mpnet_fashion_5k

SentenceTransformer based on sentence-transformers/all-mpnet-base-v2

This is a sentence-transformers model finetuned from sentence-transformers/all-mpnet-base-v2. 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: sentence-transformers/all-mpnet-base-v2 <!-- at revision 9a3225965996d404b775526de6dbfe85d3368642 -->
• Maximum Sequence Length: 128 tokens
• Output Dimensionality: 768 tokens
• Similarity Function: Cosine Similarity

<!-- - **Training Dataset:** Unknown --> <!-- - **Language:** Unknown --> <!-- - **License:** Unknown -->

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': 128, 'do_lower_case': False}) with Transformer model: MPNetModel 
  (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})
)

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("knguyennguyen/mpnet_fashion_5k")
# Run inference
sentences = [
    "I'm looking for a versatile and comfortable outerwear option that can provide warmth and protection from the wind. It should be suitable for both adults and kids, easy to clean, and made from a soft and breathable material.",
    "Title: Cover Custom Western Texas Stars Washable and Reusable Warm Windproof for Women Men Boys Girls Kids Descripion: ['Our Products Are Made Of High-Quality 100% Polyester Fiber, Which Is Very Soft, Breathable And Washable.']",
    'Title: Goodthreads Men\'s Soft Cotton Long-Sleeve Pullover Hoodie T-Shirt Descripion: [\'An Amazon brand - This pullover hoodie in soft cotton features a self-tie drawstring and a kangaroo pocket. Made in our Signature Tumbled Cotton for a soft, yet sturdy, hand. We utilize a unique Heritage Wash to give our garments a custom, lived-in feel right away\'\n "Goodthreads\' collection of men\'s clothing crafted with care takes wear-everywhere apparel to the next level. Create can\'t-miss pairings with long- and short-sleeve button-down shirts in standard and slim fits, plus chino pants and shorts made from wrinkle-free non-iron fabric. With these classics-and T-shirts, polo shirts, and outerwear to round out your look-Goodthreads is your go-to for wardrobe staples with the style you want."]',
]
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]

<!-- ### 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.* --> <!-- ## 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: 4,693 training samples
• Columns: <code>sentence_0</code> and <code>sentence_1</code>
• Approximate statistics based on the first 1000 samples:

  	sentence_0	sentence_1
  type	string	string
  details	<ul><li>min: 28 tokens</li><li>mean: 47.05 tokens</li><li>max: 93 tokens</li></ul>	<ul><li>min: 22 tokens</li><li>mean: 107.27 tokens</li><li>max: 128 tokens</li></ul>

• Samples:

  sentence_0	sentence_1
  <code>I'm looking for a bulk selection of decorative pieces that can be used to create unique jewelry and craft projects. They should come in a variety of styles, with a classic gold finish, and be suitable for personalizing items like necklaces or bracelets. These accessories should also be versatile enough for various crafting applications and make a lovely gift for special occasions.</code>	<code>Title: Wholesale Bulk 50PCS Mixed Gold Charms Pendants DIY for Jewelry Making and Crafting Descripion: ['50pcs Mixed KC Gold Charms Pendants for Jewelry Making, DIY Craft Charms Bulk for Necklace Bracelet Jewelry Making Crafting'<br> 'Color:' 'KC Gold.' 'Size:' '0.42" - 1.15" (11 - 28 mm).'<br> 'Main Material:' 'Alloy, Metal.' 'Package Include:'<br> "50pcs gold charm. 1 pcs chamois cloth of SUNEEY.(Suitable for cleaning and polishing jewelry.) Gold charm, it's fashion, creative, full of special means, is a very useful accessory,Exquisite and classical design charms.It can be used in all kinds of decoration. A good gift for yourself or friends, or birthday gift, anniversary present. Suit for key chain, bag pendant, sweater chain pendants, ornaments, escort cards, scrapbooking, and other crafts etc. These charm can be used to create earrings, necklaces, charm bracelets, and all kinds of jewelry making and craft projects. Perfect for scrapbooking project, necklace pendant drop, jewelry making accessories. Jewelry Making Accessory Mixed wholesale metal charms Assorted themes great array of subjects and styles for all kinds of interests Great for parties or groups. This gold pendant set is very charming with the unique design. It is simple and understated but gorgeous and classy. This pretty design can highlight your appearance, grasp everyone's eyes in the crowd. We’re confident that you will love them,as it will make you stand out."]</code>
  <code>I'm looking for a stylish and comfortable cropped top that I can easily throw on after my workouts. It should be versatile enough for casual outings and have a fit that flatters the figure.</code>	<code>Title: Core 10 Women's Soft Workout Cropped Hoodie Sweatshirt Descripion: ['An Amazon brand - This cropped Hoodie is a wardrobe-essential sweatshirt that features an easy, flattering fit for all your post-workout, layering, or everyday styling needs'<br> 'Empowering women to reach their full potential is at the heart of what we do. Because when you’re wearing Core 10, you’re ready to experience more. Be more. Live more.']</code>
  <code>I'm looking for a comfortable and stylish top for women that has a relaxed fit and a hood. It should come in trendy colors and allow for easy movement, making it perfect for casual outings or workouts.</code>	<code>Title: PUMA Ladies' Hooded Tee Descripion: ['Features: PUMA Colors: Black, Pink, and Purple Dropped shoulder seams Side slits for enhanced range of motion Mesh interior lined hood Puma Branded taping inside of neckline Content: 60% Cotton

• Loss: <code>MultipleNegativesRankingLoss</code> with these parameters:

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

Training Hyperparameters

Non-Default Hyperparameters

• per_device_train_batch_size: 128
• per_device_eval_batch_size: 128
• num_train_epochs: 5
• multi_dataset_batch_sampler: round_robin

All Hyperparameters

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

• overwrite_output_dir: False
• do_predict: False
• eval_strategy: no
• prediction_loss_only: True
• per_device_train_batch_size: 128
• per_device_eval_batch_size: 128
• 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
• use_liger_kernel: False
• eval_use_gather_object: False
• batch_sampler: batch_sampler
• multi_dataset_batch_sampler: round_robin

</details>

Framework Versions

• Python: 3.11.11
• Sentence Transformers: 3.1.1
• Transformers: 4.45.2
• PyTorch: 2.5.1+cu121
• Accelerate: 1.2.1
• Datasets: 3.2.0
• Tokenizers: 0.20.3

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}
}

<!-- ## 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.* -->