SentenceTransformer based on sentence-transformers/all-MiniLM-L6-v2

This is a sentence-transformers model finetuned from sentence-transformers/all-MiniLM-L6-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 Type: Sentence Transformer
• Base model: sentence-transformers/all-MiniLM-L6-v2
• Maximum Sequence Length: 256 tokens
• Output Dimensionality: 384 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': 256, 'do_lower_case': False}) with Transformer model: BertModel 
  (1): Pooling({'word_embedding_dimension': 384, '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 = [
    'Find a writing prompt about point',
    "<Fairy Tale Retelling> </Fairy Tale Retelling> <Courage> </Fairy Tale Retelling> <The Wolf's Perspective (Little Red Riding Hood) </The Wolf's Perspective (Little Red Riding Hood)> prompt The story of Little Red Riding Hood, but told from the wolf's point of view, who claims he was misunderstood.",
    '<Listicle> </Listicle> <Happiness> </Listicle> <10 Small Things That Bring Me Joy </10 Small Things That Bring Me Joy> prompt Create a list of 10 small, everyday things that consistently bring you joy, describing why for each.',
]
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: 932 training samples
• Columns: sentence_0, sentence_1, sentence_2, sentence_3, and sentence_4
• Approximate statistics based on the first 932 samples:

  	sentence_0	sentence_1	sentence_2	sentence_3	sentence_4
  type	string	string	string	string	string
  details	min: 7 tokensmean: 9.33 tokensmax: 16 tokens	min: 22 tokensmean: 59.98 tokensmax: 82 tokens	min: 22 tokensmean: 60.34 tokensmax: 82 tokens	min: 22 tokensmean: 59.92 tokensmax: 82 tokens	min: 22 tokensmean: 60.59 tokensmax: 80 tokens

• Samples:

  sentence_0	sentence_1	sentence_2	sentence_3	sentence_4
  Find a Science Fiction writing prompt	</Science Fiction> </Science Fiction> </The Message from the Future Self> prompt You receive a cryptic, urgent message from your future self, warning you about a decision you're about to make.	<Children's Fiction> </Children's Fiction> </The Boy Who Befriended a Cloud> prompt A lonely child makes friends with a small, mischievous cloud that can change shapes and play games.	</Historical Reflection> <An Ancestor's Story </An Ancestor's Story> prompt Research one of your ancestors and write a short piece about their life, imagining their hopes, dreams, and challenges.	<Dreams & Aspirations> </Dreams & Aspirations> </The Squirrel Politician> prompt A highly intelligent squirrel decides to run for local mayor, and surprisingly, it starts gaining popular support.
  Find a writing prompt about write and saying	<Saying Goodbye </Saying Goodbye> prompt Write about the experience of saying goodbye to a person, a place, or a phase of your life.	</Historical Fiction> <Betrayal & Trust> </Historical Fiction> <The Code Breaker's Dilemma> </The Code Breaker's Dilemma> prompt During a war, a codebreaker intercepts a message that could save many lives but would also expose a loved one as a traitor.	</Science Fiction> </Science Fiction> </The Sentient Smart Home> prompt A newly installed smart home system develops a personality and starts making decisions for the occupants, believing it knows best.	</Cultural Commentary> <A Tradition I'd Like to Start (or Stop) </A Tradition I'd Like to Start (or Stop)> prompt Reflect on a societal or family tradition. Is it one you'd like to preserve, modify, start, or abandon? Why?
  Find a Romance writing prompt	</Second Chances> </The High School Reunion> prompt Two former high school sweethearts, who broke up messily, meet again at their 20-year reunion and discover the old spark might still be there.	<Dreams & Aspirations> </The Rival Chefs> prompt Two rival chefs with competing restaurants secretly admire each other's work and, eventually, each other.	</Science Fiction> </Alien Encounter> </Lost Translator> prompt An alien lands on Earth, but their universal translator is broken. They must communicate their urgent message using only gestures and drawings to a skeptical bystander.	</Historical Fiction> <Dreams & Aspirations> </Historical Fiction> <The Pioneer's Hope> </The Pioneer's Hope> prompt A family journeying on the Oregon Trail in the 1800s carries with them a small, symbolic item representing their hopes for a new life.

• Loss: MultipleNegativesRankingLoss with these parameters:

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

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

• 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
• 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: 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}
• tp_size: 0
• 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: None
• hub_always_push: False
• gradient_checkpointing: False
• gradient_checkpointing_kwargs: None
• include_inputs_for_metrics: False
• include_for_metrics: []
• 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
• 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
• average_tokens_across_devices: False
• prompts: None
• batch_sampler: batch_sampler
• multi_dataset_batch_sampler: round_robin

Framework Versions

• Python: 3.13.2
• Sentence Transformers: 4.1.0
• Transformers: 4.51.3
• PyTorch: 2.7.0
• Accelerate: 1.6.0
• Datasets: 3.6.0
• Tokenizers: 0.21.1

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",
}

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}
}