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>
This commit is contained in:
1 parent
ac931b5bcb
commit
4ed88da2ea
1 file changed
+10
@@ -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"
|
||||
|
||||
|
||||
Reference in new issue
Block a user