How to use the ctranslate2.specs.attention_spec function in ctranslate2
To help you get started, we’ve selected a few ctranslate2 examples, based on popular ways it is used in public projects.
Secure your code as it's written. Use Snyk Code to scan source code in minutes - no build needed - and fix issues immediately.
OpenNMT / CTranslate2 / python / ctranslate2 / specs / transformer_spec.py View on Github 
def __init__(self):
self.self_attention = attention_spec.MultiHeadAttentionSpec(self_attention=True)
self.attention = attention_spec.MultiHeadAttentionSpec()
self.ffn = FeedForwardSpec()ctranslate2
Fast inference engine for Transformer models
Package Health Score
91 / 100Popular ctranslate2 functions
- ctranslate2.converters
- ctranslate2.converters.Converter
- ctranslate2.converters.converter.Converter
- ctranslate2.converters.utils
- ctranslate2.specs.attention_spec
- ctranslate2.specs.attention_spec.MultiHeadAttentionSpec
- ctranslate2.specs.catalog
- ctranslate2.specs.common_spec
- ctranslate2.specs.common_spec.EmbeddingsSpec
- ctranslate2.specs.common_spec.LayerNormSpec
- ctranslate2.specs.common_spec.LinearSpec
- ctranslate2.specs.model_spec
- ctranslate2.specs.model_spec.LayerSpec
- ctranslate2.specs.model_spec.ModelSpec
- ctranslate2.specs.model_spec.OPTIONAL
- ctranslate2.specs.transformer_spec
- ctranslate2.specs.transformer_spec.TransformerSpec