What are the default models used for the various pipeline tasks? I assume the âSummarizationPipelineâ uses Bart-large-cnn or some variant of T5, but what about the other tasks?
|ConversationalPipeline|?|
You can find all the defaults here:
SUPPORTED_TASKS = { "feature-extraction": { "impl": FeatureExtractionPipeline, "tf": TFAutoModel if is_tf_available() else None, "pt": AutoModel if is_torch_available() else None, "default": {"model": {"pt": "distilbert-base-cased", "tf": "distilbert-base-cased"}}, }, "sentiment-analysis": { "impl": TextClassificationPipeline, "tf": TFAutoModelForSequenceClassification if is_tf_available() else None, "pt": AutoModelForSequenceClassification if is_torch_available() else None, "default": { "model": { "pt": "distilbert-base-uncased-finetuned-sst-2-english", "tf": "distilbert-base-uncased-finetuned-sst-2-english", }, }, }, "ner": { "impl": TokenClassificationPipeline,
show original
2 Likes
Thanks. @BramVanroy