands.`	`Two kids in jackets walk to school.`
`A man selling donuts to a customer during a world exhibition event held in the city of Angeles`	`A man selling donuts to a customer.`	`A woman drinks her coffee in a small cafe.`

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: steps
per_device_train_batch_size: 128
per_device_eval_batch_size: 128
num_train_epochs: 1
warmup_ratio: 0.1
fp16: 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: 128
per_device_eval_batch_size: 128
per_gpu_train_batch_size: None
per_gpu_eval_batch_size: None
gradient_accumulation_steps: 1
eval_accumulation_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: 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: {'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: False
hub_always_push: False
gradient_checkpointing: False
gradient_checkpointing_kwargs: None
include_inputs_for_metrics: False
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
batch_sampler: no_duplicates
multi_dataset_batch_sampler: proportional

Training Logs

Epoch	Step	Training Loss	loss	sts-dev-128_spearman_cosine	sts-dev-256_spearman_cosine	sts-dev-512_spearman_cosine	sts-dev-64_spearman_cosine	sts-dev-768_spearman_cosine	sts-test-128_spearman_cosine	sts-test-256_spearman_cosine	sts-test-512_spearman_cosine	sts-test-64_spearman_cosine	sts-test-768_spearman_cosine
0.3797	30	15.8875	6.1089	0.8036	0.8123	0.8143	0.8010	0.8076	-	-	-	-	-
0.7595	60	7.4874	5.0189	0.8195	0.8257	0.8277	0.8138	0.8256	-	-	-	-	-
1.0	79	-	-	-	-	-	-	-	0.7742	0.7795	0.7783	0.7694	0.7774

Framework Versions

Python: 3.10.12
Sentence Transformers: 3.0.0
Transformers: 4.41.1
PyTorch: 2.3.0+cu121
Accelerate: 0.30.1
Datasets: 2.19.1
Tokenizers: 0.19.1

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}
}