vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

clarify comment

Browse source
This commit is contained in:
Xuan Son Nguyen 2024-08-28 11:24:09 +02:00
parent f3a3033415
commit fa0c2bdc45
1 changed files with 3 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

4
convert_lora_to_gguf.py
View file

@ -364,7 +364,9 @@ if __name__ == '__main__':
def modify_tensors(self, data_torch: Tensor, name: str, bid: int | None) -> Iterable[tuple[str, Tensor]]: def modify_tensors(self, data_torch: Tensor, name: str, bid: int | None) -> Iterable[tuple[str, Tensor]]:
dest = list(super().modify_tensors(data_torch, name, bid)) dest = list(super().modify_tensors(data_torch, name, bid))
# for now, we cannot convert archs that use the same tensor for tok_embd and output # some archs may have the same tensor for lm_head and output (tie word embeddings)
# in this case, adapters targeting lm_head will fail when using llama-export-lora
# therefore, we ignore them for now
# see: https://github.com/ggerganov/llama.cpp/issues/9065 # see: https://github.com/ggerganov/llama.cpp/issues/9065
if name == "lm_head.weight" and len(dest) == 0: if name == "lm_head.weight" and len(dest) == 0:
raise ValueError("lm_head is present in adapter, but is ignored in base model") raise ValueError("lm_head is present in adapter, but is ignored in base model")