size mismatch for transformer.text_embed.text_embed.weight: copying a param with shape torch.Size([2546, 100]) from checkpoint, the shape in current model is torch.Size([2546, 512])

[T-When]

Checks

• This template is only for bug reports, usage problems go with 'Help Wanted'.
• I have thoroughly reviewed the project documentation but couldn't find information to solve my problem.
• I have searched for existing issues, including closed ones, and couldn't find a solution.
• I confirm that I am using English to submit this report in order to facilitate communication.

Environment Details

widow's10 , python 3.9.5 ,

Steps to Reproduce

size mismatch for transformer.text_embed.text_embed.weight: copying a param with shape torch.Size([2546, 100]) from checkpoint, the shape in current model is torch.Size([2546, 512]).
size mismatch for transformer.input_embed.proj.weight: copying a param with shape torch.Size([1024, 300]) from checkpoint, the shape in current model is torch.Size([1024, 712]).

✔️ Expected Behavior

training must be started

❌ Actual Behavior

size mismatch for transformer.text_embed.text_embed.weight: copying a param with shape torch.Size([2546, 100]) from checkpoint, the shape in current model is torch.Size([2546, 512])

[ZhikangNiu]

You need to change the text dim from 512 to 100 to load this checkpoint

[SWivid]

Hi @T-When make sure you are using checkpoint of F5 (instead of E2)