Hugging Face Forums

When i use GPT2LMHeadModel, why it have a keys to ignore on load missing in pytorch version,while it doesn't have in tensorflow2 version?

🤗Transformers

Orient July 28, 2022, 9:34am 1

When i use GPT2LMHeadModel, why it have a _keys_to_ignore_on_load_missing in pytorch version,while it doesn’t have in tensorflow2 version? Is that mean TFGPT2LMHeadModel and GPT2LMHeadModel is different?

Topic		Replies	Views	Activity
I am using TFGPT2LMHeadModel and GPT2LMHeadModel, when i use tensorflow version to load pytorch_model.bin,there are some weight can not be used 🤗Transformers	0	236	August 2, 2022
I am using TFGPT2LMHeadModel and GPT2LMHeadModel.When i use GPT2LMHeadModel weight to initialize TFGPT2LMHeadModel, there is some weight is not used.I'm comfirm the config file is the same one, but why is it happened? 🤗Transformers	0	242	July 28, 2022
GPT2LMHeadModel.from_pretrained('gpt2') not loading attn weights Beginners	1	1794	July 22, 2020
Why if use cache in gpt2 model from transformers , the logits are different if i do a forward pass from scratch Models	1	197	February 25, 2024
GPT-2 Forward w/ and w/o caching of past gives different results Beginners	0	346	May 31, 2022