metadata

pipeline_tag: sentence-similarity
tags:
  - sentence-transformers
  - feature-extraction
  - sentence-similarity
language:
  - ru
  - en
base_model: sentence-transformers/LaBSE
inference: true
widget:
  - source_sentence: Москва
    sentences:
      - Moscow
      - Mytishchi
      - Meshchera
    example_title: Geonames cities

LaBSE_geonames_RU_RELOCATION

This is a sentence-transformers model: It maps geonames to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search.

This model fine tuned on geonames cities15000 in RU and popular relocation countries.

Usage (Sentence-Transformers)

Using this model becomes easy when you have sentence-transformers installed:

pip install -U sentence-transformers

Then you can use the model like this:

from sentence_transformers import SentenceTransformer
cities = ["Vladivostok", "Moscow"]

model = SentenceTransformer('artefucktor/LaBSE_geonames_RU_RELOCATION')
embeddings = model.encode(cities)
print(embeddings)

Training

The model was trained with the parameters:

DataLoader:

torch.utils.data.dataloader.DataLoader of length 2376 with parameters:

{'batch_size': 8, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}

Loss:

sentence_transformers.losses.MultipleNegativesRankingLoss.MultipleNegativesRankingLoss with parameters:

{'scale': 20.0, 'similarity_fct': 'cos_sim'}

Parameters of the fit()-Method:

{
    "epochs": 5,
    "evaluation_steps": 0,
    "evaluator": "NoneType",
    "max_grad_norm": 1,
    "optimizer_class": "<class 'torch.optim.adamw.AdamW'>",
    "optimizer_params": {
        "lr": 2e-05
    },
    "scheduler": "WarmupLinear",
    "steps_per_epoch": null,
    "warmup_steps": 10000,
    "weight_decay": 0.01
}

Full Model Architecture

SentenceTransformer(
  (0): Transformer({'max_seq_length': 256, 'do_lower_case': False}) 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})
  (2): Dense({'in_features': 768, 'out_features': 768, 'bias': True, 'activation_function': 'torch.nn.modules.activation.Tanh'})
  (3): Normalize()
)

artefucktor
/

LaBSE_geonames_RU_RELOCATION

LaBSE_geonames_RU_RELOCATION

Usage (Sentence-Transformers)

Training

Full Model Architecture

Citing & Authors