Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

How to use AutoModel and AutoTokenizer with OpenPrompt? #232

Open
HodaMemar opened this issue Jan 15, 2023 · 2 comments
Open

How to use AutoModel and AutoTokenizer with OpenPrompt? #232

HodaMemar opened this issue Jan 15, 2023 · 2 comments

Comments

@HodaMemar
Copy link

Dear All
Thank you for this amazing library.
Many clinical models in Huggingface like PubMedBert or ClinicalBert use different tokenizers and models that are accessible via AutoModel and AutoTokenizer. For example, I work with PubMedbert as below:

  • pubmed_bert_model = AutoModel.from_pretrained('microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract-fulltext')
    
  • pubmed_bert_tokenizer = AutoTokenizer.from_pretrained('microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract-fulltext')
    

Is there some way to use them in load_plm function?
I read the #124 issue but I don't understand it well.
Thank you!

@doussa2504
Copy link

Hi did you find a way to use them?

@HodaMemar
Copy link
Author

Hi did you find a way to use them?

Hi.
Please refer to issue #199. Of course, I asked another question that was sent in that issue.
Please inform me if you find a way

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants