for pytorch weight file
I tried to merge the PyTorch weights and config.json files into a complete model. However, it seems that some keys are missing in the weight file. Is it because the current transformer architecture has been updated?
RuntimeError: Error(s) in loading state_dict for GPT2Model:
Missing key(s) in state_dict: "h.0.attn.masked_bias", "h.1.attn.masked_bias", "h.2.attn.masked_bias", "h.3.attn.masked_bias", "h.4.attn.masked_bias", "h.5.attn.masked_bias", "h.6.attn.masked_bias", "h.7.attn.masked_bias", "h.8.attn.masked_bias", "h.9.attn.masked_bias", "h.10.attn.masked_bias", "h.11.attn.masked_bias".
The issue has been resolved. Indeed, it was due to the transformer version. To use the PyTorch weight file, the transformer version must be 2.80 or earlier.