Commit 4ed88da2e for llama.cpp

commit 4ed88da2ea2a51edc158efe0ee2a1e452d75644d
Author: Lines <linellazatin@gmail.com>
Date:   Tue Nov 10 20:00:03 2026 +0800

    convert : workaround conversion for p-e-w/gpt-oss-20b-heretic-ara-v4 (#31860)

    * fix(conversion-base): changed tokenizer init only for gpt-oss checkpoints, no content modification

    * fix(conversion-gpt_oss): normalized 4 tensor suffixes, no content modification

    * fix: whitespaces

    * revert fix(conversion-base) per #31860

    * updated conversion/gpt_oss.py alt->erro reframe

    Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@huggingface.co>

    ---------

    Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@huggingface.co>

diff --git a/conversion/gpt_oss.py b/conversion/gpt_oss.py
index 7542ec0ea..c4cae9611 100644
--- a/conversion/gpt_oss.py
+++ b/conversion/gpt_oss.py
@@ -85,6 +85,16 @@ class GptOssModel(TextModel):
     def filter_tensors(cls, item: tuple[str, Callable[[], Tensor]]) -> tuple[str, Callable[[], Tensor]] | None:
         name, gen = item

+        # Normalize erroneous GPT-OSS MXFP4 tensor naming.
+        # https://github.com/p-e-w/heretic/pull/211#issuecomment-5094370390
+        if "mlp.experts." in name:
+            for proj in ("down_proj", "gate_up_proj"):
+                name = name.replace(
+                    f"{proj}_blocks_blocks", f"{proj}_blocks"
+                ).replace(
+                    f"{proj}_blocks_scales", f"{proj}_scales"
+                )
+
         if "sinks" in name:
             name += ".weight"