NgDdZddlmZddlZddlmZGddZdS)z This file contains the templating for model cards prior to the v3.0 release. It still exists to be used alongside SentenceTransformer.old_fit for backwards compatibility, but will be removed in a future release. ) annotationsN)fullnamec`eZdZgdZdddddddZdZd Zd Zed Z ed Z d S)ModelCardTemplate)zsentence-transformerszfeature-extractionsentence-similarityrz"z/z9)z{PIPELINE_TAG}z{MODEL_DESCRIPTION}z{TRAINING_SECTION}z{USAGE_TRANSFORMERS_SECTION}z {EVALUATION}z{CITING}as --- library_name: sentence-transformers pipeline_tag: {PIPELINE_TAG} tags: {TAGS} {DATASETS} --- # {MODEL_NAME} This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a {NUM_DIMENSIONS} dimensional dense vector space and can be used for tasks like clustering or semantic search. {MODEL_DESCRIPTION} ## Usage (Sentence-Transformers) Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed: ``` pip install -U sentence-transformers ``` Then you can use the model like this: ```python from sentence_transformers import SentenceTransformer sentences = ["This is an example sentence", "Each sentence is converted"] model = SentenceTransformer('{MODEL_NAME}') embeddings = model.encode(sentences) print(embeddings) ``` {USAGE_TRANSFORMERS_SECTION} ## Evaluation Results {EVALUATION} For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name={MODEL_NAME}) {TRAINING_SECTION} ## Full Model Architecture ``` {FULL_MODEL_STR} ``` ## Citing & Authors {CITING} z ## Training The model was trained with the parameters: {LOSS_FUNCTIONS} Parameters of the fit()-Method: ``` {FIT_PARAMETERS} ``` a ## Usage (HuggingFace Transformers) Without [sentence-transformers](https://www.SBERT.net), you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings. ```python from transformers import AutoTokenizer, AutoModel import torch {POOLING_FUNCTION} # Sentences we want sentence embeddings for sentences = ['This is an example sentence', 'Each sentence is converted'] # Load model from HuggingFace Hub tokenizer = AutoTokenizer.from_pretrained('{MODEL_NAME}') model = AutoModel.from_pretrained('{MODEL_NAME}') # Tokenize sentences encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt') # Compute token embeddings with torch.no_grad(): model_output = model(**encoded_input) # Perform pooling. In this case, {POOLING_MODE} pooling. sentence_embeddings = {POOLING_FUNCTION_NAME}(model_output, encoded_input['attention_mask']) print("Sentence embeddings:") print(sentence_embeddings) ``` c6|dkrdS|dkrdS|dkrdSdS)Nmax) max_poolinga # Max Pooling - Take the max value over time for every dimension. def max_pooling(model_output, attention_mask): token_embeddings = model_output[0] #First element of model_output contains all token embeddings input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float() token_embeddings[input_mask_expanded == 0] = -1e9 # Set padding tokens to large negative value return torch.max(token_embeddings, 1)[0] mean) mean_poolinga #Mean Pooling - Take attention mask into account for correct averaging def mean_pooling(model_output, attention_mask): token_embeddings = model_output[0] #First element of model_output contains all token embeddings input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float() return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9) cls) cls_poolingzP def cls_pooling(model_output, attention_mask): return model_output[0][:,0] ) pooling_modes f/var/www/html/ai-engine/env/lib/python3.11/site-packages/sentence_transformers/model_card_templates.pymodel_card_get_pooling_functionz1ModelCardTemplate.model_card_get_pooling_function|sM 5   V # #  U " "# "c t|dr|}nli}t|dr|jnd|d<t|drt|j|d<t|drt|j|d<dt|dt |d|d }d t|t|drd |d nd }||gS#t$r/}tj dt|Yd}~d Sd}~wwxYw)Nget_config_dict batch_sizeunknownsampler batch_samplerz**DataLoader**: `z ` of length z with parameters: ``` z ```z**Loss**: `{}` {}zwith parameters: ``` z ```r z2Exception when creating get_train_objective_info: ) hasattrrrrrrlenformat ExceptionloggingWARNstr) dataloaderloss loader_paramsdataloader_strloss_stres rget_train_objective_infoz*ModelCardTemplate.get_train_objective_infos z#455 X * : : < < " GNz[gGhGh.wj.C.Cnw l+:y11L/7 8J/K/KM),:77X5=j>V5W5WM/2hz6J6JX[\fXgXgN .44 4!233      H#H- -    LVcRSffVV W W W22222 sDD E$D<<EN) __name__ __module__ __qualname____TAGS____DEFAULT_VARS____MODEL_CARD____TRAINING_SECTION____USAGE_TRANSFORMERS__ staticmethodrr)rrrrr sUUUH/C (*IO 5Nn B  \ D\rr)__doc__ __future__rr utilrrrrrr6sz #"""""rrrrrrrrrrr