internlm-chat-7b can convert to gguf but can not run

[lizhiling12345]

internlm-chat-7b is similar to llama,difference is self_attn.k_proj.bias,self_attn.o_proj.bias,self_attn.q_proj.bias
can convert to gguf,but can not run,error occurred:
error loading model: done_getting_tensors: wrong number of tensors; expected 419, got 291
is there a way to solve it?

[github-actions]

This issue was closed because it has been inactive for 14 days since being marked as stale.