[Model][2/N] Automatic conversion of CrossEncoding model (#19978)

Signed-off-by: wang.yuqi <noooop@126.com>
This commit is contained in:
wang.yuqi
2025-07-03 13:59:23 +00:00
committed by GitHub
parent 1819fbda63
commit 6f1229f91d
16 changed files with 199 additions and 92 deletions
+17 -6
View File
@@ -285,6 +285,7 @@ class PoolerHead(nn.Module):
else:
pooled_data = pooled_data.to(torch.float32)
# for matryoshka representation
if isinstance(pooling_metadata, V0PoolingMetadata):
dimensions_list = [
pooling_param.dimensions
@@ -299,10 +300,16 @@ class PoolerHead(nn.Module):
if any(d is not None for d in dimensions_list):
# change the output dimension
assert len(pooled_data) == len(dimensions_list)
pooled_data = [
vecs if d is None else vecs[..., :d]
for vecs, d in zip(pooled_data, dimensions_list)
]
if len(set(dimensions_list)) == 1 and not isinstance(
pooled_data, list):
# if all dimensions are the same
d = dimensions_list[0]
pooled_data = pooled_data[..., :d]
else:
pooled_data = [
vecs if d is None else vecs[..., :d]
for vecs, d in zip(pooled_data, dimensions_list)
]
if self.normalize:
if isinstance(pooled_data, list):
@@ -325,6 +332,10 @@ class PoolerHead(nn.Module):
else:
pooled_data = F.sigmoid(pooled_data)
# shape:
# classify (& score) -> (batch_size, num_classes)
# embed -> (batch_size, embedding_dim) or list(embedding_dim)
# (batch_size, dimensions) or list(dimensions) if using MRL
return pooled_data
@@ -419,7 +430,6 @@ class ClassifierPooler(nn.Module):
offset += prompt_len
pooled_data.append(pooled_data_i)
offset = 0
pooled_data_lst = []
for pooled_data_i in pooled_data:
@@ -436,7 +446,8 @@ class ClassifierPooler(nn.Module):
# apply classifier once on the full batch if possible
pooled_output = self.classifier(pooled_output)
scores = self.default_activation_function(pooled_output).squeeze(-1)
# shape: (batch_size, num_labels)
scores = self.default_activation_function(pooled_output)
pooled_outputs = [PoolingSequenceGroupOutput(data) for data in scores]
return PoolerOutput(outputs=pooled_outputs)