pilllll/finetuned-embedding-e5

SentenceTransformer based on intfloat/multilingual-e5-large

This is a sentence-transformers model finetuned from intfloat/multilingual-e5-large. 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
• Maximum Sequence Length: 512 tokens
• Output Dimensionality: 1024 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': 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:

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
sentences = [
    'query: หนังสือนิทาน',
    'passage: title: เด็กหญิงข้าวเปลือก author: หยาดฝน ธัญโชติกานต์. category: นิทาน description: ',
    'passage: title: Current drug discovery technologies author: N/A category: Drugs Design Periodicals, Pharmaceutical technology Periodicals, Drug Design, Technology, Pharmaceutical, Drugs Design, Pharmaceutical technology, Periodicals description: ',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 1024]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities)
# tensor([[ 1.0000,  0.7672, -0.0610],
#         [ 0.7672,  1.0000,  0.0661],
#         [-0.0610,  0.0661,  1.0000]])

Training Details

Training Dataset

Unnamed Dataset

• Size: 132,830 training samples
• Columns: sentence_0, sentence_1, and sentence_2
• Approximate statistics based on the first 1000 samples:

  	sentence_0	sentence_1	sentence_2
  type	string	string	string
  details	min: 6 tokens mean: 14.35 tokens max: 38 tokens	min: 17 tokens mean: 90.98 tokens max: 512 tokens	min: 19 tokens mean: 87.53 tokens max: 512 tokens

• Samples:

  sentence_0	sentence_1	sentence_2
  query: ไสยศาสตร์ สำหรับมือใหม่	passage: title: สถานการณ์พระพุทธศาสนา : กระแสไสยศาสตร์ author: พระธรรมปิฎก (ป.อ. ปยุตฺโต) category: ไสยศาสตร์, พุทธศาสนากับไสยศาสตร์ description:	passage: title: Hospitality marketing management author: Robert D. Reid category: Hospitality industry Marketing, Food service Marketing, Restaurants Marketing, Accueil (Tourisme) Marketing, Services alimentaires Marketing, Marketing, Tiếp thị, Hospitality industry, Khách sạn, Dịch vụ ăn uống, Restaurants, Quán ăn description:
  query: 伤科方	passage: title: 骨伤科效方集 author: Gengmin Tang category: Orthopedics, Medicine formulae, receipts, prescriptions, 伤科方 description:	passage: title: 福慧之道 author: Yinai Sun category: Happiness, Well-being, Conduct of life, Human comfort, Bonheur, Bien-être, Morale pratique, ethics (philosophical concept), comfort (sensation), Fo jiao Ren sheng zhe xue Tong su du wu description: Ben shu shi dui zheng ge zhong hua wen hua de zong jie, jiang shu ji fu ji hui de fang fa. nei rong bao gua : fu mai yu hui mai : ren sheng de xing fu er mai ; ru he jie fu hui er mai ; cai fu fu tian ; zhi hui fu tian ; fu tian fa ze ; ri xing yi shan ; fu hui ren sheng
  query: basic Acid-Base Imbalance problems book	passage: title: Acid-base, fluids, and electrolytes made ridiculously simple author: Richard A. Preston category: Acid-Base Imbalance problems, Body Fluids problems, Water-Electrolyte Imbalance problems, Water-electrolyte imbalance description:	passage: title: Fetal and neonatal neurology and neurosurgery author: Malcolm I. Levene category: Brain Diseases, Newborn infants, Nervous system Surgery, Nervous system Diseases, Brain embryology, Fetal Diseases therapy, Infant, Newborn, Neurosurgery, Prenatal Diagnosis methods, Ultrasonography methods, Neurosurgical Procedures, Cerveau Maladies, Nouveau-nés, Neurochirurgie, Système nerveux Maladies description:

• 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
• per_device_eval_batch_size: 64
• num_train_epochs: 1
• 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: 64
• per_device_eval_batch_size: 64
• 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: 1
• 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: {}

Training Logs

Epoch	Step	Training Loss
0.2408	500	0.4763
0.4817	1000	0.1799
0.7225	1500	0.1731
0.9634	2000	0.1628

Framework Versions

• Python: 3.12.13
• Sentence Transformers: 5.3.0
• Transformers: 5.0.0
• PyTorch: 2.10.0+cu128
• Accelerate: 1.13.0
• 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{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},
}