Problems arising from Inferrence

[yaosheng-zhang]

Reminder

• I have read the above rules and searched the existing issues.

System Info

我是用Codellama 和 Starcoder2 lora训练完成后，进行推理出现下面的问题，但是之前deepSeekcoder就没有问题

[rank1]: size mismatch for base_model.model.model.embed_tokens.modules_to_save.default.weight: copying a param with shape torch.Size([32064, 4096]) from checkpoint, the shape in current model is torch.Size([32016, 4096]).
[rank1]: size mismatch for base_model.model.lm_head.modules_to_save.default.weight: copying a param with shape torch.Size([32064, 4096]) from checkpoint, the shape in current model is torch.Size([32016, 4096]).

Reproduction

Put your message here.

Others

No response

[hiyouga]

set resize_vocab at inference

[yaosheng-zhang]

并未看到有

resize_vocab 选项