SentenceTransformer

class sentence_transformers.sentence_transformer.model.SentenceTransformer(model_name_or_path: str | None = None, *, modules: list[Module] | None = None, device: str | None = None, prompts: dict[str, str] | None = None, default_prompt_name: str | None = None, cache_folder: str | None = None, trust_remote_code: bool = False, revision: str | None = None, local_files_only: bool = False, token: bool | str | None = None, use_auth_token: bool | str | None = None, model_kwargs: dict[str, Any] | None = None, processor_kwargs: dict[str, Any] | None = None, config_kwargs: dict[str, Any] | None = None, model_card_data: SentenceTransformerModelCardData | None = None, backend: Literal['torch', 'onnx', 'openvino'] = 'torch', similarity_fn_name: Literal['cosine', 'dot', 'euclidean', 'manhattan'] | SimilarityFunction | None = None, truncate_dim: int | None = None)[source]

Loads or creates a SentenceTransformer model that can be used to map text and other inputs to dense embeddings.

Parameters:

model_name_or_path (str, optional) – If a filepath on disk, loads the model from that path. Otherwise, tries to download a pre-trained SentenceTransformer model. If that fails, tries to construct a model from the Hugging Face Hub with that name. Defaults to None.
modules (list[nn.Module], optional) – A list of torch modules that are called sequentially. Can be used to create custom SentenceTransformer models from scratch. Defaults to None.
device (str, optional) – Device (like "cuda", "cpu", "mps", "npu") that should be used for computation. If None, checks if a GPU can be used. Defaults to None.
prompts (dict[str, str], optional) – A dictionary with prompts for the model. The key is the prompt name, the value is the prompt text. The prompt text will be prepended before any text to encode. For example: {"query": "query: ", "passage": "passage: "}. If a model has saved prompts, you can override them by passing your own, or pass {"query": "", "document": ""} to disable them. Defaults to None.
default_prompt_name (str, optional) – The name of the prompt that should be used by default. If not set, no prompt will be applied. Defaults to None.
cache_folder (str, optional) – Path to store models. Can also be set by the SENTENCE_TRANSFORMERS_HOME environment variable. Defaults to None.
trust_remote_code (bool, optional) – Whether to allow for custom models defined on the Hub in their own modeling files. Only set to True for repositories you trust and in which you have read the code, as it will execute code present on the Hub on your local machine. Defaults to False.
revision (str, optional) – The specific model version to use. It can be a branch name, a tag name, or a commit id, for a stored model on Hugging Face. Defaults to None.
local_files_only (bool, optional) – Whether to only look at local files (i.e., do not try to download the model). Defaults to False.
token (bool or str, optional) – Hugging Face authentication token to download private models. Defaults to None.
use_auth_token (bool or str, optional) – Deprecated. Use token instead.
model_kwargs (dict[str, Any], optional) –
Keyword arguments passed to the underlying Hugging Face Transformers model via AutoModel.from_pretrained. Particularly useful options include:
- torch_dtype: Override the default torch.dtype and load the model under a specific dtype. Can be torch.float16, torch.bfloat16, torch.float32, or "auto" to use the dtype from the model’s config.json.
- attn_implementation: The attention implementation to use. For example "eager", "sdpa", or "flash_attention_2". If you pip install kernels, then "flash_attention_2" should work without having to install flash_attn. It is frequently the fastest option. Defaults to "sdpa" when available (torch>=2.1.1).
- device_map: Device map for model parallelism, e.g. "auto".
- provider: For backend="onnx", the ONNX execution provider (e.g. "CUDAExecutionProvider").
- file_name: For backend="onnx" or "openvino", the filename to load (e.g. for optimized or quantized models).
- export: For backend="onnx" or "openvino", whether to export the model to the backend format. Also set automatically if the exported file doesn’t exist.
See the PreTrainedModel.from_pretrained documentation for more details. Defaults to None.
processor_kwargs (dict[str, Any], optional) – Keyword arguments passed to the Hugging Face Transformers processor/tokenizer via AutoProcessor.from_pretrained. See the AutoTokenizer.from_pretrained documentation for more details. Defaults to None.
config_kwargs (dict[str, Any], optional) – Keyword arguments passed to the Hugging Face Transformers config via AutoConfig.from_pretrained. See the AutoConfig.from_pretrained documentation for more details. Defaults to None.
model_card_data (SentenceTransformerModelCardData, optional) – A model card data object that contains information about the model. Used to generate a model card when saving the model. If not set, a default model card data object is created. Defaults to None.
backend (str, optional) – The backend to use for inference. Can be "torch" (default), "onnx", or "openvino". Defaults to "torch".
similarity_fn_name (str or SimilarityFunction, optional) – The name of the similarity function to use. Valid options are "cosine", "dot", "euclidean", and "manhattan". If not set, it is automatically set to "cosine" when similarity or similarity_pairwise are first accessed. Defaults to None.
truncate_dim (int, optional) – The dimension to truncate sentence embeddings to. None means no truncation. Defaults to None.

Example

from sentence_transformers import SentenceTransformer

# Load a pre-trained SentenceTransformer model
model = SentenceTransformer('sentence-transformers/all-mpnet-base-v2')

# Encode some texts
sentences = [
    "The weather is lovely today.",
    "It's so sunny outside!",
    "He drove to the stadium.",
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# (3, 768)

# Get the similarity scores between all sentences
similarities = model.similarity(embeddings, embeddings)
print(similarities)
# tensor([[1.0000, 0.6817, 0.0492],
#         [0.6817, 1.0000, 0.0421],
#         [0.0492, 0.0421, 1.0000]])

Initialize a BaseModel instance.

Parameters:

model_name_or_path (str, optional) – If a filepath on disk, loads the model from that path. Otherwise, tries to download a pre-trained model. If that fails, tries to construct a model from the Hugging Face Hub with that name. Defaults to None.
modules (list[nn.Module], optional) – A list of torch modules that are called sequentially. Can be used to create custom models from scratch. Defaults to None.
device (str, optional) – Device (like "cuda", "cpu", "mps", "npu") that should be used for computation. If None, checks if a GPU can be used. Defaults to None.
prompts (dict[str, str], optional) – A dictionary with prompts for the model. The key is the prompt name, the value is the prompt text. The prompt text will be prepended before any text during inference. For example: {"query": "query: ", "passage": "passage: "}. If a model has saved prompts, you can override them by passing your own, or pass {"query": "", "document": ""} to disable them. Defaults to None.
default_prompt_name (str, optional) – The name of the prompt that should be used by default. If not set, no prompt will be applied. Defaults to None.
cache_folder (str, optional) – Path to store models. Can also be set by the SENTENCE_TRANSFORMERS_HOME environment variable. Defaults to None.
trust_remote_code (bool, optional) – Whether to allow for custom models defined on the Hub in their own modeling files. Only set to True for repositories you trust and in which you have read the code, as it will execute code present on the Hub on your local machine. Defaults to False.
revision (str, optional) – The specific model version to use. It can be a branch name, a tag name, or a commit id, for a stored model on Hugging Face. Defaults to None.
local_files_only (bool, optional) – Whether to only look at local files (i.e., do not try to download the model). Defaults to False.
token (bool or str, optional) – Hugging Face authentication token to download private models. Defaults to None.
model_kwargs (dict[str, Any], optional) –
Keyword arguments passed to the underlying Hugging Face Transformers model via AutoModel.from_pretrained. Particularly useful options include:
- torch_dtype: Override the default torch.dtype and load the model under a specific dtype. Can be torch.float16, torch.bfloat16, torch.float32, or "auto" to use the dtype from the model’s config.json.
- attn_implementation: The attention implementation to use. For example "eager", "sdpa", or "flash_attention_2". If you pip install kernels, then "flash_attention_2" should work without having to install flash_attn. It is frequently the fastest option. Defaults to "sdpa" when available (torch>=2.1.1).
- device_map: Device map for model parallelism, e.g. "auto".
- provider: For backend="onnx", the ONNX execution provider (e.g. "CUDAExecutionProvider").
- file_name: For backend="onnx" or "openvino", the filename to load (e.g. for optimized or quantized models).
- export: For backend="onnx" or "openvino", whether to export the model to the backend format. Also set automatically if the exported file doesn’t exist.
See the PreTrainedModel.from_pretrained documentation for more details. Defaults to None.
processor_kwargs (dict[str, Any], optional) –
Keyword arguments passed to the Hugging Face Transformers processor/tokenizer via AutoProcessor.from_pretrained. See the AutoTokenizer.from_pretrained documentation for more details. Defaults to None.
config_kwargs (dict[str, Any], optional) –
Keyword arguments passed to the Hugging Face Transformers config via AutoConfig.from_pretrained. See the AutoConfig.from_pretrained documentation for more details. Defaults to None.
model_card_data (CardData, optional) – A model card data object that contains information about the model. Used to generate a model card when saving the model. If not set, a default model card data object is created. Defaults to None.
backend (str, optional) – The backend to use for inference. Can be "torch" (default), "onnx", or "openvino". Defaults to "torch".

active_adapters() → list[str][source]

If you are not familiar with adapters and PEFT methods, we invite you to read more about them on the PEFT official documentation: https://huggingface.co/docs/peft

Gets the current active adapters of the model. In case of multi-adapter inference (combining multiple adapters for inference) returns the list of all active adapters so that users can deal with them accordingly.

For previous PEFT versions (that does not support multi-adapter inference), module.active_adapter will return a single string.

add_adapter(*args, **kwargs) → None[source]

Adds a fresh new adapter to the current model for training purposes. If no adapter name is passed, a default name is assigned to the adapter to follow the convention of PEFT library (in PEFT we use “default” as the default adapter name).

Requires peft as a backend to load the adapter weights and the underlying model to be compatible with PEFT.

Parameters:

*args – Positional arguments to pass to the underlying AutoModel add_adapter function. More information can be found in the transformers documentation https://huggingface.co/docs/transformers/main/en/main_classes/peft#transformers.integrations.PeftAdapterMixin.add_adapter
**kwargs – Keyword arguments to pass to the underlying AutoModel add_adapter function. More information can be found in the transformers documentation https://huggingface.co/docs/transformers/main/en/main_classes/peft#transformers.integrations.PeftAdapterMixin.add_adapter

bfloat16() → T

Casts all floating point parameters and buffers to bfloat16 datatype.

Note

This method modifies the module in-place.

Returns:: self
Return type:: Module

compile(*args, **kwargs)

Compile this Module’s forward using torch.compile().

This Module’s __call__ method is compiled and all arguments are passed as-is to torch.compile().

See torch.compile() for details on the arguments for this function.

cpu() → T

Moves all model parameters and buffers to the CPU.

Note

This method modifies the module in-place.

Returns:: self
Return type:: Module

cuda(device: int | device | None = None) → T

Moves all model parameters and buffers to the GPU.

This also makes associated parameters and buffers different objects. So it should be called before constructing optimizer if the module will live on GPU while being optimized.

Note

This method modifies the module in-place.

Parameters:: device (int, optional) – if specified, all parameters will be copied to that device
Returns:: self
Return type:: Module

delete_adapter(*args, **kwargs) → None[source]

If you are not familiar with adapters and PEFT methods, we invite you to read more about them on the PEFT official documentation: https://huggingface.co/docs/peft

Delete an adapter’s LoRA layers from the underlying model.

Parameters:

*args – Positional arguments to pass to the underlying AutoModel delete_adapter function. More information can be found in the transformers documentation https://huggingface.co/docs/transformers/main/en/main_classes/peft#transformers.integrations.PeftAdapterMixin.delete_adapter
**kwargs – Keyword arguments to pass to the underlying AutoModel delete_adapter function. More information can be found in the transformers documentation https://huggingface.co/docs/transformers/main/en/main_classes/peft#transformers.integrations.PeftAdapterMixin.delete_adapter

property device: device: Get torch.device from module, assuming that the whole module has one device. In case there are no PyTorch parameters, fall back to CPU.

disable_adapters() → None[source]: Disable all adapters that are attached to the model. This leads to inferring with the base model only.

double() → T

Casts all floating point parameters and buffers to double datatype.

Note

This method modifies the module in-place.

Returns:: self
Return type:: Module

property dtype: dtype | None

The dtype of the module (assuming that all the module parameters have the same dtype).

Type:: torch.dtype

enable_adapters() → None[source]: Enable adapters that are attached to the model. The model will use self.active_adapter()

encode(inputs: SingleInput, prompt_name: str | None = None, prompt: str | None = None, batch_size: int = 32, show_progress_bar: bool | None = None, output_value: Literal['sentence_embedding', 'token_embeddings'] = 'sentence_embedding', precision: Literal['float32', 'int8', 'uint8', 'binary', 'ubinary'] = 'float32', convert_to_numpy: Literal[False] = True, convert_to_tensor: bool = False, device: str | list[str | torch.device] | None = None, normalize_embeddings: bool = False, truncate_dim: int | None = None, pool: dict[Literal['input', 'output', 'processes'], Any] | None = None, chunk_size: int | None = None, **kwargs) → Tensor[source]

encode(inputs: list[SingleInput] | SingleInput, prompt_name: str | None = None, prompt: str | None = None, batch_size: int = 32, show_progress_bar: bool | None = None, output_value: Literal['sentence_embedding'] = 'sentence_embedding', precision: Literal['float32', 'int8', 'uint8', 'binary', 'ubinary'] = 'float32', convert_to_numpy: Literal[True] = True, convert_to_tensor: Literal[False] = False, device: str | list[str | torch.device] | None = None, normalize_embeddings: bool = False, truncate_dim: int | None = None, pool: dict[Literal['input', 'output', 'processes'], Any] | None = None, chunk_size: int | None = None, **kwargs) → np.ndarray

encode(inputs: list[SingleInput] | SingleInput, prompt_name: str | None = None, prompt: str | None = None, batch_size: int = 32, show_progress_bar: bool | None = None, output_value: Literal['sentence_embedding'] = 'sentence_embedding', precision: Literal['float32', 'int8', 'uint8', 'binary', 'ubinary'] = 'float32', convert_to_numpy: bool = True, convert_to_tensor: Literal[True] = False, device: str | list[str | torch.device] | None = None, normalize_embeddings: bool = False, truncate_dim: int | None = None, pool: dict[Literal['input', 'output', 'processes'], Any] | None = None, chunk_size: int | None = None, **kwargs) → Tensor

encode(inputs: list[SingleInput], prompt_name: str | None = None, prompt: str | None = None, batch_size: int = 32, show_progress_bar: bool | None = None, output_value: Literal['sentence_embedding', 'token_embeddings'] = 'sentence_embedding', precision: Literal['float32', 'int8', 'uint8', 'binary', 'ubinary'] = 'float32', convert_to_numpy: bool = True, convert_to_tensor: bool = False, device: str | list[str | torch.device] | None = None, normalize_embeddings: bool = False, truncate_dim: int | None = None, pool: dict[Literal['input', 'output', 'processes'], Any] | None = None, chunk_size: int | None = None, **kwargs) → list[Tensor]

encode(inputs: list[SingleInput], prompt_name: str | None = None, prompt: str | None = None, batch_size: int = 32, show_progress_bar: bool | None = None, output_value: None = 'sentence_embedding', precision: Literal['float32', 'int8', 'uint8', 'binary', 'ubinary'] = 'float32', convert_to_numpy: bool = True, convert_to_tensor: bool = False, device: str | list[str | torch.device] | None = None, normalize_embeddings: bool = False, truncate_dim: int | None = None, pool: dict[Literal['input', 'output', 'processes'], Any] | None = None, chunk_size: int | None = None, **kwargs) → list[dict[str, Tensor]]

encode(inputs: SingleInput, prompt_name: str | None = None, prompt: str | None = None, batch_size: int = 32, show_progress_bar: bool | None = None, output_value: None = 'sentence_embedding', precision: Literal['float32', 'int8', 'uint8', 'binary', 'ubinary'] = 'float32', convert_to_numpy: bool = True, convert_to_tensor: bool = False, device: str | list[str | torch.device] | None = None, normalize_embeddings: bool = False, truncate_dim: int | None = None, pool: dict[Literal['input', 'output', 'processes'], Any] | None = None, chunk_size: int | None = None, **kwargs) → dict[str, Tensor]

encode(inputs: SingleInput, prompt_name: str | None = None, prompt: str | None = None, batch_size: int = 32, show_progress_bar: bool | None = None, output_value: Literal['token_embeddings'] = 'sentence_embedding', precision: Literal['float32', 'int8', 'uint8', 'binary', 'ubinary'] = 'float32', convert_to_numpy: bool = True, convert_to_tensor: bool = False, device: str | list[str | torch.device] | None = None, normalize_embeddings: bool = False, truncate_dim: int | None = None, pool: dict[Literal['input', 'output', 'processes'], Any] | None = None, chunk_size: int | None = None, **kwargs) → Tensor

Computes embeddings for the given inputs.

Tip

If you are unsure whether you should use encode(), encode_query(), or encode_document(), your best bet is to use encode_query() and encode_document() for Information Retrieval tasks with clear query and document/passage distinction, and use encode() for all other tasks.

Note that encode() is the most general method and can be used for any task, including Information Retrieval, and that if the model was not trained with predefined prompts and/or task types, then all three methods will return identical embeddings.

Tip

Adjusting batch_size can significantly improve processing speed. The optimal value depends on your hardware, model size, precision, and input length. Benchmark a few batch sizes on a small subset of your data to find the best value.

Parameters:

inputs – The inputs to embed. Can be a string, a list of strings, or multimodal inputs (dicts, images, arrays).
prompt_name (str, optional) – The name of the prompt to use for encoding. Must be a key in the prompts dictionary, which is either set in the constructor or loaded from the model configuration. For example if prompt_name is “query” and the prompts is {“query”: “query: “, …}, then the sentence “What is the capital of France?” will be encoded as “query: What is the capital of France?” because the sentence is appended to the prompt. If prompt is also set, this argument is ignored. Defaults to None.
prompt (str, optional) – The prompt to use for encoding. For example, if the prompt is “query: “, then the sentence “What is the capital of France?” will be encoded as “query: What is the capital of France?” because the sentence is appended to the prompt. If prompt is set, prompt_name is ignored. Defaults to None.
batch_size (int, optional) – The batch size used for the computation. Defaults to 32.
show_progress_bar (bool, optional) – Whether to output a progress bar when encoding. Defaults to None, in which case the progress bar will be shown if the logger’s effective level is INFO or DEBUG.
output_value (Optional[Literal["sentence_embedding", "token_embeddings"]], optional) – The type of embeddings to return.
precision (Literal["float32", "int8", "uint8", "binary", "ubinary"], optional) – The precision to use for the embeddings.
convert_to_numpy (bool, optional) – Whether the output should be a list of numpy vectors.
convert_to_tensor (bool, optional) – Whether the output should be one large tensor.
device (str, torch.device, list, or None, optional) –
Device(s) to use for computation. Can be:
- A single device string (e.g., “cuda:0”, “cpu”) for single-process encoding
- A list of device strings (e.g., [“cuda:0”, “cuda:1”], [“cpu”, “cpu”, “cpu”, “cpu”]) to distribute encoding across multiple processes
- None to auto-detect available device for single-process encoding
If a list is provided, multi-process encoding will be used. Defaults to None.
normalize_embeddings (bool, optional) – Whether to normalize returned vectors to have length 1.
truncate_dim (int, optional) – The dimension to truncate sentence embeddings to.
pool (Dict[Literal["input", "output", "processes"], Any], optional) – A pool created by start_multi_process_pool().
chunk_size (int, optional) – Size of chunks for multi-process encoding.
**kwargs – Additional keyword arguments to pass to the model’s preprocess and forward methods.

Returns:

By default, a 2d numpy: array with shape [num_inputs, output_dimension] is returned. If output_value is None, a list of dicts (or a single dict for singular input) is returned.

Return type:

Union[List[Tensor], ndarray, Tensor, dict[str, Tensor], list[dict[str, Tensor]]]

Computes embeddings specifically optimized for document/passage representation.

This method is a specialized version of encode() that differs in exactly two ways:

If no prompt_name or prompt is provided, it uses the first available prompt from the following candidates: "document", "passage", "corpus" (checked in that order).
It sets the task to “document”. If the model has a Router module, it will use the “document” task type to route the input through the appropriate submodules.

Tip

Adjusting batch_size can significantly improve processing speed. The optimal value depends on your hardware, model size, precision, and input length. Benchmark a few batch sizes on a small subset of your data to find the best value.

All other parameters are identical to encode(). See encode() for the full parameter documentation.

encode_multi_process(sentences: list[str], pool: dict[Literal['input', 'output', 'processes'], Any], prompt_name: str | None = None, prompt: str | None = None, batch_size: int = 32, chunk_size: int | None = None, show_progress_bar: bool | None = None, precision: Literal['float32', 'int8', 'uint8', 'binary', 'ubinary'] = 'float32', normalize_embeddings: bool = False, truncate_dim: int | None = None) → ndarray[source]: Warning

This method is deprecated. You can now call SentenceTransformer.encode() with the same parameters instead, which will automatically handle multi-process encoding using the provided pool.

Computes embeddings specifically optimized for query representation.

This method is a specialized version of encode() that differs in exactly two ways:

If no prompt_name or prompt is provided, it uses a predefined “query” prompt, if available in the model’s prompts dictionary.
It sets the task to “query”. If the model has a Router module, it will use the “query” task type to route the input through the appropriate submodules.

Tip

Adjusting batch_size can significantly improve processing speed. The optimal value depends on your hardware, model size, precision, and input length. Benchmark a few batch sizes on a small subset of your data to find the best value.

All other parameters are identical to encode(). See encode() for the full parameter documentation.

eval() → T

Sets the module in evaluation mode.

This has any effect only on certain modules. See documentations of particular modules for details of their behaviors in training/evaluation mode, if they are affected, e.g. Dropout, BatchNorm, etc.

This is equivalent with self.train(False).

See Locally disabling gradient computation for a comparison between .eval() and several similar mechanisms that may be confused with it.

Returns:: self
Return type:: Module

evaluate(evaluator: BaseEvaluator, output_path: str | None = None) → dict[str, float] | float[source]

Evaluate the model based on an evaluator

Parameters:

evaluator (BaseEvaluator) – The evaluator used to evaluate the model.
output_path (str, optional) – The path where the evaluator can write the results. Defaults to None.

Returns:

The evaluation results.

fit(train_objectives: ~collections.abc.Iterable[tuple[~torch.utils.data.dataloader.DataLoader, ~torch.nn.modules.module.Module]], evaluator: ~sentence_transformers.base.evaluation.evaluator.BaseEvaluator | None = None, epochs: int = 1, steps_per_epoch=None, scheduler: str = 'WarmupLinear', warmup_steps: int = 10000, optimizer_class: type[~torch.optim.optimizer.Optimizer] = <class 'torch.optim.adamw.AdamW'>, optimizer_params: dict[str, object] = {'lr': 2e-05}, weight_decay: float = 0.01, evaluation_steps: int = 0, output_path: str | None = None, save_best_model: bool = True, max_grad_norm: float = 1, use_amp: bool = False, callback: ~collections.abc.Callable[[float, int, int], None] | None = None, show_progress_bar: bool = True, checkpoint_path: str | None = None, checkpoint_save_steps: int = 500, checkpoint_save_total_limit: int = 0, resume_from_checkpoint: bool = False) → None[source]

Deprecated training method from before Sentence Transformers v3.0, it is recommended to use SentenceTransformerTrainer instead. This method uses SentenceTransformerTrainer behind the scenes, but does not provide as much flexibility as the Trainer itself.

This training approach uses a list of DataLoaders and Loss functions to train the model. Each DataLoader is sampled in turn for one batch. We sample only as many batches from each DataLoader as there are in the smallest one to make sure of equal training with each dataset, i.e. round robin sampling.

This method should produce equivalent results in v3.0+ as before v3.0, but if you encounter any issues with your existing training scripts, then you may wish to use SentenceTransformer.old_fit instead. That uses the old training method from before v3.0.

Parameters:

train_objectives – Tuples of (DataLoader, LossFunction). Pass more than one for multi-task learning
evaluator – An evaluator (sentence_transformers.sentence_transformer.evaluation) evaluates the model performance during training on held- out dev data. It is used to determine the best model that is saved to disk.
epochs – Number of epochs for training
steps_per_epoch – Number of training steps per epoch. If set to None (default), one epoch is equal the DataLoader size from train_objectives.
scheduler – Learning rate scheduler. Available schedulers: constantlr, warmupconstant, warmuplinear, warmupcosine, warmupcosinewithhardrestarts
warmup_steps – Behavior depends on the scheduler. For WarmupLinear (default), the learning rate is increased from o up to the maximal learning rate. After these many training steps, the learning rate is decreased linearly back to zero.
optimizer_class – Optimizer
optimizer_params – Optimizer parameters
weight_decay – Weight decay for model parameters
evaluation_steps – If > 0, evaluate the model using evaluator after each number of training steps
output_path – Storage path for the model and evaluation files
save_best_model – If true, the best model (according to evaluator) is stored at output_path
max_grad_norm – Used for gradient normalization.
use_amp – Use Automatic Mixed Precision (AMP). Only for Pytorch >= 1.6.0
callback – Callback function that is invoked after each evaluation. It must accept the following three parameters in this order: score, epoch, steps
show_progress_bar – If True, output a tqdm progress bar
checkpoint_path – Folder to save checkpoints during training
checkpoint_save_steps – Will save a checkpoint after so many steps
checkpoint_save_total_limit – Total number of checkpoints to store
resume_from_checkpoint – If true, searches for checkpoints to continue training from.

float() → T

Casts all floating point parameters and buffers to float datatype.

Note

This method modifies the module in-place.

Returns:: self
Return type:: Module

get_adapter_state_dict(*args, **kwargs) → dict[source]

If you are not familiar with adapters and PEFT methods, we invite you to read more about them on the PEFT official documentation: https://huggingface.co/docs/peft

Gets the adapter state dict that should only contain the weights tensors of the specified adapter_name adapter. If no adapter_name is passed, the active adapter is used.

Parameters:

*args – Positional arguments to pass to the underlying AutoModel get_adapter_state_dict function. More information can be found in the transformers documentation https://huggingface.co/docs/transformers/main/en/main_classes/peft#transformers.integrations.PeftAdapterMixin.get_adapter_state_dict
**kwargs – Keyword arguments to pass to the underlying AutoModel get_adapter_state_dict function. More information can be found in the transformers documentation https://huggingface.co/docs/transformers/main/en/main_classes/peft#transformers.integrations.PeftAdapterMixin.get_adapter_state_dict

get_backend() → Literal['torch', 'onnx', 'openvino'][source]

Return the backend used for inference, which can be one of “torch”, “onnx”, or “openvino”.

Returns:: The backend used for inference.
Return type:: str

get_embedding_dimension() → int | None[source]

Returns the number of dimensions in the output of SentenceTransformer.encode().

Returns:: The number of dimensions in the output of encode. If it’s not known, it’s None.
Return type:: Optional[int]

get_max_seq_length() → int | None[source]

Deprecated since version Use: the max_seq_length property instead.

Returns the maximal sequence length that the first module of the model accepts. Longer inputs will be truncated.

Returns:: The maximal sequence length that the model accepts, or None if it is not defined.
Return type:: Optional[int]

get_model_kwargs() → list[str][source]

Get the keyword arguments specific to this model for inference methods like encode or predict.

Example

>>> from sentence_transformers import SentenceTransformer, SparseEncoder
>>> SentenceTransformer("sentence-transformers/all-MiniLM-L6-v2").get_model_kwargs()
[]
>>> SentenceTransformer("jinaai/jina-embeddings-v4", trust_remote_code=True).get_model_kwargs()
['task', 'truncate_dim']
>>> SparseEncoder("opensearch-project/opensearch-neural-sparse-encoding-doc-v3-distill").get_model_kwargs()
['task']

Returns:: A list of keyword arguments for the forward pass.
Return type:: list[str]

gradient_checkpointing_enable(gradient_checkpointing_kwargs: dict[str, Any] | None = None) → None[source]: Enable gradient checkpointing for the model.

half() → T

Casts all floating point parameters and buffers to half datatype.

Note

This method modifies the module in-place.

Returns:: self
Return type:: Module

is_singular_input(inputs: Any) → bool[source]

Check if the input represents a single example or a batch of examples.

Parameters:: inputs – The input to check.
Returns:: True if the input is a single example, False if it is a batch.
Return type:: bool

static load(input_path: str) → SentenceTransformer[source]: Deprecated: Use SentenceTransformer(input_path) instead.

load_adapter(*args, **kwargs) → None[source]

Load adapter weights from file or remote Hub folder.” If you are not familiar with adapters and PEFT methods, we invite you to read more about them on PEFT official documentation: https://huggingface.co/docs/peft

Requires peft as a backend to load the adapter weights and the underlying model to be compatible with PEFT.

Parameters:

*args – Positional arguments to pass to the underlying AutoModel load_adapter function. More information can be found in the transformers documentation https://huggingface.co/docs/transformers/main/en/main_classes/peft#transformers.integrations.PeftAdapterMixin.load_adapter
**kwargs – Keyword arguments to pass to the underlying AutoModel load_adapter function. More information can be found in the transformers documentation https://huggingface.co/docs/transformers/main/en/main_classes/peft#transformers.integrations.PeftAdapterMixin.load_adapter

property max_seq_length: int | None

Returns the maximal input sequence length for the model. Longer inputs will be truncated.

Returns:: The maximal input sequence length, or None if not defined.
Return type:: Optional[int]

property modalities: list[Literal['text', 'image', 'audio', 'video', 'message'] | tuple[Literal['text', 'image', 'audio', 'video'], ...]]: Return the list of modalities supported by this model, e.g. ["text"] or ["text", "image", "message"].

model_card_data_class[source]: alias of SentenceTransformerModelCardData

old_fit(train_objectives: ~collections.abc.Iterable[tuple[~torch.utils.data.dataloader.DataLoader, ~torch.nn.modules.module.Module]], evaluator: ~sentence_transformers.base.evaluation.evaluator.BaseEvaluator | None = None, epochs: int = 1, steps_per_epoch=None, scheduler: str = 'WarmupLinear', warmup_steps: int = 10000, optimizer_class: type[~torch.optim.optimizer.Optimizer] = <class 'torch.optim.adamw.AdamW'>, optimizer_params: dict[str, object] = {'lr': 2e-05}, weight_decay: float = 0.01, evaluation_steps: int = 0, output_path: str | None = None, save_best_model: bool = True, max_grad_norm: float = 1, use_amp: bool = False, callback: ~collections.abc.Callable[[float, int, int], None] | None = None, show_progress_bar: bool = True, checkpoint_path: str | None = None, checkpoint_save_steps: int = 500, checkpoint_save_total_limit: int = 0) → None[source]

Deprecated training method from before Sentence Transformers v3.0, it is recommended to use sentence_transformers.sentence_transformer.trainer.SentenceTransformerTrainer instead. This method should only be used if you encounter issues with your existing training scripts after upgrading to v3.0+.

This training approach uses a list of DataLoaders and Loss functions to train the model. Each DataLoader is sampled in turn for one batch. We sample only as many batches from each DataLoader as there are in the smallest one to make sure of equal training with each dataset, i.e. round robin sampling.

Parameters:

train_objectives – Tuples of (DataLoader, LossFunction). Pass more than one for multi-task learning
evaluator – An evaluator (sentence_transformers.sentence_transformer.evaluation) evaluates the model performance during training on held- out dev data. It is used to determine the best model that is saved to disk.
epochs – Number of epochs for training
steps_per_epoch – Number of training steps per epoch. If set to None (default), one epoch is equal the DataLoader size from train_objectives.
scheduler – Learning rate scheduler. Available schedulers: constantlr, warmupconstant, warmuplinear, warmupcosine, warmupcosinewithhardrestarts
warmup_steps – Behavior depends on the scheduler. For WarmupLinear (default), the learning rate is increased from o up to the maximal learning rate. After these many training steps, the learning rate is decreased linearly back to zero.
optimizer_class – Optimizer
optimizer_params – Optimizer parameters
weight_decay – Weight decay for model parameters
evaluation_steps – If > 0, evaluate the model using evaluator after each number of training steps
output_path – Storage path for the model and evaluation files
save_best_model – If true, the best model (according to evaluator) is stored at output_path
max_grad_norm – Used for gradient normalization.
use_amp – Use Automatic Mixed Precision (AMP). Only for Pytorch >= 1.6.0
callback – Callback function that is invoked after each evaluation. It must accept the following three parameters in this order: score, epoch, steps
show_progress_bar – If True, output a tqdm progress bar
checkpoint_path – Folder to save checkpoints during training
checkpoint_save_steps – Will save a checkpoint after so many steps
checkpoint_save_total_limit – Total number of checkpoints to store

Preprocesses the inputs for the model.

Parameters:

inputs (list[SingleInput | PairInput]) – A list of inputs to be preprocessed. Each input can be a string, dict, tuple, PIL Image, numpy array, torch Tensor, or other supported modality. If a single input is provided, it must be wrapped in a list.
prompt (str, optional) – A prompt string to prepend to text inputs. Defaults to None. If the model supports the message modality, the prompt will be added as a system message to the input messages instead of being prepended to text.

Returns:

A dictionary of tensors with the preprocessed inputs.

Return type:

dict[str, Tensor | Any]

property processor: Any: Property to get the processor that is used by this model

push_to_hub(repo_id: str, token: str | None = None, private: bool | None = None, safe_serialization: bool = True, commit_message: str | None = None, local_model_path: str | None = None, exist_ok: bool = False, replace_model_card: bool = False, train_datasets: list[str] | None = None, revision: str | None = None, create_pr: bool = False) → str[source]

Uploads all elements of this model to a HuggingFace Hub repository, creating it if it doesn’t exist.

Parameters:

repo_id (str) – Repository name for your model in the Hub, including the user or organization.
token (str, optional) – An authentication token (See https://huggingface.co/settings/token)
private (bool, optional) – Set to true, for hosting a private model
safe_serialization (bool, optional) – If true, save the model using safetensors. If false, save the model the traditional PyTorch way
commit_message (str, optional) – Message to commit while pushing.
local_model_path (str, optional) – Path of the model locally. If set, this file path will be uploaded. Otherwise, the current model will be uploaded
exist_ok (bool, optional) – If true, saving to an existing repository is OK. If false, saving only to a new repository is possible
replace_model_card (bool, optional) – If true, replace an existing model card in the hub with the automatically created model card. If false (default), keep the existing model card if one exists in the repository.
train_datasets (List[str], optional) – Datasets used to train the model. If set, the datasets will be added to the model card in the Hub.
revision (str, optional) – Branch to push the uploaded files to
create_pr (bool, optional) – If True, create a pull request instead of pushing directly to the main branch

Returns:

The url of the commit of your model in the repository on the Hugging Face Hub.

Return type:

str

save_pretrained(path: str, model_name: str | None = None, create_model_card: bool = True, train_datasets: list[str] | None = None, safe_serialization: bool = True) → None[source]

Saves a model and its configuration files to a directory, so that it can be loaded again.

Parameters:

path (str) – Path on disk where the model will be saved.
model_name (str, optional) – Optional model name.
create_model_card (bool, optional) – If True, create a README.md with basic information about this model.
train_datasets (List[str], optional) – Optional list with the names of the datasets used to train the model.
safe_serialization (bool, optional) – If True, save the model using safetensors. If False, save the model the traditional (but unsafe) PyTorch way.

set_adapter(*args, **kwargs) → None[source]

Sets a specific adapter by forcing the model to use that adapter and disable the other adapters.

Parameters:

*args – Positional arguments to pass to the underlying AutoModel set_adapter function. More information can be found in the transformers documentation https://huggingface.co/docs/transformers/main/en/main_classes/peft#transformers.integrations.PeftAdapterMixin.set_adapter
**kwargs – Keyword arguments to pass to the underlying AutoModel set_adapter function. More information can be found in the transformers documentation https://huggingface.co/docs/transformers/main/en/main_classes/peft#transformers.integrations.PeftAdapterMixin.set_adapter

set_pooling_include_prompt(include_prompt: bool) → None[source]

Sets the include_prompt attribute in the pooling layer in the model, if there is one.

This is useful for INSTRUCTOR models, as the prompt should be excluded from the pooling strategy for these models.

property similarity: Callable[[Tensor | ndarray[Any, dtype[float32]], Tensor | ndarray[Any, dtype[float32]]], Tensor]: Return a function that computes the similarity between two collections of embeddings. The output will be a matrix with the similarity scores between all embeddings from the first parameter and all embeddings from the second parameter.

property similarity_fn_name: Literal['cosine', 'dot', 'euclidean', 'manhattan']

Return the name of the similarity function.

If not previously set, accessing this property defaults it to "cosine".

property similarity_pairwise: Callable[[Tensor | ndarray[Any, dtype[float32]], Tensor | ndarray[Any, dtype[float32]]], Tensor]: Return a function that computes the pairwise similarity between two collections of embeddings.

smart_batching_collate(batch: list[InputExample]) → tuple[list[dict[str, Tensor]], Tensor][source]

Transforms a batch from a SmartBatchingDataset to a batch of tensors for the model Here, batch is a list of InputExample instances: [InputExample(…), …]

Parameters:: batch – a batch from a SmartBatchingDataset
Returns:: a batch of tensors for the model

start_multi_process_pool(target_devices: list[str] | None = None) → dict[Literal['input', 'output', 'processes'], Any][source]

Starts a multi-process pool to infer with several independent processes.

This method is recommended if you want to predict on multiple GPUs or CPUs. It is advised to start only one process per GPU. This method works together with predict and stop_multi_process_pool.

Parameters:: target_devices (List[str], optional) – PyTorch target devices, e.g. [“cuda:0”, “cuda:1”, …], [“npu:0”, “npu:1”, …], or [“cpu”, “cpu”, “cpu”, “cpu”]. If target_devices is None and CUDA/NPU is available, then all available CUDA/NPU devices will be used. If target_devices is None and CUDA/NPU is not available, then 4 CPU devices will be used.
Returns:: A dictionary with the target processes, an input queue, and an output queue.
Return type:: Dict[str, Any]

static stop_multi_process_pool(pool: dict[Literal['input', 'output', 'processes'], Any]) → None[source]

Stops all processes started with start_multi_process_pool.

Parameters:: pool (Dict[str, object]) – A dictionary containing the input queue, output queue, and process list.
Returns:: None

supports(modality: Literal['text', 'image', 'audio', 'video', 'message'] | tuple[Literal['text', 'image', 'audio', 'video'], ...]) → bool[source]

Check if the model supports the given modality.

A modality is supported if:

It is directly listed in modalities (including tuple modalities that are explicitly listed), or
It is a tuple of modalities (e.g. ("image", "text")) where each part is individually supported and the model also supports "message" format, which is used to combine multiple modalities into a single input.

Parameters:: modality – A single modality string (e.g. "text", "image") or a tuple of modality strings (e.g. ("image", "text")).
Returns:: Whether the model supports the given modality.
Return type:: bool

Example:

>>> from sentence_transformers import SentenceTransformer
>>> model = SentenceTransformer("sentence-transformers/all-MiniLM-L6-v2")
>>> model.supports("text")
True
>>> model.supports("image")
False

to(*args, **kwargs)

Moves and/or casts the parameters and buffers.

This can be called as

to(device=None, dtype=None, non_blocking=False)

to(dtype, non_blocking=False)

to(tensor, non_blocking=False)

to(memory_format=torch.channels_last)

Its signature is similar to torch.Tensor.to(), but only accepts floating point or complex dtypes. In addition, this method will only cast the floating point or complex parameters and buffers to dtype (if given). The integral parameters and buffers will be moved device, if that is given, but with dtypes unchanged. When non_blocking is set, it tries to convert/move asynchronously with respect to the host if possible, e.g., moving CPU Tensors with pinned memory to CUDA devices.

See below for examples.

Note

This method modifies the module in-place.

Parameters:

device (torch.device) – the desired device of the parameters and buffers in this module
dtype (torch.dtype) – the desired floating point or complex dtype of the parameters and buffers in this module
tensor (torch.Tensor) – Tensor whose dtype and device are the desired dtype and device for all parameters and buffers in this module
memory_format (torch.memory_format) – the desired memory format for 4D parameters and buffers in this module (keyword only argument)

Returns:

self

Return type:

Module

Examples:

>>> # xdoctest: +IGNORE_WANT("non-deterministic")
>>> linear = nn.Linear(2, 2)
>>> linear.weight
Parameter containing:
tensor([[ 0.1913, -0.3420],
        [-0.5113, -0.2325]])
>>> linear.to(torch.double)
Linear(in_features=2, out_features=2, bias=True)
>>> linear.weight
Parameter containing:
tensor([[ 0.1913, -0.3420],
        [-0.5113, -0.2325]], dtype=torch.float64)
>>> # xdoctest: +REQUIRES(env:TORCH_DOCTEST_CUDA1)
>>> gpu1 = torch.device("cuda:1")
>>> linear.to(gpu1, dtype=torch.half, non_blocking=True)
Linear(in_features=2, out_features=2, bias=True)
>>> linear.weight
Parameter containing:
tensor([[ 0.1914, -0.3420],
        [-0.5112, -0.2324]], dtype=torch.float16, device='cuda:1')
>>> cpu = torch.device("cpu")
>>> linear.to(cpu)
Linear(in_features=2, out_features=2, bias=True)
>>> linear.weight
Parameter containing:
tensor([[ 0.1914, -0.3420],
        [-0.5112, -0.2324]], dtype=torch.float16)

>>> linear = nn.Linear(2, 2, bias=None).to(torch.cdouble)
>>> linear.weight
Parameter containing:
tensor([[ 0.3741+0.j,  0.2382+0.j],
        [ 0.5593+0.j, -0.4443+0.j]], dtype=torch.complex128)
>>> linear(torch.ones(3, 2, dtype=torch.cdouble))
tensor([[0.6122+0.j, 0.1150+0.j],
        [0.6122+0.j, 0.1150+0.j],
        [0.6122+0.j, 0.1150+0.j]], dtype=torch.complex128)

tokenize(texts: list[str] | list[dict] | list[tuple[str, str]], **kwargs) → dict[str, Tensor][source]: Deprecated since version `tokenize`: is deprecated. Use preprocess instead.

property tokenizer: Any: Property to get the tokenizer that is used by this model

train(mode: bool = True) → T

Sets the module in training mode.

This has any effect only on certain modules. See documentations of particular modules for details of their behaviors in training/evaluation mode, if they are affected, e.g. Dropout, BatchNorm, etc.

Parameters:: mode (bool) – whether to set training mode (True) or evaluation mode (False). Default: True.
Returns:: self
Return type:: Module

property transformers_model: PreTrainedModel | None

Property to get the underlying transformers PreTrainedModel instance, if it exists. Note that it’s possible for a model to have multiple underlying transformers models, but this property will return the first one it finds in the module hierarchy.

Note

This property can also return e.g. ORTModelForFeatureExtraction or OVModelForFeatureExtraction instances from the optimum-intel and optimum-onnx libraries, if the model is loaded using backend="onnx" or backend="openvino".

Returns:: The underlying transformers model or None if not found.
Return type:: PreTrainedModel or None

truncate_embeddings(truncate_dim: int | None) → Iterator[None][source]

In this context, SentenceTransformer.encode() outputs embeddings truncated at dimension truncate_dim.

This may be useful when you are using the same model for different applications where different dimensions are needed.

Parameters:: truncate_dim (int, optional) – The dimension to truncate embeddings to. None does no truncation.

Example

from sentence_transformers import SentenceTransformer

model = SentenceTransformer("sentence-transformers/all-mpnet-base-v2")

with model.truncate_embeddings(truncate_dim=16):
    embeddings_truncated = model.encode(["hello there", "hiya"])
assert embeddings_truncated.shape[-1] == 16

SentenceTransformerModelCardData

class sentence_transformers.sentence_transformer.model_card.SentenceTransformerModelCardData(language: str | list[str] | None = <factory>, license: str | None = None, model_name: str | None = None, model_id: str | None = None, train_datasets: list[dict[str, str]] = <factory>, eval_datasets: list[dict[str, str]] = <factory>, task_name: str | None = 'retrieval', tags: list[str] = <factory>, local_files_only: bool = False, generate_widget_examples: bool = True)[source]

A dataclass storing data used in the model card.

Parameters:

language (Optional[Union[str, List[str]]]) – The model language, either a string or a list, e.g. “en” or [“en”, “de”, “nl”]
license (Optional[str]) – The license of the model, e.g. “apache-2.0”, “mit”, or “cc-by-nc-sa-4.0”
model_name (Optional[str]) – The pretty name of the model, e.g. “SentenceTransformer based on microsoft/mpnet-base”.
model_id (Optional[str]) – The model ID when pushing the model to the Hub, e.g. “tomaarsen/sbert-mpnet-base-allnli”.
train_datasets (List[Dict[str, str]]) – A list of the names and/or Hugging Face dataset IDs of the training datasets. e.g. [{“name”: “SNLI”, “id”: “stanfordnlp/snli”}, {“name”: “MultiNLI”, “id”: “nyu-mll/multi_nli”}, {“name”: “STSB”}]
eval_datasets (List[Dict[str, str]]) – A list of the names and/or Hugging Face dataset IDs of the evaluation datasets. e.g. [{“name”: “SNLI”, “id”: “stanfordnlp/snli”}, {“id”: “mteb/stsbenchmark-sts”}]
task_name (str) – The human-readable task the model is trained on, e.g. “semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more”.
tags (Optional[List[str]]) – A list of tags for the model, e.g. [“sentence-transformers”, “sentence-similarity”, “feature-extraction”].
local_files_only (bool) – If True, don’t attempt to find dataset or base model information on the Hub. Defaults to False.
generate_widget_examples (bool) – If True, generate widget examples from the evaluation or training dataset, and compute their similarities. Defaults to True.

Tip

Install codecarbon to automatically track carbon emission usage and include it in your model cards.

Example:

>>> model = SentenceTransformer(
...     "microsoft/mpnet-base",
...     model_card_data=SentenceTransformerModelCardData(
...         model_id="tomaarsen/sbert-mpnet-base-allnli",
...         train_datasets=[{"name": "SNLI", "id": "stanfordnlp/snli"}, {"name": "MultiNLI", "id": "nyu-mll/multi_nli"}],
...         eval_datasets=[{"name": "SNLI", "id": "stanfordnlp/snli"}, {"name": "MultiNLI", "id": "nyu-mll/multi_nli"}],
...         license="apache-2.0",
...         language="en",
...     ),
... )