[Render][Speculator] Add return_loss_mask to render endpoint for training data generation (#46846)
Signed-off-by: Ranran Haoran Zhang <ranzhang@redhat.com> Co-authored-by: Benjamin Chislett <chislett.ben@gmail.com>
This commit is contained in:
co-authored by
Benjamin Chislett
parent
a2a92cbbaa
commit
09841ae705
@@ -42,6 +42,11 @@ class TokensInput(_InputOptions):
|
||||
"""Char-level (start, end) offsets per token, propagated from the
|
||||
renderer's TokensPrompt when offsets were computed."""
|
||||
|
||||
assistant_tokens_mask: NotRequired[list[int] | None]
|
||||
"""Per-token 0/1 mask marking assistant-generated tokens.
|
||||
Populated when ``return_assistant_tokens_mask=True`` is set on the
|
||||
render request and the chat template supports ``{% generation %}``."""
|
||||
|
||||
|
||||
def tokens_input(
|
||||
prompt_token_ids: list[int],
|
||||
@@ -151,6 +156,11 @@ class MultiModalInput(_InputOptions):
|
||||
`prompt_token_ids`.
|
||||
"""
|
||||
|
||||
assistant_tokens_mask: NotRequired[list[int] | None]
|
||||
"""Per-token 0/1 mask marking assistant-generated tokens.
|
||||
Populated when ``return_assistant_tokens_mask=True`` is set on the
|
||||
render request and the chat template supports ``{% generation %}``."""
|
||||
|
||||
|
||||
def mm_input(
|
||||
prompt_token_ids: list[int],
|
||||
|
||||
Reference in New Issue
Block a user