🚀 The feature, motivation and pitch
In flava multimodal encoder, why don't we pass an attention mask to mask out '[PAD]' embeddings coming from text encoder? Is this a bug or intentional?
|
multimodal_outputs = self.encode_mm( |
Alternatives
No response
Additional context
No response
🚀 The feature, motivation and pitch
In flava multimodal encoder, why don't we pass an attention mask to mask out '[PAD]' embeddings coming from text encoder? Is this a bug or intentional?
multimodal/torchmultimodal/models/flava/model.py
Line 197 in e4d288b
Alternatives
No response
Additional context
No response