OSError: gpt2 does not appear to have a file named config.json. Checkout 'https://huggingface.co./gpt2/None' for available files.
#98
by
Iust1n2
- opened
I'm using AutoTokenizer.from_pretrained("gpt2")
with transformers Version: 4.35.2
and tokenizers Version: 0.15.0
Try:
tokenizer = GPT2Tokenizer.from_pretrained(model_name
config = GPT2Config.from_pretrained(model_name)
model = GPT2LMHeadModel.from_pretrained(model_name, config=config)
model.to(device)
I dont believe the AutoTokenizer is supported