Views
No views yet
SentenceTransformer(
(0): Transformer({'transformer_task': 'feature-extraction', 'modality_config': {'text': {'method': 'forward', 'method_output_name': 'last_hidden_state'}}, 'module_output_name': 'token_embeddings', 'architecture': 'BertModel'})
(1): Pooling({'embedding_dimension': 384, 'pooling_mode': 'mean', 'include_prompt': True})
(2): Normalize({})
)pip install -U sentence-transformers1from sentence_transformers import SentenceTransformer
2
3# Download from the 🤗 Hub
4model = SentenceTransformer("sentence_transformers_model_id")
5# Run inference
6sentences = [
7 'peach skin, neutral-warm undertone, golden blonde hair, light green eyes, — recommended color: salmon, style: edgy, category: coat',
8 'light beige skin, neutral-warm undertone, auburn light hair, steel blue eyes, — recommended color: turquoise, style: sporty, category: jeans',
9 'rosy beige skin, neutral-cool undertone, dark ash hair, blue eyes, — recommended color: dusty rose, style: classic, category: shorts',
10]
11embeddings = model.encode(sentences)
12print(embeddings.shape)
13# [3, 384]
14
15# Get the similarity scores for the embeddings
16similarities = model.similarity(embeddings, embeddings)
17print(similarities)
18# tensor([[1.0000, 0.9890, 0.3512],
19# [0.9890, 1.0000, 0.3301],
20# [0.3512, 0.3301, 1.0000]])sentence_0, sentence_1, and label| sentence_0 | sentence_1 | label | |
|---|---|---|---|
| type | string | string | float |
| modality | text | text | |
| details |
|
|
|
| sentence_0 | sentence_1 | label |
|---|---|---|
light beige skin, neutral-warm undertone, auburn light hair, light hazel eyes, — recommended color: light teal, style: elegant, category: coat | cool tan skin, cool undertone, silver white hair, black eyes, — recommended color: hot pink, style: chic, category: blazer | 0.0 |
golden skin, warm undertone, golden blonde hair, blue eyes, — recommended color: butter yellow, style: chic, category: top | light beige skin, warm undertone, honey blonde hair, blue eyes, — recommended color: lavender, style: casual, category: jeans | 1.0 |
golden skin, neutral-warm undertone, golden blonde hair, blue eyes, — recommended color: light camel, style: romantic, category: jeans | ivory skin, warm undertone, strawberry blonde hair, light hazel eyes, — recommended color: lavender, style: elegant, category: top | 1.0 |
ContrastiveLoss with these parameters:
1{
2 "distance_metric": "SiameseDistanceMetric.COSINE_DISTANCE",
3 "margin": 0.5,
4 "size_average": true
5}per_device_train_batch_size: 32num_train_epochs: 2per_device_eval_batch_size: 32multi_dataset_batch_sampler: round_robinper_device_train_batch_size: 32num_train_epochs: 2max_steps: -1learning_rate: 5e-05lr_scheduler_type: linearlr_scheduler_kwargs: Nonewarmup_steps: 0optim: adamw_torch_fusedoptim_args: Noneweight_decay: 0.0adam_beta1: 0.9adam_beta2: 0.999adam_epsilon: 1e-08optim_target_modules: Nonegradient_accumulation_steps: 1average_tokens_across_devices: Truemax_grad_norm: 1label_smoothing_factor: 0.0bf16: Falsefp16: Falsebf16_full_eval: Falsefp16_full_eval: Falsetf32: Nonegradient_checkpointing: Falsegradient_checkpointing_kwargs: Nonetorch_compile: Falsetorch_compile_backend: Nonetorch_compile_mode: Noneuse_liger_kernel: Falseliger_kernel_config: Noneuse_cache: Falseneftune_noise_alpha: Nonetorch_empty_cache_steps: Noneauto_find_batch_size: Falselog_on_each_node: Truelogging_nan_inf_filter: Trueinclude_num_input_tokens_seen: nolog_level: passivelog_level_replica: warningdisable_tqdm: Falseproject: huggingfacetrackio_space_id: Nonetrackio_bucket_id: Nonetrackio_static_space_id: Noneper_device_eval_batch_size: 32prediction_loss_only: Trueeval_on_start: Falseeval_do_concat_batches: Trueeval_use_gather_object: Falseeval_accumulation_steps: Noneinclude_for_metrics: []batch_eval_metrics: Falsesave_only_model: Falsesave_on_each_node: Falseenable_jit_checkpoint: Falsepush_to_hub: Falsehub_private_repo: Nonehub_model_id: Nonehub_strategy: every_savehub_always_push: Falsehub_revision: Noneload_best_model_at_end: Falseignore_data_skip: Falserestore_callback_states_from_checkpoint: Falsefull_determinism: Falseseed: 42data_seed: Noneuse_cpu: Falseaccelerator_config: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}parallelism_config: Nonedataloader_drop_last: Falsedataloader_num_workers: 0dataloader_pin_memory: Truedataloader_persistent_workers: Falsedataloader_prefetch_factor: Noneremove_unused_columns: Truelabel_names: Nonetrain_sampling_strategy: randomlength_column_name: lengthddp_find_unused_parameters: Noneddp_bucket_cap_mb: Noneddp_broadcast_buffers: Falseddp_static_graph: Noneddp_backend: Noneddp_timeout: 1800fsdp: Nonefsdp_config: Nonedeepspeed: Nonedebug: []skip_memory_metrics: Truedo_predict: Falseresume_from_checkpoint: Nonewarmup_ratio: Nonelocal_rank: -1prompts: Nonebatch_sampler: batch_samplermulti_dataset_batch_sampler: round_robinrouter_mapping: {}learning_rate_mapping: {}| Epoch | Step | Training Loss |
|---|---|---|
| 1.0 | 500 | 0.0087 |
| 2.0 | 1000 | 0.0007 |
1@inproceedings{reimers-2019-sentence-bert,
2 title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
3 author = "Reimers, Nils and Gurevych, Iryna",
4 booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
5 month = "11",
6 year = "2019",
7 publisher = "Association for Computational Linguistics",
8 url = "https://arxiv.org/abs/1908.10084",
9}1@inproceedings{hadsell2006dimensionality,
2 author={Hadsell, R. and Chopra, S. and LeCun, Y.},
3 booktitle={2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06)},
4 title={Dimensionality Reduction by Learning an Invariant Mapping},
5 year={2006},
6 volume={2},
7 number={},
8 pages={1735-1742},
9 doi={10.1109/CVPR.2006.100}
10}