I am using TFGPT2LMHeadModel and GPT2LMHeadModel, when i use tensorflow version to load pytorch_model.bin,there are some weight can not be used

I am using TFGPT2LMHeadModel and GPT2LMHeadModel,when i use tensorflow version to load pytorch_model.bin,there are some weight can not be used.if tensorflow version is different from pytorch version?

information like this:
Some weights of the PyTorch model were not used when initializing the TF 2.0 model TFGPT2LMHeadModel: [‘transformer.h.3.attn.masked_bias’, ‘transformer.h.5.attn.masked_bias’, ‘transformer.h.1.attn.masked_bias’, ‘transformer.h.0.attn.masked_bias’, ‘lm_head.weight’, ‘transformer.h.2.attn.masked_bias’, ‘transformer.h.4.attn.masked_bias’]