SentenceTransformer

This is a sentence-transformers model trained. 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
  • Maximum Sequence Length: 512 tokens
  • Output Dimensionality: 768 tokens
  • Similarity Function: Cosine Similarity

Model Sources

Full Model Architecture

SentenceTransformer(
  (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: DistilBertModel 
  (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, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
)

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 = [
    '100% Cotton Throw Blanket for Couch Sofa Bed Outdoors Hypoallergenic 83"x70" Brown',
    'Hetao 100% Cotton Handmade Crochet Round Tablecloth Doilies Lace Table Covers,Beige, 27 Inch\n',
    'Life Clothing Co. Womens Tops Jade Tie Dye Hoodie (XL)\n',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 768]

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

Training Details

Training Dataset

Unnamed Dataset

  • Size: 1,830 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: 7 tokens
    • mean: 16.37 tokens
    • max: 23 tokens
    • min: 2 tokens
    • mean: 161.41 tokens
    • max: 512 tokens
    • min: 2 tokens
    • mean: 74.05 tokens
    • max: 512 tokens
  • Samples:
    sentence_0 sentence_1 sentence_2
    "acrylic lollipop holder cake pop stand with sticks, bags, and twist ties" Zealax 15pcs Treat Bags Gold Polka Dot Print Drawstring Plastic Party Favors for Cookie Roasting Treat Candy Buffet Gift Wrapping Goodies Package, 4.6 inches x 6.7 inches
    Twinkle Star Solid Brass Heavy Duty Adjustable Twist Hose Nozzle Jet Sweeper Nozzle, TWIS3231
    Product Description Shut Off Valve Shut Off Valve Adjustable Hose Nozzle Adjustable Twist Hose Nozzle Jet Sweeper Screw Threads 3/4" 3/4" 3/4" 3/4" 3/4" Shut-Off Valve YES YES YES YES NO Material Brass Brass Brass Brass Brass Package Includes 2 Pack 1 Pack 1 Pack 2 Pack 2 Pack Garden Hose Quick Connect Set Garden Hose Quick Connect Set Hose Caps Double Female Swivel Connectors Double Male Quick Connectors Screw Threads 3/4" 3/4" 3/4" 3/4" 3/4" Material Aluminum Brass Brass Brass Brass Package Includes 4 Sets 4 Sets 4 Pack 2 Pack 2 Pack Specifications: Body Material: Brass Package Includes: 1 x adjustable nozzle, 1 x jet sweeper nozzle. Twinkle Star Solid Brass Heavy Duty Adjustable Twist Hose Nozzle Jet Sweeper Nozzle Heavy-duty solid brass construction. With 4 holes at the tip for maximum pressure and water flow, fitted with O-ring seals at the back and front to prevent any leaks. Twisting barrel to adjusts water from a fine mist to a powerful jet stream. Fits standard garden hose, great for watering gardens, car washing, deck, siding & driveway cleaning and more. Notes: 1. Please choose the correct hose size. 2. To prevent leakage, make sure the jet has rubber ring. 3. If water leaks after a long period of use, please replace with a new washer. Read more Adjustable jet rotates from a light stream to powerful stream. Heavy duty brass 3/4”female thread. Solid brass integral inner core, anti - damage, anti - rust, anti - leakage, durable. Read more
    NFL Women's OTS Fleece Hoodie Ultra Game NFL womens Fleece Hoodie Pullover Sweatshirt Tie Neck
    Womens Antler Evolution Whitetail Tee Short Sleeve
    "Belkin QODE Ultimate Pro Keyboard Case for iPad Air 2 White" iPad Pro Guide
    Under Armour Boys' Prototype Short
    From the manufacturer Read more Read more Read more
  • Loss: TripletLoss with these parameters:
    {
        "distance_metric": "TripletDistanceMetric.EUCLIDEAN",
        "triplet_margin": 25.0
    }
    

Training Hyperparameters

Non-Default Hyperparameters

  • per_device_train_batch_size: 54
  • per_device_eval_batch_size: 54
  • num_train_epochs: 5
  • multi_dataset_batch_sampler: round_robin

All Hyperparameters

Click to expand
  • overwrite_output_dir: False
  • do_predict: False
  • eval_strategy: no
  • prediction_loss_only: True
  • per_device_train_batch_size: 54
  • per_device_eval_batch_size: 54
  • 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: 5
  • 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: False
  • 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: False
  • 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: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
  • fsdp_transformer_layer_cls_to_wrap: None
  • accelerator_config: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': 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

Framework Versions

  • Python: 3.10.12
  • Sentence Transformers: 3.1.1
  • Transformers: 4.44.2
  • PyTorch: 2.4.1+cu121
  • Accelerate: 0.34.2
  • Datasets: 3.0.0
  • Tokenizers: 0.19.1

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",
}

TripletLoss

@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}
}
Downloads last month
13
Safetensors
Model size
66.4M params
Tensor type
F32
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.