upstream-archive/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-07-23 11:10:55 -05:00
Code Issues Packages Projects Releases Wiki Activity

conversion: fix non-MoE NomicBert GGUF conversion error (#25996)

Browse Source
This commit is contained in:
Shahir BIn Zulfiker
2026-07-23 09:01:35 +06:00
committed by GitHub
parent 4310aa4f87
commit d941f6e1c9
1 changed files with 2 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
conversion/bert.py
View File

@@ -369,12 +369,13 @@ class NomicBertModel(BertModel):
return super().filter_tensors(item)
def modify_tensors(self, data_torch: torch.Tensor, name: str, bid: int | None) -> Iterable[tuple[str, torch.Tensor]]:
n_experts = self.find_hparam(["num_local_experts", "num_experts"])
if "mlp.experts.mlp.w1" in name:
n_experts = self.find_hparam(["num_local_experts", "num_experts"])
data_torch = data_torch.view(n_experts, self.hparams["n_inner"], self.hparams["n_embd"])
name += ".weight"
if "mlp.experts.mlp.w2" in name:
n_experts = self.find_hparam(["num_local_experts", "num_experts"])
data_torch = data_torch.view(n_experts, self.hparams["n_inner"], self.hparams["n_embd"])
data_torch = data_torch.transpose(1, 2)
name += ".weight"