CloudlessSky/fullname_encoder_v1

SentenceTransformer based on intfloat/multilingual-e5-small

This is a sentence-transformers model finetuned from intfloat/multilingual-e5-small. It maps sentences & paragraphs to a 384-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: intfloat/multilingual-e5-small
• Maximum Sequence Length: 512 tokens
• Output Dimensionality: 384 dimensions
• Similarity Function: Cosine Similarity

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: BertModel 
  (1): Pooling({'word_embedding_dimension': 384, '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("CloudlessSky/fullname_encoder_v1")
# Run inference
sentences = [
    'ромазанов хусин алеевич',
    'роиазанов хусир алеевич',
    'морозов тимофей васильевич',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 384]

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

Training Details

Training Dataset

Unnamed Dataset

• Size: 2,000,000 training samples
• Columns: sentence1, sentence2, and label
• Approximate statistics based on the first 1000 samples:

  	sentence1	sentence2	label
  type	string	string	int
  details	min: 6 tokens mean: 10.9 tokens max: 19 tokens	min: 6 tokens mean: 11.86 tokens max: 27 tokens	0: ~48.70% 1: ~51.30%

• Samples:

  sentence1	sentence2	label
  лебедев александр арсентьевич	лебедев александр арсеньевич	0
  кирюхин сергей никитович	мухин сергей никитович	0
  додонов иван сидорович	сидоров иван спиридонович	0

• Loss: ContrastiveLoss with these parameters:

  {
      "distance_metric": "SiameseDistanceMetric.COSINE_DISTANCE",
      "margin": 0.5,
      "size_average": true
  }
  

Evaluation Dataset

Unnamed Dataset

• Size: 663,132 evaluation samples
• Columns: sentence1, sentence2, and label
• Approximate statistics based on the first 1000 samples:

  	sentence1	sentence2	label
  type	string	string	int
  details	min: 5 tokens mean: 10.92 tokens max: 22 tokens	min: 2 tokens mean: 11.77 tokens max: 24 tokens	0: ~50.20% 1: ~49.80%

• Samples:

  sentence1	sentence2	label
  иванисько ульян иванович	ульян иванисько иванович	1
  топычканов иван александрович	кабанов иван александрович	0
  джавадов камал джавад оглы	джавадов джавад камал оглы	1

• Loss: ContrastiveLoss with these parameters:

  {
      "distance_metric": "SiameseDistanceMetric.COSINE_DISTANCE",
      "margin": 0.5,
      "size_average": true
  }
  

Training Hyperparameters

Non-Default Hyperparameters

• eval_strategy: steps
• per_device_train_batch_size: 64
• per_device_eval_batch_size: 128
• num_train_epochs: 8

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: 128
• 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: 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: 8
• 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: False
• 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}
• tp_size: 0
• 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: batch_sampler
• multi_dataset_batch_sampler: proportional

Training Logs

Click to expand

Epoch	Step	Training Loss	Validation Loss
0.016	500	0.0143	-
0.032	1000	0.0119	-
0.048	1500	0.0112	-
0.064	2000	0.0108	-
0.08	2500	0.0105	-
0.096	3000	0.0098	-
0.112	3500	0.0101	-
0.128	4000	0.0096	-
0.144	4500	0.0096	-
0.16	5000	0.0093	-
0.176	5500	0.0093	-
0.192	6000	0.0089	-
0.208	6500	0.0087	-
0.224	7000	0.0086	-
0.24	7500	0.0084	-
0.256	8000	0.0083	-
0.272	8500	0.0082	-
0.288	9000	0.008	-
0.304	9500	0.0079	-
0.32	10000	0.008	0.0055
0.336	10500	0.0077	-
0.352	11000	0.0077	-
0.368	11500	0.0076	-
0.384	12000	0.0073	-
0.4	12500	0.0074	-
0.416	13000	0.0074	-
0.432	13500	0.0074	-
0.448	14000	0.0075	-
0.464	14500	0.0072	-
0.48	15000	0.007	-
0.496	15500	0.007	-
0.512	16000	0.0069	-
0.528	16500	0.0071	-
0.544	17000	0.0067	-
0.56	17500	0.007	-
0.576	18000	0.0068	-
0.592	18500	0.0068	-
0.608	19000	0.0069	-
0.624	19500	0.0067	-
0.64	20000	0.0067	0.0044
0.656	20500	0.0065	-
0.672	21000	0.0064	-
0.688	21500	0.0065	-
0.704	22000	0.0065	-
0.72	22500	0.0064	-
0.736	23000	0.0064	-
0.752	23500	0.0063	-
0.768	24000	0.0064	-
0.784	24500	0.0063	-
0.8	25000	0.0063	-
0.816	25500	0.0062	-
0.832	26000	0.0063	-
0.848	26500	0.0062	-
0.864	27000	0.006	-
0.88	27500	0.006	-
0.896	28000	0.006	-
0.912	28500	0.0061	-
0.928	29000	0.0061	-
0.944	29500	0.0059	-
0.96	30000	0.006	0.0039
0.976	30500	0.0059	-
0.992	31000	0.0059	-
1.008	31500	0.0057	-
1.024	32000	0.0056	-
1.04	32500	0.0056	-
1.056	33000	0.0056	-
1.072	33500	0.0056	-
1.088	34000	0.0056	-
1.104	34500	0.0054	-
1.12	35000	0.0056	-
1.1360	35500	0.0055	-
1.152	36000	0.0053	-
1.168	36500	0.0055	-
1.184	37000	0.0054	-
1.2	37500	0.0056	-
1.216	38000	0.0054	-
1.232	38500	0.0053	-
1.248	39000	0.0055	-
1.264	39500	0.0054	-
1.28	40000	0.0055	0.0037
1.296	40500	0.0053	-
1.312	41000	0.0052	-
1.328	41500	0.0052	-
1.3440	42000	0.0054	-
1.3600	42500	0.0055	-
1.376	43000	0.0053	-
1.392	43500	0.0054	-
1.408	44000	0.0053	-
1.424	44500	0.0053	-
1.44	45000	0.0053	-
1.456	45500	0.0053	-
1.472	46000	0.0051	-
1.488	46500	0.0053	-
1.504	47000	0.0052	-
1.52	47500	0.0052	-
1.536	48000	0.0052	-
1.552	48500	0.005	-
1.568	49000	0.005	-
1.584	49500	0.0052	-
1.6	50000	0.0053	0.0036
1.616	50500	0.0052	-
1.6320	51000	0.0052	-
1.6480	51500	0.005	-
1.6640	52000	0.0051	-
1.6800	52500	0.005	-
1.696	53000	0.0051	-
1.712	53500	0.0051	-
1.728	54000	0.005	-
1.744	54500	0.0049	-
1.76	55000	0.0049	-
1.776	55500	0.0049	-
1.792	56000	0.0051	-
1.808	56500	0.0049	-
1.8240	57000	0.0049	-
1.8400	57500	0.0051	-
1.8560	58000	0.0049	-
1.8720	58500	0.005	-
1.888	59000	0.0049	-
1.904	59500	0.0049	-
1.92	60000	0.0048	0.0034
1.936	60500	0.005	-
1.952	61000	0.0048	-
1.968	61500	0.0048	-
1.984	62000	0.0049	-
2.0	62500	0.0049	-
2.016	63000	0.0046	-
2.032	63500	0.0045	-
2.048	64000	0.0045	-
2.064	64500	0.0046	-
2.08	65000	0.0044	-
2.096	65500	0.0046	-
2.112	66000	0.0045	-
2.128	66500	0.0046	-
2.144	67000	0.0045	-
2.16	67500	0.0044	-
2.176	68000	0.0045	-
2.192	68500	0.0046	-
2.208	69000	0.0046	-
2.224	69500	0.0045	-
2.24	70000	0.0046	0.0033
2.2560	70500	0.0045	-
2.2720	71000	0.0045	-
2.288	71500	0.0045	-
2.304	72000	0.0045	-
2.32	72500	0.0045	-
2.336	73000	0.0045	-
2.352	73500	0.0046	-
2.368	74000	0.0045	-
2.384	74500	0.0045	-
2.4	75000	0.0044	-
2.416	75500	0.0044	-
2.432	76000	0.0045	-
2.448	76500	0.0045	-
2.464	77000	0.0045	-
2.48	77500	0.0045	-
2.496	78000	0.0044	-
2.512	78500	0.0044	-
2.528	79000	0.0044	-
2.544	79500	0.0046	-
2.56	80000	0.0045	0.0032
2.576	80500	0.0045	-
2.592	81000	0.0044	-
2.608	81500	0.0043	-
2.624	82000	0.0045	-
2.64	82500	0.0043	-
2.656	83000	0.0044	-
2.672	83500	0.0043	-
2.6880	84000	0.0043	-
2.7040	84500	0.0043	-
2.7200	85000	0.0044	-
2.7360	85500	0.0044	-
2.752	86000	0.0044	-
2.768	86500	0.0044	-
2.784	87000	0.0043	-
2.8	87500	0.0043	-
2.816	88000	0.0042	-
2.832	88500	0.0044	-
2.848	89000	0.0044	-
2.864	89500	0.0044	-
2.88	90000	0.0043	0.0031
2.896	90500	0.0043	-
2.912	91000	0.0044	-
2.928	91500	0.0043	-
2.944	92000	0.0043	-
2.96	92500	0.0042	-
2.976	93000	0.0042	-
2.992	93500	0.0042	-
3.008	94000	0.0041	-
3.024	94500	0.0038	-
3.04	95000	0.004	-
3.056	95500	0.0038	-
3.072	96000	0.0039	-
3.088	96500	0.0039	-
3.104	97000	0.0039	-
3.12	97500	0.0039	-
3.136	98000	0.0039	-
3.152	98500	0.0038	-
3.168	99000	0.004	-
3.184	99500	0.004	-
3.2	100000	0.004	0.0031
3.216	100500	0.0039	-
3.232	101000	0.0038	-
3.248	101500	0.004	-
3.2640	102000	0.0039	-
3.2800	102500	0.0041	-
3.296	103000	0.004	-
3.312	103500	0.0039	-
3.328	104000	0.0039	-
3.344	104500	0.004	-
3.36	105000	0.004	-
3.376	105500	0.004	-
3.392	106000	0.0041	-
3.408	106500	0.004	-
3.424	107000	0.0039	-
3.44	107500	0.0039	-
3.456	108000	0.004	-
3.472	108500	0.0039	-
3.488	109000	0.0038	-
3.504	109500	0.0039	-
3.52	110000	0.0039	0.0030
3.536	110500	0.0041	-
3.552	111000	0.0039	-
3.568	111500	0.0041	-
3.584	112000	0.0038	-
3.6	112500	0.0038	-
3.616	113000	0.0039	-
3.632	113500	0.0038	-
3.648	114000	0.0039	-
3.664	114500	0.0038	-
3.68	115000	0.0038	-
3.6960	115500	0.004	-
3.7120	116000	0.0038	-
3.7280	116500	0.0039	-
3.7440	117000	0.0039	-
3.76	117500	0.0038	-
3.776	118000	0.0039	-
3.792	118500	0.0039	-
3.808	119000	0.0038	-
3.824	119500	0.0039	-
3.84	120000	0.0039	0.0029
3.856	120500	0.0039	-
3.872	121000	0.0039	-
3.888	121500	0.0037	-
3.904	122000	0.0038	-
3.92	122500	0.0038	-
3.936	123000	0.0038	-
3.952	123500	0.0039	-
3.968	124000	0.0038	-
3.984	124500	0.0039	-
4.0	125000	0.0039	-
4.016	125500	0.0034	-
4.032	126000	0.0035	-
4.048	126500	0.0036	-
4.064	127000	0.0035	-
4.08	127500	0.0035	-
4.096	128000	0.0035	-
4.112	128500	0.0035	-
4.128	129000	0.0036	-
4.144	129500	0.0035	-
4.16	130000	0.0035	0.0029
4.176	130500	0.0035	-
4.192	131000	0.0035	-
4.208	131500	0.0035	-
4.224	132000	0.0036	-
4.24	132500	0.0036	-
4.256	133000	0.0036	-
4.272	133500	0.0035	-
4.288	134000	0.0034	-
4.304	134500	0.0036	-
4.32	135000	0.0035	-
4.336	135500	0.0036	-
4.352	136000	0.0036	-
4.368	136500	0.0035	-
4.384	137000	0.0036	-
4.4	137500	0.0035	-
4.416	138000	0.0034	-
4.432	138500	0.0034	-
4.448	139000	0.0034	-
4.464	139500	0.0035	-
4.48	140000	0.0035	0.0029
4.496	140500	0.0034	-
4.5120	141000	0.0035	-
4.5280	141500	0.0035	-
4.5440	142000	0.0036	-
4.5600	142500	0.0035	-
4.576	143000	0.0034	-
4.592	143500	0.0034	-
4.608	144000	0.0035	-
4.624	144500	0.0035	-
4.64	145000	0.0036	-
4.656	145500	0.0036	-
4.672	146000	0.0035	-
4.688	146500	0.0035	-
4.704	147000	0.0033	-
4.72	147500	0.0035	-
4.736	148000	0.0035	-
4.752	148500	0.0036	-
4.768	149000	0.0036	-
4.784	149500	0.0035	-
4.8	150000	0.0035	0.0028
4.816	150500	0.0035	-
4.832	151000	0.0035	-
4.848	151500	0.0035	-
4.864	152000	0.0036	-
4.88	152500	0.0036	-
4.896	153000	0.0035	-
4.912	153500	0.0035	-
4.928	154000	0.0035	-
4.944	154500	0.0035	-
4.96	155000	0.0035	-
4.976	155500	0.0035	-
4.992	156000	0.0034	-
5.008	156500	0.0033	-
5.024	157000	0.0032	-
5.04	157500	0.0032	-
5.056	158000	0.0033	-
5.072	158500	0.0032	-
5.088	159000	0.0032	-
5.104	159500	0.0031	-
5.12	160000	0.0032	0.0028
5.136	160500	0.0032	-
5.152	161000	0.0032	-
5.168	161500	0.0033	-
5.184	162000	0.0033	-
5.2	162500	0.0031	-
5.216	163000	0.0033	-
5.232	163500	0.0032	-
5.248	164000	0.0032	-
5.264	164500	0.0032	-
5.28	165000	0.0033	-
5.296	165500	0.0033	-
5.312	166000	0.0031	-
5.328	166500	0.0032	-
5.344	167000	0.0032	-
5.36	167500	0.0033	-
5.376	168000	0.0033	-
5.392	168500	0.0032	-
5.408	169000	0.0032	-
5.424	169500	0.0032	-
5.44	170000	0.0032	0.0027
5.456	170500	0.0031	-
5.4720	171000	0.0031	-
5.4880	171500	0.0032	-
5.504	172000	0.0031	-
5.52	172500	0.0031	-
5.536	173000	0.0032	-
5.552	173500	0.0031	-
5.568	174000	0.0032	-
5.584	174500	0.0032	-
5.6	175000	0.0032	-
5.616	175500	0.0032	-
5.632	176000	0.0032	-
5.648	176500	0.0032	-
5.664	177000	0.0032	-
5.68	177500	0.0032	-
5.696	178000	0.0032	-
5.712	178500	0.0033	-
5.728	179000	0.0032	-
5.744	179500	0.0031	-
5.76	180000	0.0033	0.0027
5.776	180500	0.0033	-
5.792	181000	0.003	-
5.808	181500	0.0032	-
5.824	182000	0.0032	-
5.84	182500	0.0032	-
5.856	183000	0.0032	-
5.872	183500	0.0033	-
5.888	184000	0.0032	-
5.904	184500	0.0032	-
5.92	185000	0.0032	-
5.936	185500	0.0031	-
5.952	186000	0.0031	-
5.968	186500	0.0031	-
5.984	187000	0.0033	-
6.0	187500	0.0031	-
6.016	188000	0.0028	-
6.032	188500	0.0029	-
6.048	189000	0.003	-
6.064	189500	0.003	-
6.08	190000	0.0029	0.0027
6.096	190500	0.0029	-
6.112	191000	0.0029	-
6.128	191500	0.003	-
6.144	192000	0.0029	-
6.16	192500	0.003	-
6.176	193000	0.003	-
6.192	193500	0.0029	-
6.208	194000	0.0029	-
6.224	194500	0.0029	-
6.24	195000	0.003	-
6.256	195500	0.0029	-
6.272	196000	0.0029	-
6.288	196500	0.0029	-
6.304	197000	0.0029	-
6.32	197500	0.003	-
6.336	198000	0.0029	-
6.352	198500	0.0029	-
6.368	199000	0.003	-
6.384	199500	0.0029	-
6.4	200000	0.0029	0.0028
6.416	200500	0.0029	-
6.432	201000	0.0029	-
6.448	201500	0.0031	-
6.464	202000	0.0029	-
6.48	202500	0.003	-
6.496	203000	0.003	-
6.5120	203500	0.003	-
6.5280	204000	0.0029	-
6.5440	204500	0.003	-
6.5600	205000	0.0029	-
6.576	205500	0.0028	-
6.592	206000	0.003	-
6.608	206500	0.0029	-
6.624	207000	0.003	-
6.64	207500	0.003	-
6.656	208000	0.003	-
6.672	208500	0.0029	-
6.688	209000	0.003	-
6.704	209500	0.003	-
6.72	210000	0.0029	0.0027
6.736	210500	0.0029	-
6.752	211000	0.0029	-
6.768	211500	0.0029	-
6.784	212000	0.0029	-
6.8	212500	0.0029	-
6.816	213000	0.003	-
6.832	213500	0.0028	-
6.848	214000	0.003	-
6.864	214500	0.0029	-
6.88	215000	0.0029	-
6.896	215500	0.0029	-
6.912	216000	0.0029	-
6.928	216500	0.0029	-
6.944	217000	0.0028	-
6.96	217500	0.003	-
6.976	218000	0.003	-
6.992	218500	0.0029	-
7.008	219000	0.0028	-
7.024	219500	0.0028	-
7.04	220000	0.0028	0.0027
7.056	220500	0.0027	-
7.072	221000	0.0027	-
7.088	221500	0.0027	-
7.104	222000	0.0026	-
7.12	222500	0.0028	-
7.136	223000	0.0027	-
7.152	223500	0.0028	-
7.168	224000	0.0027	-
7.184	224500	0.0027	-
7.2	225000	0.0028	-
7.216	225500	0.0027	-
7.232	226000	0.0028	-
7.248	226500	0.0027	-
7.264	227000	0.0027	-
7.28	227500	0.0027	-
7.296	228000	0.0027	-
7.312	228500	0.0028	-
7.328	229000	0.0027	-
7.344	229500	0.0028	-
7.36	230000	0.0028	0.0027
7.376	230500	0.0028	-
7.392	231000	0.0028	-
7.408	231500	0.0028	-
7.424	232000	0.0027	-
7.44	232500	0.0027	-
7.456	233000	0.0028	-
7.4720	233500	0.0028	-
7.4880	234000	0.0028	-
7.504	234500	0.0028	-
7.52	235000	0.0028	-
7.536	235500	0.0027	-
7.552	236000	0.0027	-
7.568	236500	0.0028	-
7.584	237000	0.0028	-
7.6	237500	0.0027	-
7.616	238000	0.0028	-
7.632	238500	0.0026	-
7.648	239000	0.0027	-
7.664	239500	0.0027	-
7.68	240000	0.0028	0.0027
7.696	240500	0.0028	-
7.712	241000	0.0027	-
7.728	241500	0.0028	-
7.744	242000	0.0027	-
7.76	242500	0.0027	-
7.776	243000	0.0027	-
7.792	243500	0.0028	-
7.808	244000	0.0027	-
7.824	244500	0.0027	-
7.84	245000	0.0027	-
7.856	245500	0.0029	-
7.872	246000	0.0028	-
7.888	246500	0.0027	-
7.904	247000	0.0026	-
7.92	247500	0.0027	-
7.936	248000	0.0027	-
7.952	248500	0.0027	-
7.968	249000	0.0028	-
7.984	249500	0.0027	-
8.0	250000	0.0028	0.0027

Framework Versions

• Python: 3.10.16
• Sentence Transformers: 4.1.0
• Transformers: 4.51.3
• PyTorch: 2.6.0+cu118
• Accelerate: 1.6.0
• Datasets: 3.5.0
• 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",
}

ContrastiveLoss

@inproceedings{hadsell2006dimensionality,
    author={Hadsell, R. and Chopra, S. and LeCun, Y.},
    booktitle={2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06)},
    title={Dimensionality Reduction by Learning an Invariant Mapping},
    year={2006},
    volume={2},
    number={},
    pages={1735-1742},
    doi={10.1109/CVPR.2006.100}
}