The vocab size of the tokenizer 39410 is smaller than the vocab size of the base model 39424 This is not the intended use. Please check your model and tokenizer.

[wtmshanbao]

我在合并ChatLaw13b和ziya时报错vocab_szie对应不上。我合并ziya模型时直接使用huggingface上的elinas/llama-13b-hf-transformers-4.29作为llama的基础模型，合并了modelscope上的Fengshenbang/Ziya-LLaMA-13B-v1。请问是哪个模型的版本与发布的模型不符合吗？