SentenceTransformer based on sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2

This is a sentence-transformers model finetuned from sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2. It maps sentences & paragraphs to a 384-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 Sources

Full Model Architecture

SentenceTransformer(
  (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel 
  (1): Pooling({'word_embedding_dimension': 384, '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("T-Blue/tsdae_pro_MiniLM_L12_2")
# Run inference
sentences = [
    'ā¤Ŧđ‘€Ģđ‘Ŗđ‘€ŗā¤Ē đ‘€ĸđ‘€ĸ đ‘€ŗđ‘€Ģđ‘€ĸ𑀟đ‘Ļ đ‘€ ā¤šđ‘€˛đ‘€ĸ đ‘€ ā¤šđ‘€Ģđ‘€ĸđ‘€ đ‘€ ā¤šđ‘€Ÿā¤¤đ‘€ĸđ‘€Ļ ā¤Ē⤚đ‘€ĸđ‘€ ā¤šđ‘€žđ‘Ŗđ‘€Ÿ đ‘€Ŗā¤š đ‘€˛ā¤šđ‘€ŗā¤šā¤˛ā¤¨ā¤˛ā¤˛ā¤¨đ‘€žā¤š ā¤Ŗā¤šđ‘€Ÿā¤š ā¤ĸ⤚ đ‘€ ā¤šđ‘€¤ā¤šā¤¨đ‘€Ÿā¤š ⤤đ‘€ĸ𑀞đ‘€ĸ𑀟 đ‘€Ģā¤šđ‘€Ÿđ‘€žā¤šā¤˛đ‘€ĸ ⤪⤚⤪đ‘€ĸ𑀟',
    'ā¤šđ‘€ đ‘€ĸ𑀟ā¤Ē⤚⤤⤤đ‘€ĸ⤪⤚ ⤚ ⤤đ‘€ĸ𑀞đ‘€ĸ𑀟 ā¤Ŧđ‘€Ģđ‘Ŗđ‘€ŗā¤Ē đ‘€ŗđ‘Ļđ‘€Ēđ‘€ĸđ‘Ļđ‘€ŗ đ‘€ĸđ‘€ĸ đ‘€ŗđ‘€Ģđ‘€ĸ𑀟đ‘Ļ đ‘€ ā¤šđ‘€˛đ‘€ĸ đ‘€ ā¤šđ‘€Ģđ‘€ĸđ‘€ đ‘€ ā¤šđ‘€Ÿā¤¤đ‘€ĸđ‘€Ļ ā¤Ē⤚đ‘€Ēđ‘Ļ đ‘€Ŗā¤š ā¤žđ‘€ĸ𑀠ā¤ĸđ‘€ĸ𑀟 đ‘€ĸ𑀟ā¤Ŧā¤šđ‘€Ÿā¤Ē⤚ā¤Ēā¤Ēā¤¨đ‘€Ÿ ā¤Ēđ‘€ŗā¤šđ‘€Ēđ‘€ĸ𑀟 ā¤Ē⤚đ‘€ĸđ‘€ ā¤šđ‘€žđ‘Ŗđ‘€Ÿ đ‘€Ŗđ‘€ĸđ‘€Ēđ‘Ļā¤ĸ⤚ đ‘€Ŗā¤š đ‘€˛ā¤šđ‘€ŗā¤šā¤˛ā¤¨ā¤˛ā¤˛ā¤¨đ‘€žā¤š đ‘€Ÿā¤š ā¤šđ‘€ đ‘€ĸđ‘€Ÿā¤¤đ‘€ĸđ‘€Ļ ā¤Ŗā¤šđ‘€Ÿā¤š ā¤ĸ⤚ đ‘€ ā¤šđ‘€¤ā¤šā¤¨đ‘€Ÿā¤š ⤤đ‘€ĸ𑀞đ‘€ĸ𑀟 đ‘€žđ‘€ąā¤šđ‘€Ÿā¤¤đ‘€ĸ⤪⤚đ‘€Ē đ‘€Ģā¤šđ‘€Ÿđ‘€žā¤šā¤˛đ‘€ĸ ⤪⤚⤪đ‘€ĸ𑀟 ā¤Ēā¤šđ‘€˛đ‘€ĸ⤪⤚đ‘€Ēđ‘€ŗā¤¨đ‘€¯',
    'ā¤Ēđ‘Ŗā¤§đ‘€ŗā¤Ŗ ⤧đ‘€Ģđ‘€ĸđ‘€Ēđ‘€ĸ đ‘€ā¤šđ‘€Ÿ đ‘€Ģ⤚đ‘€ĸ𑀲đ‘Ļ đ‘€ŗđ‘€Ģđ‘€ĸ ⤚ đ‘€Ēā¤šđ‘€Ÿā¤šđ‘€Ē 𑀭𑀭 ā¤Ŧ⤚ đ‘€ąā¤šā¤Ēā¤šđ‘€Ÿ ⤚ā¤Ŧā¤¨đ‘€ŗā¤Ē⤚ 𑀭ā¤Ĩ𑀗𑀧𑀮 ā¤žā¤šđ‘€Ÿ đ‘€ąā¤šđ‘€ŗā¤šđ‘€Ÿ ā¤ĸā¤šđ‘€Ŗđ‘€ đ‘€ĸ𑀟ā¤Ēđ‘Ŗđ‘€Ÿ ā¤žā¤šđ‘€Ÿ đ‘€¤ā¤šđ‘€ ā¤ĸđ‘€ĸ⤚ 𑀟đ‘Ļđ‘€¯',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 384]

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

Training Details

Training Dataset

Unnamed Dataset

  • Size: 64,000 training samples
  • Columns: sentence_0 and sentence_1
  • Approximate statistics based on the first 1000 samples:
    sentence_0 sentence_1
    type string string
    details
    • min: 4 tokens
    • mean: 37.72 tokens
    • max: 292 tokens
    • min: 4 tokens
    • mean: 90.07 tokens
    • max: 512 tokens
  • Samples:
    sentence_0 sentence_1
    đ‘€žā¤¨đ‘€Ŗā¤¨ ā¤ĸđ‘€ĸđ‘€Ē𑀟đ‘€ĸ𑀟đ‘€Ļđ‘€žā¤¨đ‘€ŗā¤š ā¤Ēđ‘Ļđ‘€žā¤¨đ‘€Ÿ ā¤Ēđ‘Ļđ‘€žā¤¨đ‘€Ÿ ā¤Ē⤚ā¤Ŧ⤚ ā¤Ŗā¤šđ‘€Ÿā¤š đ‘€žā¤¨đ‘€Ŗā¤¨ đ‘€Ŗā¤š ā¤ĸđ‘€ĸđ‘€Ē𑀟đ‘€ĸ𑀟đ‘€Ļđ‘€žā¤¨đ‘€ŗā¤š đ‘€Ŗā¤š ā¤Ēđ‘Ļđ‘€žā¤¨đ‘€Ÿ ā¤Ē⤚⤤đ‘€Ģđ‘Ŗā¤Ŧā¤šđ‘€¯
    ⤚ ⤤đ‘€ĸā¤ĸđ‘€ĸā¤Ŗđ‘Ŗā¤Ŗđ‘€ĸ𑀟 đ‘€ŗā¤šđ‘€Ŗā¤šđ‘€Ēđ‘€ąā¤šđ‘€Ē đ‘€ŗā¤¨ ā¤ā¤šđ‘€Ē⤚ đ‘€ ā¤šā¤Ēđ‘€ŗā¤šā¤Ŗđ‘€ĸ𑀟 ⤚ā¤ĸđ‘Ŗđ‘€žā¤šđ‘€ĸđ‘€žā¤šđ‘€ ā¤šđ‘€Ē ⤚ ā¤Ŗā¤šđ‘€ąā¤šđ‘€Ÿā¤¤đ‘€ĸ𑀟 ⤤đ‘€ĸā¤ĸđ‘€ĸā¤Ŗđ‘Ŗā¤Ŗđ‘€ĸ𑀟 đ‘€ŗā¤šđ‘€Ŗā¤šđ‘€Ēđ‘€ąā¤šđ‘€Ē đ‘€˜ā¤šđ‘€ ā¤šđ‘€™ā¤šđ‘€Ļ đ‘€ ā¤šđ‘€ŗā¤¨ ā¤šđ‘€ đ‘€˛ā¤šđ‘€Ÿđ‘€ĸ đ‘€¤ā¤š đ‘€ŗā¤¨ đ‘€ĸ⤪⤚ ā¤ā¤šđ‘€Ē⤚ đ‘€ ā¤¨ā¤Ēā¤šđ‘€Ÿđ‘Ļ ⤚ đ‘€ ā¤šā¤Ēđ‘€ŗā¤šā¤Ŗđ‘€ĸ𑀟 ⤚ā¤ĸđ‘Ŗđ‘€žā¤šđ‘€Ÿđ‘€ŗā¤¨đ‘€¯
    đ‘€Ŗā¤š ā¤Ŧā¤¨đ‘€Ŗā¤¨đ‘€ đ‘€ ā¤šđ‘€ąā¤š đ‘€˜ā¤šđ‘€Ēđ‘€ĸđ‘€Ŗā¤¨đ‘€Ÿ đ‘€ ā¤¨đ‘€˜ā¤šā¤˛ā¤˛ā¤¨ ā¤Ē⤚ đ‘€¯ ā¤Ē⤚ ā¤ĸ⤚ đ‘€Ŗā¤š ā¤Ŧā¤¨đ‘€Ŗā¤¨đ‘€ đ‘€ ā¤šđ‘€ąā¤š ā¤Ŧ⤚ đ‘€˜ā¤šđ‘€Ēđ‘€ĸđ‘€Ŗā¤¨đ‘€Ÿ ā¤šđ‘€Ÿā¤šđ‘€Ē⤤đ‘€Ģđ‘€ĸđ‘€ŗā¤Ē đ‘€Ŗā¤šā¤ĸā¤šđ‘€Ÿā¤ˇđ‘€Ŗā¤šā¤ĸā¤šđ‘€Ÿ đ‘€Ŗā¤š đ‘€ ā¤¨đ‘€˜ā¤šā¤˛ā¤˛ā¤¨ đ‘€ ā¤šđ‘€ŗā¤¨ ā¤šā¤˛ā¤šā¤ā¤š đ‘€Ŗā¤š ā¤ā¤¨đ‘€Ÿā¤Ŧđ‘€ĸ⤪⤚đ‘€Ē đ‘€ ā¤šđ‘€™ā¤šđ‘€ĸđ‘€žā¤šā¤Ē⤚ đ‘€™ā¤Ŗā¤šđ‘€Ÿā¤¤đ‘€ĸ ā¤Ē⤚ đ‘€˜ā¤šđ‘€ ā¤¨đ‘€ŗ đ‘€¯
  • Loss: DenoisingAutoEncoderLoss

Training Hyperparameters

Non-Default Hyperparameters

  • per_device_train_batch_size: 16
  • per_device_eval_batch_size: 16
  • 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: 16
  • per_device_eval_batch_size: 16
  • per_gpu_train_batch_size: None
  • per_gpu_eval_batch_size: None
  • gradient_accumulation_steps: 1
  • eval_accumulation_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: 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
  • batch_sampler: batch_sampler
  • multi_dataset_batch_sampler: round_robin

Training Logs

Epoch Step Training Loss
0.125 500 2.5392
0.25 1000 1.4129
0.375 1500 1.3383
0.5 2000 1.288
0.625 2500 1.2627
0.75 3000 1.239
0.875 3500 1.2208
1.0 4000 1.2041
1.125 4500 1.1743
1.25 5000 1.1633
1.375 5500 1.1526
1.5 6000 1.1375
1.625 6500 1.1313
1.75 7000 1.1246
1.875 7500 1.1162
2.0 8000 1.1096
2.125 8500 1.0876
2.25 9000 1.0839
2.375 9500 1.0791
2.5 10000 1.0697
2.625 10500 1.0671
2.75 11000 1.0644
2.875 11500 1.0579
3.0 12000 1.0528

Framework Versions

  • Python: 3.10.12
  • Sentence Transformers: 3.0.1
  • Transformers: 4.42.4
  • PyTorch: 2.3.1+cu121
  • Accelerate: 0.33.0
  • Datasets: 2.18.0
  • 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",
}

DenoisingAutoEncoderLoss

@inproceedings{wang-2021-TSDAE,
    title = "TSDAE: Using Transformer-based Sequential Denoising Auto-Encoderfor Unsupervised Sentence Embedding Learning",
    author = "Wang, Kexin and Reimers, Nils and Gurevych, Iryna", 
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2021",
    month = nov,
    year = "2021",
    address = "Punta Cana, Dominican Republic",
    publisher = "Association for Computational Linguistics",
    pages = "671--688",
    url = "https://arxiv.org/abs/2104.06979",
}
Downloads last month
38
Safetensors
Model size
0.1B params
Tensor type
F32
¡
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for T-Blue/tsdae_pro_MiniLM_L12_2

Papers for T-Blue/tsdae_pro_MiniLM_L12_2