Support embedding models in V1 (#16188)

Signed-off-by: Max de Bayser <mbayser@br.ibm.com>
Signed-off-by: Max de Bayser <maxdebayser@gmail.com>
Signed-off-by: 22quinn <33176974+22quinn@users.noreply.github.com>
Co-authored-by: 22quinn <33176974+22quinn@users.noreply.github.com>
This commit is contained in:
Maximilien de Bayser
2025-06-18 21:36:33 -07:00
committed by GitHub
co-authored by 22quinn
parent 4959915089
commit 799397ee4f
56 changed files with 889 additions and 281 deletions
+2 -2
View File
@@ -446,8 +446,8 @@ class BertEmbeddingModel(nn.Module, SupportsV0Only, SupportsQuant):
softmax=False)
class BertForSequenceClassification(nn.Module, SupportsCrossEncoding,
SupportsQuant):
class BertForSequenceClassification(nn.Module, SupportsV0Only,
SupportsCrossEncoding, SupportsQuant):
"""A model that uses Bert to provide embedding functionalities.
This class encapsulates the BertModel and provides an interface for