explosion spaCy Discussions
Discussions
-
You must be logged in to vote Tok2vec loss is growing in TextCategorizer
lang / frFrench language data and models trainingTraining and updating models feat / textcatFeature: Text Classifier feat / cliFeature: Command-line interface feat / tok2vecFeature: Token-to-vector layer and pretraining -
You must be logged in to vote ValueError("[E203] If the tok2vec embedding layer is not updated during training, make sure to include it in 'annotating components'")
usageGeneral spaCy usage trainingTraining and updating models feat / cliFeature: Command-line interface feat / tok2vecFeature: Token-to-vector layer and pretraining -
You must be logged in to vote Tok2vec output tensor usage for search / similarity tasks
usageGeneral spaCy usage feat / tok2vecFeature: Token-to-vector layer and pretraining -
You must be logged in to vote Training pipelines (tok, lem, morph, parse) together or separately?
feat / tok2vecFeature: Token-to-vector layer and pretraining -
You must be logged in to vote How does an NER model predicts an entity with OOV tokens ?
feat / tok2vecFeature: Token-to-vector layer and pretraining -
You must be logged in to vote No proper data to initialize the Model of component 'tok2vec'
feat / tok2vecFeature: Token-to-vector layer and pretraining -
You must be logged in to vote pretraining to init_tok2vec (textcat) - ValueError: Cannot deserialize model: mismatched structure
trainingTraining and updating models feat / tok2vecFeature: Token-to-vector layer and pretraining feat / configFeature: Training config -
You must be logged in to vote Custom word2vec static impact on tok2vec settings
feat / vectorsFeature: Word vectors and similarity feat / tok2vecFeature: Token-to-vector layer and pretraining -
You must be logged in to vote Train multilingual pipeline with LLaMA embeddings
feat / tok2vecFeature: Token-to-vector layer and pretraining feat/llmFeature: LLMs (incl. spacy-llm) -
You must be logged in to vote AssertionError: [E923] It looks like there is no proper sample data to initialize the Model of component 'tok2vec'.
trainingTraining and updating models feat / tok2vecFeature: Token-to-vector layer and pretraining -
You must be logged in to vote Freezing tok2vec vs unfreezing tok2vec while updating pre-trained model
trainingTraining and updating models feat / tok2vecFeature: Token-to-vector layer and pretraining -
You must be logged in to vote Tok2vec, OOV and static vectors...again
modelsIssues related to the statistical models feat / tok2vecFeature: Token-to-vector layer and pretraining -
You must be logged in to vote Get all the tokens' vector without loop
feat / tok2vecFeature: Token-to-vector layer and pretraining -
You must be logged in to vote Pretrain with transformers
feat / tok2vecFeature: Token-to-vector layer and pretraining feat / transformerFeature: Transformer -
You must be logged in to vote Textcat with tok2vec specification but no vectors?
usageGeneral spaCy usage feat / tok2vecFeature: Token-to-vector layer and pretraining -
You must be logged in to vote NER and Textcat with shared tok2vec with only one pipeline updating vectors
feat / nerFeature: Named Entity Recognizer feat / textcatFeature: Text Classifier feat / tok2vecFeature: Token-to-vector layer and pretraining -
You must be logged in to vote What does it mean to have CNN as both model and tok2vec?
feat / textcatFeature: Text Classifier feat / tok2vecFeature: Token-to-vector layer and pretraining feat / configFeature: Training config -
You must be logged in to vote SpanCategorizer confidence scores are equal for all spans.
feat / pipelineFeature: Processing pipeline and components feat / tok2vecFeature: Token-to-vector layer and pretraining -
You must be logged in to vote ValueError when attempting to run pretraining with custom reader
feat / tok2vecFeature: Token-to-vector layer and pretraining feat / trainingFeature: Training utils, Example, Corpus and converters -
You must be logged in to vote Behaviour of is_oov for en_core_web_trf pipeline
feat / vectorsFeature: Word vectors and similarity feat / tok2vecFeature: Token-to-vector layer and pretraining -
You must be logged in to vote embed, encode, attend, predict [Source code link]
feat / tok2vecFeature: Token-to-vector layer and pretraining -
You must be logged in to vote Can´t use Extension attributes in Tok2Vec
feat / tok2vecFeature: Token-to-vector layer and pretraining -
You must be logged in to vote Best way to get contextual vector embeddings of tokens in a document
feat / tok2vecFeature: Token-to-vector layer and pretraining -
You must be logged in to vote Spacy cli pretrain function
feat / tok2vecFeature: Token-to-vector layer and pretraining -
You must be logged in to vote Spacy pretrain [Config validation error] - attempting to pretrain new vector weights
feat / tok2vecFeature: Token-to-vector layer and pretraining
