Support Cross encoder models (#10400)

Signed-off-by: Max de Bayser <maxdebayser@gmail.com>
Signed-off-by: Max de Bayser <mbayser@br.ibm.com>
Signed-off-by: Flavia Beo <flavia.beo@ibm.com>
Co-authored-by: Flavia Beo <flavia.beo@ibm.com>
This commit is contained in:
Maximilien de Bayser
2024-11-24 18:56:20 -08:00
committed by GitHub
co-authored by Flavia Beo
parent 49628fe13e
commit 214efc2c3c
28 changed files with 1370 additions and 62 deletions
+18
View File
@@ -38,6 +38,9 @@ class TokensPrompt(TypedDict):
prompt_token_ids: List[int]
"""A list of token IDs to pass to the model."""
token_type_ids: NotRequired[List[int]]
"""A list of token type IDs to pass to the cross encoder model."""
multi_modal_data: NotRequired["MultiModalDataDict"]
"""
DEPRECATED: Optional multi-modal data to pass to the model,
@@ -133,6 +136,9 @@ class TokenInputs(TypedDict):
prompt_token_ids: List[int]
"""The token IDs of the prompt."""
token_type_ids: NotRequired[List[int]]
"""The token type IDs of the prompt."""
prompt: NotRequired[str]
"""
The original prompt text corresponding to the token IDs, if available.
@@ -160,6 +166,7 @@ class TokenInputs(TypedDict):
def token_inputs(
prompt_token_ids: List[int],
token_type_ids: Optional[List[int]] = None,
prompt: Optional[str] = None,
multi_modal_data: Optional["MultiModalDataDict"] = None,
multi_modal_placeholders: Optional["MultiModalPlaceholderDict"] = None,
@@ -170,6 +177,8 @@ def token_inputs(
if prompt is not None:
inputs["prompt"] = prompt
if token_type_ids is not None:
inputs["token_type_ids"] = token_type_ids
if multi_modal_data is not None:
inputs["multi_modal_data"] = multi_modal_data
if multi_modal_placeholders is not None:
@@ -234,6 +243,15 @@ class SingletonInputsAdapter:
assert_never(inputs)
@cached_property
def token_type_ids(self) -> List[int]:
inputs = self.inputs
if inputs["type"] == "token" or inputs["type"] == "multimodal":
return inputs.get("token_type_ids", [])
assert_never(inputs)
@cached_property
def prompt_embeds(self) -> Optional[torch.Tensor]:
inputs = self.inputs