Skip to content

This is a simple, local implementation of Representation Learning. Credits in README file.

License

Notifications You must be signed in to change notification settings

blackbeelabs/deepdive-representation-engineering

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

6 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Credits: Notes

The Hidden Life of Embeddings

My notes:

To initialise environment

pyenv virtualenv 3.11.1 representationlearning
pyenv activate representationlearning
cd /path/to/root
pip install --pre torch --index-url https://download.pytorch.org/whl/nightly/cpu && pip install -r requirements.txt && pip install git+https://github.com/kz364/repeng.git && pip install -r requirements-jupyter.txt

Note that if you want to download the Google models, perform:

# huggingface-cli login

with your access key filled in.

To download models

cd /path/to/src
python download_model.py -m "google/gemma-2b-it"
python quickstart_infer.py -m "google/gemma-2b-it"

And to QA the downloaded models

cd /path/to/src
python quickstart_infer.py -m "google/gemma-2b-it"

Run the notebooks

About

This is a simple, local implementation of Representation Learning. Credits in README file.

Resources

License

Stars

Watchers

Forks