convert : remove redundant code #15708
Conversation
Signed-off-by: Jie Fu <[email protected]>
| # if data ends up empty, it means data_torch was a scalar tensor -> restore | ||
| if len(data.shape) == 0: | ||
| data = data_torch.numpy() | ||
|
|
There was a problem hiding this comment.
I think the intention here was to have the shape be non-zero for scalars, in which case
data = data.reshape(1)might be more appropriate in that otherwise redundant if condition.
There was a problem hiding this comment.
Thanks @compilade for the comments.
Is there a case that data.reshape(1) is needed when converting gguf models?
If not, there might be some risk adding data.reshape(1) here.
I would suggest removing the code at the moment which doesn't change the logic.
And we can still add data.reshape(1) in the future if it really matters.
What do you think?
Thanks.
There was a problem hiding this comment.
Is there a case that
data.reshape(1)is needed when converting gguf models?
Yes, and it's exactly when len(data.shape) == 0 (aka when the shape is an empty tuple ()).
It doesn't really happen in practice because most models don't have scalar tensors.
I would suggest removing the code at the moment which doesn't change the logic.
And we can still adddata.reshape(1)in the future if it really matters.
Agreed.
There was a problem hiding this comment.
Thanks @ggerganov and @compilade for your approval.
|
Thanks @taronaeo . |
Signed-off-by: Jie Fu <[email protected]>
Since
data = data_torch.numpy()has been called at line 303, line 307 seems to be redundant.Or am I missing something?
Thanks.