SentenceTransformer based on sentence-transformers/LaBSE

This is a sentence-transformers model finetuned from sentence-transformers/LaBSE. It maps inputs to a 768-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, classification, clustering, and more.

Model Details

Model Description

Model Type: Sentence Transformer
Base model: sentence-transformers/LaBSE
Maximum Sequence Length: 256 tokens
Output Dimensionality: 768 dimensions
Similarity Function: Cosine Similarity
Supported Modality: Text

Model Sources

Documentation: Sentence Transformers Documentation
Repository: Sentence Transformers on GitHub
Hugging Face: Sentence Transformers on Hugging Face

Full Model Architecture

SentenceTransformer(
  (0): Transformer({'transformer_task': 'feature-extraction', 'modality_config': {'text': {'method': 'forward', 'method_output_name': 'last_hidden_state'}}, 'module_output_name': 'token_embeddings', 'architecture': 'BertModel'})
  (1): Pooling({'embedding_dimension': 768, 'pooling_mode': 'cls', 'include_prompt': True})
  (2): Dense({'in_features': 768, 'out_features': 768, 'bias': True, 'activation_function': 'torch.nn.modules.activation.Tanh', 'module_input_name': 'sentence_embedding', 'module_output_name': 'sentence_embedding'})
  (3): Normalize({'module_input_name': 'sentence_embedding', 'module_output_name': 'sentence_embedding'})
)

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("sentence_transformers_model_id")
# Run inference
queries = [
    'Stag | 122 Bruce Street, Scotia, NY',
]
documents = [
    'Stag Corporation | BRUCE STREET, SCOTIA, NY',
    '#2 HUB CO | 142 COTTAGE STREET, LEWISTON, ME',
    'ORTHOPEDIC  PHYSICIANS | 75, ALTOONA, AL',
]
query_embeddings = model.encode_query(queries)
document_embeddings = model.encode_document(documents)
print(query_embeddings.shape, document_embeddings.shape)
# [1, 768] [3, 768]

# Get the similarity scores for the embeddings
similarities = model.similarity(query_embeddings, document_embeddings)
print(similarities)
# tensor([[ 0.7677,  0.1634, -0.0688]])

Evaluation

Metrics

Information Retrieval

Dataset: biencoder-val
Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.929
cosine_accuracy@5	1.0
cosine_accuracy@10	1.0
cosine_accuracy@30	1.0
cosine_precision@1	0.929
cosine_precision@3	0.3333
cosine_precision@5	0.2
cosine_precision@10	0.1
cosine_recall@1	0.929
cosine_recall@3	1.0
cosine_recall@5	1.0
cosine_recall@10	1.0
cosine_ndcg@10	0.9733
cosine_mrr@10	0.9638
cosine_map@100	0.9638

Training Details

Training Dataset

Unnamed Dataset

Size: 623,829 training samples
Columns: anchor and positive
Approximate statistics based on the first 100 samples:
anchor positive
type string string

modality text text
details
min: 18 tokens
mean: 31.59 tokens
max: 55 tokens

min: 7 tokens
mean: 33.45 tokens
max: 64 tokens

	anchor	positive
type	string	string
modality	text	text
details	min: 18 tokens mean: 31.59 tokens max: 55 tokens	min: 7 tokens mean: 33.45 tokens max: 64 tokens

Samples:

anchor	positive
`Bangalore South Automotive Private Limited \| C-901, Goyalco Orchid, Lakeview, Bangalore South, Bangalore, Karnataka`	`Bangalore South Automotive Limited Private \| C-901., GOYALCO ORCHID, LAKEVIEW, BANGALORE SOUTH, ಕರ್ನಾಟಕ`
`Bangalore South Automotive Private Limited \| C-901, Goyalco Orchid, Lakeview, Bangalore South, Bangalore, Karnataka`	`Bangalore Sóuth Automotive Private Limited \|`
`Software Pinnacle Tourism \| 3016/5, 1St Floor, Ranjit Nagar, New Delhi, Central Delhi, Delhi`	`Software Pinnacle Tóurism \| A-3016/5, 1ST FLOOR, RANJIT NAGAR, NEW DELHI, दिल्ली`

Loss: MultipleNegativesRankingLoss with these parameters:

{
    "scale": 20.0,
    "similarity_fct": "cos_sim",
    "gather_across_devices": false,
    "directions": [
        "query_to_doc"
    ],
    "partition_mode": "joint",
    "hardness_mode": null,
    "hardness_strength": 0.0
}

Training Hyperparameters

Non-Default Hyperparameters

per_device_train_batch_size: 64
num_train_epochs: 2
learning_rate: 2e-05
warmup_steps: 0.1

All Hyperparameters

Click to expand

per_device_train_batch_size: 64
num_train_epochs: 2
max_steps: -1
learning_rate: 2e-05
lr_scheduler_type: linear
lr_scheduler_kwargs: None
warmup_steps: 0.1
optim: adamw_torch_fused
optim_args: None
weight_decay: 0.0
adam_beta1: 0.9
adam_beta2: 0.999
adam_epsilon: 1e-08
optim_target_modules: None
gradient_accumulation_steps: 1
average_tokens_across_devices: True
max_grad_norm: 1.0
label_smoothing_factor: 0.0
bf16: False
fp16: False
bf16_full_eval: False
fp16_full_eval: False
tf32: None
gradient_checkpointing: False
gradient_checkpointing_kwargs: None
torch_compile: False
torch_compile_backend: None
torch_compile_mode: None
use_liger_kernel: False
liger_kernel_config: None
use_cache: False
neftune_noise_alpha: None
torch_empty_cache_steps: None
auto_find_batch_size: False
log_on_each_node: True
logging_nan_inf_filter: True
include_num_input_tokens_seen: no
log_level: passive
log_level_replica: warning
disable_tqdm: False
project: huggingface
trackio_space_id: None
trackio_bucket_id: None
trackio_static_space_id: None
per_device_eval_batch_size: 8
prediction_loss_only: True
eval_on_start: False
eval_do_concat_batches: True
eval_use_gather_object: False
eval_accumulation_steps: None
include_for_metrics: []
batch_eval_metrics: False
save_only_model: False
save_on_each_node: False
enable_jit_checkpoint: False
push_to_hub: False
hub_private_repo: None
hub_model_id: None
hub_strategy: every_save
hub_always_push: False
hub_revision: None
load_best_model_at_end: False
ignore_data_skip: False
restore_callback_states_from_checkpoint: False
full_determinism: False
seed: 42
data_seed: None
use_cpu: False
accelerator_config: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
parallelism_config: None
dataloader_drop_last: False
dataloader_num_workers: 0
dataloader_pin_memory: True
dataloader_persistent_workers: False
dataloader_prefetch_factor: None
dataloader_multiprocessing_context: None
dataloader_in_order: True
remove_unused_columns: True
label_names: None
train_sampling_strategy: random
length_column_name: length
ddp_find_unused_parameters: None
ddp_bucket_cap_mb: None
ddp_broadcast_buffers: False
ddp_static_graph: None
ddp_backend: None
ddp_timeout: 1800
fsdp: None
fsdp_config: None
deepspeed: None
debug: []
skip_memory_metrics: True
do_predict: False
resume_from_checkpoint: None
local_rank: -1
prompts: None
batch_sampler: batch_sampler
multi_dataset_batch_sampler: proportional
router_mapping: {}
learning_rate_mapping: {}
warmup_ratio: None

Training Logs

Click to expand

Epoch	Step	Training Loss	biencoder-val_cosine_ndcg@10
0.0051	50	0.2099	-
0.0103	100	0.0801	-
0.0154	150	0.0250	-
0.0205	200	0.0196	-
0.0256	250	0.0155	-
0.0308	300	0.0151	-
0.0359	350	0.0150	-
0.0410	400	0.0117	-
0.0462	450	0.0124	-
0.0513	500	0.0111	-
0.0564	550	0.0070	-
0.0616	600	0.0107	-
0.0667	650	0.0091	-
0.0718	700	0.0060	-
0.0769	750	0.0094	-
0.0821	800	0.0067	-
0.0872	850	0.0061	-
0.0923	900	0.0076	-
0.0975	950	0.0060	-
0.1026	1000	0.0047	-
0.1077	1050	0.0071	-
0.1128	1100	0.0063	-
0.1180	1150	0.0046	-
0.1231	1200	0.0039	-
0.1282	1250	0.0049	-
0.1334	1300	0.0055	-
0.1385	1350	0.0038	-
0.1436	1400	0.0041	-
0.1487	1450	0.0060	-
0.1539	1500	0.0055	-
0.1590	1550	0.0053	-
0.1641	1600	0.0047	-
0.1693	1650	0.0044	-
0.1744	1700	0.0071	-
0.1795	1750	0.0044	-
0.1847	1800	0.0025	-
0.1898	1850	0.0055	-
0.1949	1900	0.0053	-
0.2000	1950	0.0045	-
0.2052	2000	0.0047	-
0.2103	2050	0.0048	-
0.2154	2100	0.0041	-
0.2206	2150	0.0030	-
0.2257	2200	0.0037	-
0.2308	2250	0.0047	-
0.2359	2300	0.0042	-
0.2411	2350	0.0027	-
0.2462	2400	0.0047	-
0.2513	2450	0.0028	-
0.2565	2500	0.0043	-
0.2616	2550	0.0063	-
0.2667	2600	0.0027	-
0.2719	2650	0.0021	-
0.2770	2700	0.0028	-
0.2821	2750	0.0024	-
0.2872	2800	0.0045	-
0.2924	2850	0.0033	-
0.2975	2900	0.0048	-
0.3026	2950	0.0021	-
0.3078	3000	0.0031	-
0.3129	3050	0.0027	-
0.3180	3100	0.0033	-
0.3231	3150	0.0040	-
0.3283	3200	0.0012	-
0.3334	3250	0.0031	-
0.3385	3300	0.0033	-
0.3437	3350	0.0020	-
0.3488	3400	0.0028	-
0.3539	3450	0.0022	-
0.3590	3500	0.0025	-
0.3642	3550	0.0026	-
0.3693	3600	0.0028	-
0.3744	3650	0.0035	-
0.3796	3700	0.0023	-
0.3847	3750	0.0029	-
0.3898	3800	0.0031	-
0.3950	3850	0.0042	-
0.4001	3900	0.0027	-
0.4052	3950	0.0035	-
0.4103	4000	0.0026	-
0.4155	4050	0.0017	-
0.4206	4100	0.0022	-
0.4257	4150	0.0020	-
0.4309	4200	0.0025	-
0.4360	4250	0.0024	-
0.4411	4300	0.0025	-
0.4462	4350	0.0025	-
0.4514	4400	0.0021	-
0.4565	4450	0.0011	-
0.4616	4500	0.0018	-
0.4668	4550	0.0039	-
0.4719	4600	0.0016	-
0.4770	4650	0.0023	-
0.4822	4700	0.0012	-
0.4873	4750	0.0027	-
0.4924	4800	0.0020	-
0.4975	4850	0.0022	-
0.5027	4900	0.0022	-
0.5078	4950	0.0016	-
0.5129	5000	0.0027	-
0.5181	5050	0.0017	-
0.5232	5100	0.0020	-
0.5283	5150	0.0024	-
0.5334	5200	0.0024	-
0.5386	5250	0.0024	-
0.5437	5300	0.0022	-
0.5488	5350	0.0029	-
0.5540	5400	0.0016	-
0.5591	5450	0.0010	-
0.5642	5500	0.0017	-
0.5693	5550	0.0029	-
0.5745	5600	0.0017	-
0.5796	5650	0.0021	-
0.5847	5700	0.0019	-
0.5899	5750	0.0021	-
0.5950	5800	0.0030	-
0.6001	5850	0.0015	-
0.6053	5900	0.0028	-
0.6104	5950	0.0022	-
0.6155	6000	0.0020	-
0.6206	6050	0.0021	-
0.6258	6100	0.0017	-
0.6309	6150	0.0021	-
0.6360	6200	0.0015	-
0.6412	6250	0.0010	-
0.6463	6300	0.0018	-
0.6514	6350	0.0011	-
0.6565	6400	0.0035	-
0.6617	6450	0.0015	-
0.6668	6500	0.0022	-
0.6719	6550	0.0019	-
0.6771	6600	0.0017	-
0.6822	6650	0.0011	-
0.6873	6700	0.0021	-
0.6924	6750	0.0017	-
0.6976	6800	0.0014	-
0.7027	6850	0.0024	-
0.7078	6900	0.0012	-
0.7130	6950	0.0032	-
0.7181	7000	0.0020	-
0.7232	7050	0.0013	-
0.7284	7100	0.0038	-
0.7335	7150	0.0018	-
0.7386	7200	0.0019	-
0.7437	7250	0.0038	-
0.7489	7300	0.0013	-
0.7540	7350	0.0025	-
0.7591	7400	0.0022	-
0.7643	7450	0.0014	-
0.7694	7500	0.0015	-
0.7745	7550	0.0030	-
0.7796	7600	0.0016	-
0.7848	7650	0.0017	-
0.7899	7700	0.0013	-
0.7950	7750	0.0036	-
0.8002	7800	0.0022	-
0.8053	7850	0.0015	-
0.8104	7900	0.0010	-
0.8156	7950	0.0021	-
0.8207	8000	0.0019	-
0.8258	8050	0.0011	-
0.8309	8100	0.0012	-
0.8361	8150	0.0026	-
0.8412	8200	0.0011	-
0.8463	8250	0.0019	-
0.8515	8300	0.0017	-
0.8566	8350	0.0011	-
0.8617	8400	0.0012	-
0.8668	8450	0.0018	-
0.8720	8500	0.0008	-
0.8771	8550	0.0017	-
0.8822	8600	0.0023	-
0.8874	8650	0.0010	-
0.8925	8700	0.0011	-
0.8976	8750	0.0022	-
0.9027	8800	0.0023	-
0.9079	8850	0.0013	-
0.9130	8900	0.0015	-
0.9181	8950	0.0034	-
0.9233	9000	0.0011	-
0.9284	9050	0.0018	-
0.9335	9100	0.0013	-
0.9387	9150	0.0009	-
0.9438	9200	0.0008	-
0.9489	9250	0.0013	-
0.9540	9300	0.0012	-
0.9592	9350	0.0012	-
0.9643	9400	0.0008	-
0.9694	9450	0.0011	-
0.9746	9500	0.0008	-
0.9797	9550	0.0015	-
0.9848	9600	0.0014	-
0.9899	9650	0.0013	-
0.9951	9700	0.0006	-
1.0	9748	-	0.9733
1.0002	9750	0.0014	-
1.0053	9800	0.0006	-
1.0105	9850	0.0005	-
1.0156	9900	0.0011	-
1.0207	9950	0.0011	-
1.0259	10000	0.0009	-
1.0310	10050	0.0013	-
1.0361	10100	0.0008	-
1.0412	10150	0.0008	-
1.0464	10200	0.0006	-
1.0515	10250	0.0006	-
1.0566	10300	0.0010	-
1.0618	10350	0.0026	-
1.0669	10400	0.0007	-
1.0720	10450	0.0007	-
1.0771	10500	0.0010	-
1.0823	10550	0.0016	-
1.0874	10600	0.0014	-
1.0925	10650	0.0007	-
1.0977	10700	0.0006	-
1.1028	10750	0.0021	-
1.1079	10800	0.0027	-
1.1130	10850	0.0006	-
1.1182	10900	0.0006	-
1.1233	10950	0.0012	-
1.1284	11000	0.0016	-
1.1336	11050	0.0015	-
1.1387	11100	0.0026	-
1.1438	11150	0.0008	-
1.1490	11200	0.0007	-
1.1541	11250	0.0007	-
1.1592	11300	0.0012	-
1.1643	11350	0.0010	-
1.1695	11400	0.0005	-
1.1746	11450	0.0008	-
1.1797	11500	0.0006	-
1.1849	11550	0.0005	-
1.1900	11600	0.0016	-
1.1951	11650	0.0009	-
1.2002	11700	0.0011	-
1.2054	11750	0.0006	-
1.2105	11800	0.0014	-
1.2156	11850	0.0006	-
1.2208	11900	0.0006	-
1.2259	11950	0.0015	-
1.2310	12000	0.0005	-
1.2362	12050	0.0037	-
1.2413	12100	0.0006	-
1.2464	12150	0.0005	-
1.2515	12200	0.0007	-
1.2567	12250	0.0016	-
1.2618	12300	0.0006	-
1.2669	12350	0.0015	-
1.2721	12400	0.0005	-
1.2772	12450	0.0007	-
1.2823	12500	0.0006	-
1.2874	12550	0.0009	-
1.2926	12600	0.0005	-
1.2977	12650	0.0004	-
1.3028	12700	0.0011	-
1.3080	12750	0.0006	-
1.3131	12800	0.0006	-
1.3182	12850	0.0006	-
1.3233	12900	0.0004	-
1.3285	12950	0.0015	-
1.3336	13000	0.0013	-
1.3387	13050	0.0008	-
1.3439	13100	0.0010	-
1.3490	13150	0.0007	-
1.3541	13200	0.0013	-
1.3593	13250	0.0005	-
1.3644	13300	0.0017	-
1.3695	13350	0.0020	-
1.3746	13400	0.0004	-
1.3798	13450	0.0004	-
1.3849	13500	0.0009	-
1.3900	13550	0.0004	-
1.3952	13600	0.0009	-
1.4003	13650	0.0004	-
1.4054	13700	0.0007	-
1.4105	13750	0.0013	-
1.4157	13800	0.0007	-
1.4208	13850	0.0010	-
1.4259	13900	0.0010	-
1.4311	13950	0.0008	-
1.4362	14000	0.0009	-
1.4413	14050	0.0015	-
1.4465	14100	0.0008	-
1.4516	14150	0.0007	-
1.4567	14200	0.0007	-
1.4618	14250	0.0011	-
1.4670	14300	0.0023	-
1.4721	14350	0.0011	-
1.4772	14400	0.0004	-
1.4824	14450	0.0009	-
1.4875	14500	0.0005	-
1.4926	14550	0.0009	-
1.4977	14600	0.0004	-
1.5029	14650	0.0004	-
1.5080	14700	0.0004	-
1.5131	14750	0.0011	-
1.5183	14800	0.0020	-
1.5234	14850	0.0007	-
1.5285	14900	0.0005	-
1.5336	14950	0.0004	-
1.5388	15000	0.0004	-
1.5439	15050	0.0009	-
1.5490	15100	0.0005	-
1.5542	15150	0.0006	-
1.5593	15200	0.0008	-
1.5644	15250	0.0006	-
1.5696	15300	0.0023	-
1.5747	15350	0.0006	-
1.5798	15400	0.0006	-
1.5849	15450	0.0013	-
1.5901	15500	0.0006	-
1.5952	15550	0.0004	-
1.6003	15600	0.0020	-
1.6055	15650	0.0016	-
1.6106	15700	0.0005	-
1.6157	15750	0.0004	-
1.6208	15800	0.0011	-
1.6260	15850	0.0014	-
1.6311	15900	0.0005	-
1.6362	15950	0.0011	-
1.6414	16000	0.0007	-
1.6465	16050	0.0005	-
1.6516	16100	0.0008	-
1.6568	16150	0.0003	-
1.6619	16200	0.0012	-
1.6670	16250	0.0004	-
1.6721	16300	0.0003	-
1.6773	16350	0.0003	-
1.6824	16400	0.0022	-
1.6875	16450	0.0004	-
1.6927	16500	0.0005	-
1.6978	16550	0.0004	-
1.7029	16600	0.0006	-
1.7080	16650	0.0007	-
1.7132	16700	0.0009	-
1.7183	16750	0.0004	-
1.7234	16800	0.0014	-
1.7286	16850	0.0012	-
1.7337	16900	0.0005	-
1.7388	16950	0.0008	-
1.7439	17000	0.0006	-
1.7491	17050	0.0007	-
1.7542	17100	0.0004	-
1.7593	17150	0.0012	-
1.7645	17200	0.0013	-
1.7696	17250	0.0010	-
1.7747	17300	0.0009	-
1.7799	17350	0.0004	-
1.7850	17400	0.0003	-
1.7901	17450	0.0007	-
1.7952	17500	0.0004	-
1.8004	17550	0.0004	-
1.8055	17600	0.0005	-
1.8106	17650	0.0004	-
1.8158	17700	0.0003	-
1.8209	17750	0.0004	-
1.8260	17800	0.0014	-
1.8311	17850	0.0004	-
1.8363	17900	0.0008	-
1.8414	17950	0.0004	-
1.8465	18000	0.0004	-
1.8517	18050	0.0007	-
1.8568	18100	0.0003	-
1.8619	18150	0.0004	-
1.8670	18200	0.0019	-
1.8722	18250	0.0005	-
1.8773	18300	0.0007	-
1.8824	18350	0.0004	-
1.8876	18400	0.0014	-
1.8927	18450	0.0006	-
1.8978	18500	0.0004	-
1.9030	18550	0.0004	-
1.9081	18600	0.0003	-
1.9132	18650	0.0006	-
1.9183	18700	0.0008	-
1.9235	18750	0.0005	-
1.9286	18800	0.0003	-
1.9337	18850	0.0003	-
1.9389	18900	0.0003	-
1.9440	18950	0.0007	-
1.9491	19000	0.0003	-
1.9542	19050	0.0008	-
1.9594	19100	0.0007	-
1.9645	19150	0.0004	-
1.9696	19200	0.0004	-
1.9748	19250	0.0014	-
1.9799	19300	0.0009	-
1.9850	19350	0.0004	-
1.9902	19400	0.0012	-
1.9953	19450	0.0010	-
2.0	19496	-	0.9733

Training Time

Training: 1.0 hours
Evaluation: 1.8 seconds
Total: 1.0 hours

Framework Versions

Python: 3.10.12
Sentence Transformers: 6.1.0
Transformers: 5.17.0
PyTorch: 2.14.0+cu130
Accelerate: 1.15.0
Datasets: 5.0.1
Tokenizers: 0.23.2

Additional Resources

Training and Finetuning Embedding Models with Sentence Transformers: the end-to-end guide for training or finetuning Sentence Transformer models.
Introduction to Matryoshka Embedding Models: variable-size embeddings that can be truncated with minimal quality loss.
Binary and Scalar Embedding Quantization for Significantly Faster & Cheaper Retrieval: post-training compression of embedding vectors.
Multimodal Embedding & Reranker Models with Sentence Transformers: use text, image, audio, and video models through the same API.
Training and Finetuning Multimodal Embedding & Reranker Models with Sentence Transformers: train multimodal embedding models, with a Visual Document Retrieval walkthrough.

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",
}

MultipleNegativesRankingLoss

@misc{oord2019representationlearningcontrastivepredictive,
      title={Representation Learning with Contrastive Predictive Coding},
      author={Aaron van den Oord and Yazhe Li and Oriol Vinyals},
      year={2019},
      eprint={1807.03748},
      archivePrefix={arXiv},
      primaryClass={cs.LG},
      url={https://arxiv.org/abs/1807.03748},
}

Downloads last month: 17

Safetensors

Model size

0.5B params

Tensor type

F32

Model tree for Starkdoorstep12/entity-resolution-biencoder

Base model

sentence-transformers/LaBSE

Finetuned

(101)

this model

Papers for Starkdoorstep12/entity-resolution-biencoder

Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks

Paper • 1908.10084 • Published Aug 27, 2019 • 19

Representation Learning with Contrastive Predictive Coding

Paper • 1807.03748 • Published Jul 10, 2018 • 1

Evaluation results

Cosine Accuracy@1 on biencoder val
self-reported

0.929
Cosine Accuracy@5 on biencoder val
self-reported

1.000
Cosine Accuracy@10 on biencoder val
self-reported

1.000
Cosine Accuracy@30 on biencoder val
self-reported

1.000
Cosine Precision@1 on biencoder val
self-reported

0.929
Cosine Precision@3 on biencoder val
self-reported

0.333
Cosine Precision@5 on biencoder val
self-reported

0.200
Cosine Precision@10 on biencoder val
self-reported

0.100

anchor	positive
`Bangalore South Automotive Private Limited \| C-901, Goyalco Orchid, Lakeview, Bangalore South, Bangalore, Karnataka`	`Bangalore South Automotive Limited Private \| C-901., GOYALCO ORCHID, LAKEVIEW, BANGALORE SOUTH, ಕರ್ನಾಟಕ`
`Bangalore South Automotive Private Limited \| C-901, Goyalco Orchid, Lakeview, Bangalore South, Bangalore, Karnataka`	`Bangalore Sóuth Automotive Private Limited \|`
`Software Pinnacle Tourism \| 3016/5, 1St Floor, Ranjit Nagar, New Delhi, Central Delhi, Delhi`	`Software Pinnacle Tóurism \| A-3016/5, 1ST FLOOR, RANJIT NAGAR, NEW DELHI, दिल्ली`