search

thu-ml / unidiffuser

Code and models for the paper "One Transformer Fits All Distributions in Multi-Modal Diffusion"
GNU Affero General Public License v3.0
1.37k stars 86 forks source link

can' t load tokenizer for 'gpt2', why? #21

Open mxwcqu opened 1 year ago

mxwcqu commented 1 year ago

GPT2Tokenizer.from_pretrained('gpt2'),can' t load tokenizer for 'gpt2'

baofff commented 1 year ago

You can download it manually from huggingface: https://huggingface.co/gpt2 . Then you replace 'gpt2' to the local directory where files are saved.

mxwcqu commented 1 year ago

thank you

shuishui616 commented 1 year ago

Hello! I had the same problem. But I've put the weights -autoencoder_kl.pth, caption_decoder.pth and uvit_v1.pth in the models folder. What should I do?

Wanbi1 commented 1 year ago

Hello! I had the same problem. But I've put the weights -autoencoder_kl.pth, caption_decoder.pth and uvit_v1.pth in the models folder. What should I do?

Same problem for me. Waiting for help.

Wanbi1 commented 1 year ago

You can download it manually from huggingface: https://huggingface.co/gpt2 . Then you replace 'gpt2' to the local directory where files are saved.

Knock Knock