SentenceTransformer based on intfloat/multilingual-e5-base

This is a sentence-transformers model finetuned from intfloat/multilingual-e5-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: intfloat/multilingual-e5-base
Maximum Sequence Length: 512 tokens
Output Dimensionality: 768 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, 'architecture': 'XLMRobertaModel'})
  (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("nicolauduran45/e5-finetuned-entity-linking")
# Run inference
sentences = [
    'query: liquefied petroleum gas carriers. Context: Using fuel consumption as a main input, Psaraftis and Kontovas [25] presented an analysis on emissions of the world fleet for major ship types, i.e., bulk carriers, crude oil tankers, container vessels, product or chemical carriers, liquefied natural gas (liquefied natural gas) carriers, liquefied petroleum gas carriers, reefer vessels, Ro-Ro vessels, and general cargo ships.',
    'passage: Gas Carrier [SEP] A tanker equipped with specialized pressurized or refrigerated tanks for transporting liquefied natural gas (LNG), liquefied petroleum gas (LPG), or other gaseous products. [SEP] gas tanker',
    'passage: Offshore Supply Vessel [SEP] A ship designed to transport supplies, equipment, and personnel to offshore oil and gas platforms, wind farms, and other marine installations. [SEP] PSV ,  platform supply vessel ,  offshore supply ship ,  supply ship ,  offshore supply vessel ,  platform supply ship',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 768]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities)
# tensor([[1.0000, 0.8028, 0.2250],
#         [0.8028, 1.0000, 0.2569],
#         [0.2250, 0.2569, 1.0000]])

Training Details

Training Dataset

Unnamed Dataset

Size: 1,260 training samples
Columns: sentence_0 and sentence_1
Approximate statistics based on the first 1000 samples:
sentence_0 sentence_1
type string string
details
min: 16 tokens
mean: 63.57 tokens
max: 338 tokens

min: 15 tokens
mean: 77.89 tokens
max: 368 tokens

	sentence_0	sentence_1
type	string	string
details	min: 16 tokens mean: 63.57 tokens max: 338 tokens	min: 15 tokens mean: 77.89 tokens max: 368 tokens

Samples:

sentence_0	sentence_1
`query: tugboat. Context: Sharing deployment information: Information sharing between the pilot, tugboat captain and boatmen crew with their planning departments regarding the deployment information such as meeting point with the vessel, or estimated start and completion time of services.`	`passage: Tugboat [SEP] A powerful, maneuverable vessel used to push or tow other ships in harbors, through canals, or at sea, assisting with docking and navigation in confined waters. [SEP] tugboat , tug boat , tug , water tractor`
`query: fluorescence microscope. Context: staining of the striatum and the mean fluorescence density was performed through a fluorescence microscope, green fluorescence intensity represents the expression level of tyrosine hydroxylase, the results showed that the green fluorescence in the experimental group was slightly lower than that in the Sham group (Fig.`	`passage: fluorescence microscopy [SEP] Fluorescence microscopy comprises any type of microscopy where the specimen can be made to fluoresce (emit energy as visible light), typically by illuminating it with light of specific wavelengths. [SEP] Microscopy, Fluorescence`
`query: of liquefied natural gas carriers. Context: Transverse acceleration: Longitudinal acceleration: where: (2) Forced displacement of hull deformation The topic of this study is the piping system installed on the deck of liquefied natural gas carriers.`	`passage: Gas Carrier [SEP] A tanker equipped with specialized pressurized or refrigerated tanks for transporting liquefied natural gas (LNG), liquefied petroleum gas (LPG), or other gaseous products. [SEP] gas tanker`

Loss: MultipleNegativesRankingLoss with these parameters:

{
    "scale": 20.0,
    "similarity_fct": "cos_sim",
    "gather_across_devices": false
}

Training Hyperparameters

Non-Default Hyperparameters

per_device_train_batch_size: 32
per_device_eval_batch_size: 32
fp16: True
multi_dataset_batch_sampler: round_robin

All Hyperparameters

Click to expand

do_predict: False
eval_strategy: no
prediction_loss_only: True
per_device_train_batch_size: 32
per_device_eval_batch_size: 32
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
num_train_epochs: 3
max_steps: -1
lr_scheduler_type: linear
lr_scheduler_kwargs: None
warmup_ratio: None
warmup_steps: 0
log_level: passive
log_level_replica: warning
log_on_each_node: True
logging_nan_inf_filter: True
enable_jit_checkpoint: False
save_on_each_node: False
save_only_model: False
restore_callback_states_from_checkpoint: False
use_cpu: False
seed: 42
data_seed: None
bf16: False
fp16: True
bf16_full_eval: False
fp16_full_eval: False
tf32: None
local_rank: -1
ddp_backend: None
debug: []
dataloader_drop_last: False
dataloader_num_workers: 0
dataloader_prefetch_factor: None
disable_tqdm: False
remove_unused_columns: True
label_names: None
load_best_model_at_end: False
ignore_data_skip: False
fsdp: []
fsdp_config: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': 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
deepspeed: None
label_smoothing_factor: 0.0
optim: adamw_torch_fused
optim_args: None
group_by_length: False
length_column_name: length
project: huggingface
trackio_space_id: trackio
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
push_to_hub: False
resume_from_checkpoint: None
hub_model_id: None
hub_strategy: every_save
hub_private_repo: None
hub_always_push: False
hub_revision: None
gradient_checkpointing: False
gradient_checkpointing_kwargs: None
include_for_metrics: []
eval_do_concat_batches: True
auto_find_batch_size: False
full_determinism: False
ddp_timeout: 1800
torch_compile: False
torch_compile_backend: None
torch_compile_mode: None
include_num_input_tokens_seen: no
neftune_noise_alpha: None
optim_target_modules: None
batch_eval_metrics: False
eval_on_start: False
use_liger_kernel: False
liger_kernel_config: None
eval_use_gather_object: False
average_tokens_across_devices: True
use_cache: False
prompts: None
batch_sampler: batch_sampler
multi_dataset_batch_sampler: round_robin
router_mapping: {}
learning_rate_mapping: {}

Framework Versions

Python: 3.12.12
Sentence Transformers: 5.2.2
Transformers: 5.0.0
PyTorch: 2.9.0+cu128
Accelerate: 1.12.0
Datasets: 4.0.0
Tokenizers: 0.22.2

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{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}
}