Modelpublic

Data-Lab/multilingual-e5-large-instruct-embedder-tg

sourceHugging Faceupdated 2y agoView on Hugging Face

0likes90downloads

Model Card

SentenceTransformer based on intfloat/multilingual-e5-large-instruct

This is a sentence-transformers model finetuned from intfloat/multilingual-e5-large-instruct. It maps sentences & paragraphs to a 1024-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-large-instruct
—Maximum Sequence Length: 512 tokens
—Output Dimensionality: 1024 tokens
—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: XLMRobertaModel 
  (1): Pooling({'word_embedding_dimension': 1024, '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:

bash

pip install -U sentence-transformers

Then you can load this model and run inference.

python

from sentence_transformers import SentenceTransformer

# Download from the 🤗 Hub
model = SentenceTransformer("Data-Lab/multilingual-e5-large-instruct-embedder-tg")
# Run inference
sentences = [
    'паста томатная',
    'Instruct: Найти похожие продукты на основе деталей\nQuery: Паста томатная, 250 г томатная паста, кулинария, свежие ингредиенты, насыщенный вкус, универсальное применение, консистенция',
    'Instruct: Найти похожие продукты на основе деталей\nQuery: Соус Filippo Berio томатный Арраббьята 340 г соус, итальянская кухня, без консервантов, для пасты, острый, натуральные ингредиенты, высокое качество, томатный соус, органические продукты',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 1024]

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

<!--

Direct Usage (Transformers)

<details><summary>Click to see the direct usage in Transformers</summary>

</details> -->

<!--

Downstream Usage (Sentence Transformers)

You can finetune this model on your own dataset.

<details><summary>Click to expand</summary>

</details> -->

<!--

Out-of-Scope Use

List how the model may foreseeably be misused and address what users ought not to do with the model. -->

Evaluation

Metrics

Triplet

—Dataset: dev
—Evaluated with <code>TripletEvaluator</code>

Metric	Value
cosine_accuracy	0.9285
dot_accuracy	0.0715
manhattan_accuracy	0.9285
euclidean_accuracy	0.9285
max_accuracy	0.9285

<!--

Bias, Risks and Limitations

What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model. -->

<!--

Recommendations

What are recommendations with respect to the foreseeable issues? For example, filtering explicit content. -->

Training Details

Training Dataset

Unnamed Dataset

—Size: 10,190 training samples
—Columns: <code>sentence0</code>, <code>sentence1</code>, and <code>sentence_2</code>
—Approximate statistics based on the first 1000 samples: | | sentence0 | sentence1 | sentence_2 | |:--------|:---------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------| | type | string | string | string | | details | <ul><li>min: 3 tokens</li><li>mean: 7.77 tokens</li><li>max: 30 tokens</li></ul> | <ul><li>min: 34 tokens</li><li>mean: 68.57 tokens</li><li>max: 180 tokens</li></ul> | <ul><li>min: 39 tokens</li><li>mean: 70.46 tokens</li><li>max: 116 tokens</li></ul> |
—Samples: | sentence0 | sentence1 | sentence_2 | |:-------------------------------------|:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| | <code>хурма</code> | <code>Instruct: Найти похожие продукты на основе деталей Query: Чипсы из хурмы, 25 г чипсы, натуральные, фрукты, перекус, сладкий вкус, десерт</code> | <code>Instruct: Найти похожие продукты на основе деталей Query: Салат мимоза, 300 г салат, праздничный стол, обед, горбуша, отварные овощи, куриные желтки, классический рецепт, нежный вкус, закуска</code> | | <code>жареное мясо</code> | <code>Instruct: Найти похожие продукты на основе деталей Query: Жареная говядина с черным перцем жареное мясо, приготовление, специи, соусы, овощи</code> | <code>Instruct: Найти похожие продукты на основе деталей Query: Каша рисовая на безлактозном молоке безлактозное молоко, рисовая каша, завтрак на ходу, низкое содержание жира, альтернативное молоко, легкая сладость, удобная упаковка, подходящий для аллергиков</code> | | <code>бедро цыпленка бройлера</code> | <code>Instruct: Найти похожие продукты на основе деталей Query: Бедро цыплят-бройлеров Халяль 1 кг None, цыпленок, мясо, бройлер, халяль, бедро, маринование, тушение, запекание, None</code> | <code>Instruct: Найти похожие продукты на основе деталей Query: Мясо бедра (Филе бедра) индейки в маринаде "Чесночный" 1 кг None, мясо, индейка, филе, маринад, чеснок, диетическое, нежирное, острое, травы, 1 кг, None</code> |
—Loss: <code>TripletLoss</code> with these parameters:

json

  {
      "distance_metric": "TripletDistanceMetric.COSINE",
      "triplet_margin": 0.5
  }

Training Hyperparameters

Non-Default Hyperparameters

—eval_strategy: steps
—per_device_train_batch_size: 4
—per_device_eval_batch_size: 4
—fp16: True
—multi_dataset_batch_sampler: round_robin

All Hyperparameters

<details><summary>Click to expand</summary>

—overwrite_output_dir: False
—do_predict: False
—eval_strategy: steps
—prediction_loss_only: True
—per_device_train_batch_size: 4
—per_device_eval_batch_size: 4
—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
—num_train_epochs: 3
—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: 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: True
—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: {'minnumparams': 0, 'xla': False, 'xlafsdpv2': False, 'xlafsdpgrad_ckpt': False}
—fsdp_transformer_layer_cls_to_wrap: None
—accelerator_config: {'splitbatches': False, 'dispatchbatches': None, 'evenbatches': True, 'useseedablesampler': True, 'nonblocking': False, 'gradientaccumulationkwargs': 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
—eval_on_start: False
—eval_use_gather_object: False
—batch_sampler: batch_sampler
—multi_dataset_batch_sampler: round_robin

</details>

Training Logs

Epoch	Step	Training Loss	dev_max_accuracy
0.3928	500	0.2652	-
0.7855	1000	0.1742	0.9241
1.0	1273	-	0.9179
1.1783	1500	0.1526	-
1.5711	2000	0.1237	0.9197
1.9639	2500	0.0983	-
2.0	2546	-	0.9197
2.3566	3000	0.0881	0.9294
2.7494	3500	0.0711	-
3.0	3819	-	0.9285

Framework Versions

—Python: 3.10.12
—Sentence Transformers: 3.2.0
—Transformers: 4.44.0
—PyTorch: 2.3.1+cu121
—Accelerate: 0.31.0
—Datasets: 2.20.0
—Tokenizers: 0.19.1

Citation

BibTeX

Sentence Transformers

bibtex

@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",
}

TripletLoss

bibtex

@misc{hermans2017defense,
    title={In Defense of the Triplet Loss for Person Re-Identification},
    author={Alexander Hermans and Lucas Beyer and Bastian Leibe},
    year={2017},
    eprint={1703.07737},
    archivePrefix={arXiv},
    primaryClass={cs.CV}
}

<!--

Glossary

Clearly define terms in order to be accessible across audiences. -->

<!--

Model Card Authors

Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction. -->

<!--

Model Card Contact

Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors. -->