StepFun 3.5 MTP (#23274)

* StepFun 3.5 MTP

* Simplify to single layer

* Rollback core changes

* fix flake8 errors

* Remove scripts

* modify to convention

* Apply suggestions from code review

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* dos2unix

---------

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
This commit is contained in:
Piotr Wilkin (ilintar)
2026-06-02 17:44:35 +02:00
committed by GitHub
co-authored by Sigbjørn Skjæret
parent 0b7154066e
commit 2187e00337
5 changed files with 418 additions and 26 deletions
+3 -2
View File
@@ -251,8 +251,9 @@ def main() -> None:
if args.mtp or args.no_mtp:
from conversion.qwen import _Qwen35MtpMixin
if not issubclass(model_class, _Qwen35MtpMixin):
logger.error("--mtp / --no-mtp are only supported for Qwen3.5/3.6 text variants today")
from conversion.step3 import Step35Model
if not (issubclass(model_class, _Qwen35MtpMixin) or issubclass(model_class, Step35Model)):
logger.error("--mtp / --no-mtp are only supported for Qwen3.5/3.6 and Step3.5 text variants today")
sys.exit(1)
if args.no_mtp:
model_class.no_mtp = True