ChbSSKJr SSKJr SSKJr SSKJr SSKJr SSK J r "SS \5r g ) ) annotations)Any)Module)SentenceTransformer)AdaptiveLayerLoss)MatryoshkaLossc^\rSrSrSSU4SjjjrSU4Sjjr\S Sj5rSrU=r $) Matryoshka2dLoss c F>[UUUUUS9n [T U] UU UUUU U S9 g)a The Matryoshka2dLoss can be seen as a loss *modifier* that combines the :class:`AdaptiveLayerLoss` and the :class:`MatryoshkaLoss`. This allows you to train an embedding model that 1) allows users to specify the number of model layers to use, and 2) allows users to specify the output dimensions to use. The former is useful for when you want users to have the option to lower the number of layers used to improve their inference speed and memory usage, and the latter is useful for when you want users to have the option to lower the output dimensions to improve the efficiency of their downstream tasks (e.g. retrieval) or to lower their storage costs. Note, this uses `n_layers_per_step=1` and `n_dims_per_step=1` as default, following the original 2DMSE implementation. Args: model: SentenceTransformer model loss: The loss function to be used, e.g. :class:`MultipleNegativesRankingLoss`, :class:`CoSENTLoss`, etc. matryoshka_dims: A list of embedding dimensions to be used for the loss function, e.g. [768, 512, 256, 128, 64]. matryoshka_weights: A list of weights to be used for the loss function, e.g. [1, 1, 1, 1, 1]. If None, then the weights will be set to 1 for all dimensions. n_layers_per_step: The number of layers to use per step. If -1, then all layers are used. If > 0, then a random sample of n_layers_per_step layers are used per step. The 2DMSE paper uses `n_layers_per_step=1`. The default value is -1. n_dims_per_step: The number of dimensions to use per step. If -1, then all dimensions are used. If > 0, then a random sample of n_dims_per_step dimensions are used per step. The default value is -1. last_layer_weight: The weight to use for the loss of the final layer. Increase this to focus more on the performance when using all layers. The default value is 1.0. prior_layers_weight: The weight to use for the loss of the prior layers. Increase this to focus more on the performance when using fewer layers. The default value is 1.0. kl_div_weight: The weight to use for the KL-divergence loss that is used to make the prior layers match that of the last layer. Increase this to focus more on the performance when using fewer layers. The default value is 1.0. kl_temperature: The temperature to use for the KL-divergence loss. If 0, then the KL-divergence loss is not used. The default value is 1.0. References: - See the 2D Matryoshka Sentence Embeddings (2DMSE) paper: https://arxiv.org/abs/2402.14776 - `Matryoshka Embeddings <../../../examples/sentence_transformer/training/matryoshka/README.html>`_ - `Adaptive Layers <../../../examples/sentence_transformer/training/adaptive_layer/README.html>`_ Requirements: 1. The base loss cannot be :class:`CachedMultipleNegativesRankingLoss`, :class:`CachedMultipleNegativesSymmetricRankingLoss`, or :class:`CachedGISTEmbedLoss`. Inputs: +---------------------------------------+--------+ | Texts | Labels | +=======================================+========+ | any | any | +---------------------------------------+--------+ Relations: - :class:`MatryoshkaLoss` is used in this loss, and it is responsible for the dimensionality reduction. - :class:`AdaptiveLayerLoss` is used in this loss, and it is responsible for the layer reduction. Example: :: from sentence_transformers import SentenceTransformer, SentenceTransformerTrainer, losses from datasets import Dataset model = SentenceTransformer("microsoft/mpnet-base") train_dataset = Dataset.from_dict({ "anchor": ["It's nice weather outside today.", "He drove to work."], "positive": ["It's so sunny.", "He took the car to the office."], }) loss = losses.MultipleNegativesRankingLoss(model) loss = losses.Matryoshka2dLoss(model, loss, [768, 512, 256, 128, 64]) trainer = SentenceTransformerTrainer( model=model, train_dataset=train_dataset, loss=loss, ) trainer.train() )matryoshka_weightsn_dims_per_step)n_layers_per_steplast_layer_weightprior_layers_weight kl_div_weightkl_temperatureN)r super__init__) selfmodellossmatryoshka_dimsrrrrrrrmatryoshka_loss __class__s e/var/www/html/shao/venv/lib/python3.13/site-packages/sentence_transformers/losses/Matryoshka2dLoss.pyrMatryoshka2dLoss.__init__sHN)   1+     // 3')  cX>0[TU]5EURR5E$)N)rget_config_dictr)rrs rr! Matryoshka2dLoss.get_config_dicts2 g%' ii'')  rcg)Nz @misc{li20242d, title={2D Matryoshka Sentence Embeddings}, author={Xianming Li and Zongxi Li and Jing Li and Haoran Xie and Qing Li}, year={2024}, eprint={2402.14776}, archivePrefix={arXiv}, primaryClass={cs.CL} } )rs rcitationMatryoshka2dLoss.citations rr$)Nrr?r'r'g333333?)rrrrrz list[int]rzlist[float | int] | Nonerintrr(rfloatrr)rr)rr)returnNone)r*zdict[str, Any])r*str) __name__ __module__ __qualname____firstlineno__rr!propertyr%__static_attributes__ __classcell__)rs@rr r s 8r8s&"50*J(Jr