-
Notifications
You must be signed in to change notification settings - Fork 4
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
implement llm2vec models #191
base: main
Are you sure you want to change the base?
Conversation
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Generally looking good. Will you add the results as well?
Co-authored-by: Kenneth Enevoldsen <[email protected]>
Co-authored-by: Kenneth Enevoldsen <[email protected]>
Results have been added in this latest update. |
…son was saved with space delimeter
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Looks good - assuming tests pass this will merge in
Seems like you need to run |
Implemented new model class llm2vec to support various models based on the llm2vec approach and existing package https://github.com/McGill-NLP/llm2vec.
Added the first 2 models under the name TTC, a un-uspervised and a supervised model both trained on danish/scandinavian languages.
Dependencies can be installed with seb[llm2vec].
Known issue with attempting to install and run on CPU due to issues with flash-attn.