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 retrieval.

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
• Supported Modality: Text

Model Sources

• Documentation: Sentence Transformers Documentation
• Repository: Sentence Transformers on GitHub
• Hugging Face: Sentence Transformers on Hugging Face

Full Model Architecture

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({})
)

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("opnsrcntrbtrian/csne-minilm-retrieval-50k")
# Run inference
queries = [
    'Go straight down and turn off the motors. Do not call this function if you use the with keyword. Landing is done automatically when the context goes out of scope.',
]
documents = [
    'MotionCommander.land def land(self, velocity=VELOCITY): pass if self._is_flying: self.down(self._thread.get_height(), velocity) self._thread.stop() self._thread = None self._cf.commander.send_stop_setpoint() self._is_flying = False',
    "issuer_create_credential async def issuer_create_credential(wallet_handle: int, cred_offer_json: str, cred_req_json: str, cred_values_json: str, rev_reg_id: Optional[str], blob_storage_reader_handle: Optional[int]) -> (str, Optional[str], Optional[str]): pass logger = logging.getLogger(__name__) logger.debug('issuer_create_credential: >>> wallet_handle: %r, cred_offer_json: %r, cred_req_json: %r, cred_values_json: %r, rev_reg_id: %r, blob_storage_reader_handle: %r', wallet_handle, cred_offer_json, cred_req_json, cred_values_json, rev_reg_id, blob_storage_reader_handle) if not hasattr(issuer_create_credential, 'cb'): logger.debug('issuer_create_credential: Creating callback') issuer_create_credential.cb = create_cb(CFUNCTYPE(None, c_int32, c_int32, c_char_p, c_char_p, c_char_p)) c_wallet_handle = c_int32(wallet_handle) c_cred_offer_json = c_char_p(cred_offer_json.encode('utf-8')) c_cred_req_json = c_char_p(cred_req_json.encode('utf-8')) c_cred_values_json = c_char_p(cred_values_json.encode('utf-8')) c_rev_reg_id = c_char_p(rev_reg_id.encode('utf-8')) if rev_reg_id is not None else None c_blob_storage_reader_handle = c_int32(blob_storage_reader_handle) if blob_storage_reader_handle else -1 cred_json, cred_revoc_id, revoc_reg_delta_json = await do_call('indy_issuer_create_credential', c_wallet_handle, c_cred_offer_json, c_cred_req_json, c_cred_values_json, c_rev_reg_id, c_blob_storage_reader_handle, issuer_create_credential.cb) cred_json = cred_json.decode() cred_revoc_id = cred_revoc_id.decode() if cred_revoc_id else None revoc_reg_delta_json = revoc_reg_delta_json.decode() if revoc_reg_delta_json else None res = (cred_json, cred_revoc_id, revoc_reg_delta_json) logger.debug('issuer_create_credential: <<< res: %r', res) return res",
    'EventPlayer.project_events def project_events(self, initial_state, domain_events): pass return reduce(self._mutator_func or self.mutate, domain_events, initial_state)',
]
query_embeddings = model.encode_query(queries)
document_embeddings = model.encode_document(documents)
print(query_embeddings.shape, document_embeddings.shape)
# [1, 384] [3, 384]

# Get the similarity scores for the embeddings
similarities = model.similarity(query_embeddings, document_embeddings)
print(similarities)
# tensor([[ 0.5800, -0.1288,  0.1306]])

Training Details

Training Dataset

Unnamed Dataset

• Size: 50,000 training samples
• Columns: query and code
• Approximate statistics based on the first 100 samples:

  	query	code
  type	string	string
  modality	text	text
  details	min: 6 tokensmean: 33.5 tokensmax: 187 tokens	min: 37 tokensmean: 134.54 tokensmax: 256 tokens

• Samples:

  query	code
  Deal with the response url from a Discovery Service	Base.parse_discovery_service_response def parse_discovery_service_response(url='', query='', returnIDParam='entityID'): pass if url: part = urlparse(url) qsd = parse_qs(part[4]) elif query: qsd = parse_qs(query) else: qsd = {} try: return qsd[returnIDParam][0] except KeyError: return ''
  Given a set of argument tuples, set their value in a data dictionary if not blank	arg_tup_to_dict def arg_tup_to_dict(argument_tuples): pass data = dict() for arg_name, arg_val in argument_tuples: if arg_val is not None: if arg_val is True: arg_val = 'true' elif arg_val is False: arg_val = 'false' data[arg_name] = arg_val return data
  Returns a generator over the (phenotypeAssociationSet, nextPageToken) pairs defined by the specified request	Backend.phenotypeAssociationSetsGenerator def phenotypeAssociationSetsGenerator(self, request): pass dataset = self.getDataRepository().getDataset(request.dataset_id) return self._topLevelObjectGenerator(request, dataset.getNumPhenotypeAssociationSets(), dataset.getPhenotypeAssociationSetByIndex)

• Loss: MultipleNegativesRankingLoss with these parameters:

  {
      "scale": 20.0,
      "similarity_fct": "cos_sim",
      "gather_across_devices": false,
      "directions": [
          "query_to_doc"
      ],
      "partition_mode": "joint",
      "hardness_mode": null,
      "hardness_strength": 0.0
  }
  

Training Hyperparameters

Non-Default Hyperparameters

• per_device_train_batch_size: 64
• num_train_epochs: 1
• learning_rate: 2e-05
• warmup_steps: 0.1
• dataloader_drop_last: True

All Hyperparameters

• per_device_train_batch_size: 64
• num_train_epochs: 1
• max_steps: -1
• learning_rate: 2e-05
• lr_scheduler_type: linear
• lr_scheduler_kwargs: None
• warmup_steps: 0.1
• optim: adamw_torch_fused
• optim_args: None
• weight_decay: 0.0
• adam_beta1: 0.9
• adam_beta2: 0.999
• adam_epsilon: 1e-08
• optim_target_modules: None
• gradient_accumulation_steps: 1
• average_tokens_across_devices: True
• max_grad_norm: 1.0
• label_smoothing_factor: 0.0
• bf16: False
• fp16: False
• bf16_full_eval: False
• fp16_full_eval: False
• tf32: None
• gradient_checkpointing: False
• gradient_checkpointing_kwargs: None
• torch_compile: False
• torch_compile_backend: None
• torch_compile_mode: None
• use_liger_kernel: False
• liger_kernel_config: None
• use_cache: False
• neftune_noise_alpha: None
• torch_empty_cache_steps: None
• auto_find_batch_size: False
• log_on_each_node: True
• logging_nan_inf_filter: True
• include_num_input_tokens_seen: no
• log_level: passive
• log_level_replica: warning
• disable_tqdm: False
• project: huggingface
• trackio_space_id: None
• trackio_bucket_id: None
• trackio_static_space_id: None
• per_device_eval_batch_size: 8
• prediction_loss_only: True
• eval_on_start: False
• eval_do_concat_batches: True
• eval_use_gather_object: False
• eval_accumulation_steps: None
• include_for_metrics: []
• batch_eval_metrics: False
• save_only_model: False
• save_on_each_node: False
• enable_jit_checkpoint: False
• push_to_hub: False
• hub_private_repo: None
• hub_model_id: None
• hub_strategy: every_save
• hub_always_push: False
• hub_revision: None
• load_best_model_at_end: False
• ignore_data_skip: False
• restore_callback_states_from_checkpoint: False
• full_determinism: False
• seed: 42
• data_seed: None
• use_cpu: False
• accelerator_config: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
• parallelism_config: None
• dataloader_drop_last: True
• dataloader_num_workers: 0
• dataloader_pin_memory: True
• dataloader_persistent_workers: False
• dataloader_prefetch_factor: None
• remove_unused_columns: True
• label_names: None
• train_sampling_strategy: random
• length_column_name: length
• ddp_find_unused_parameters: None
• ddp_bucket_cap_mb: None
• ddp_broadcast_buffers: False
• ddp_static_graph: None
• ddp_backend: None
• ddp_timeout: 1800
• fsdp: None
• fsdp_config: None
• deepspeed: None
• debug: []
• skip_memory_metrics: True
• do_predict: False
• resume_from_checkpoint: None
• warmup_ratio: None
• local_rank: -1
• prompts: None
• batch_sampler: batch_sampler
• multi_dataset_batch_sampler: proportional
• router_mapping: {}
• learning_rate_mapping: {}

Training Logs

Training Time

• Training: 11.7 minutes

Framework Versions

• Python: 3.12.13
• Sentence Transformers: 5.6.0
• Transformers: 5.13.1
• PyTorch: 2.11.0+cu128
• Accelerate: 1.14.0
• Datasets: 4.0.0
• Tokenizers: 0.22.2

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{oord2019representationlearningcontrastivepredictive,
      title={Representation Learning with Contrastive Predictive Coding},
      author={Aaron van den Oord and Yazhe Li and Oriol Vinyals},
      year={2019},
      eprint={1807.03748},
      archivePrefix={arXiv},
      primaryClass={cs.LG},
      url={https://arxiv.org/abs/1807.03748},
}