Best way to compress Parametric UMAP encoder files (if possible)
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 8.3k
- Forks
- 871
- Avg merge
- 1d 13h
- Merged PRs (30d)
- 5
Description
Hi everyone,
I was taking a look at the doc's FAQ because I've been trying to find ways to compress parametric UMAP files for them to be previously loaded at a Flask startup. I couldn't find something regarding that specific case.
Would you have any recommendations on a best way to do it? Or more recommendations on how to make the encoder files smaller?
This is a reference for some of the files we generated, if you want to take a look: https://github.com/IBM/responsible-prompting-api/tree/main/models/umap/BAAI/bge-large-en-v1.5
Thanks in advance ☺️
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start with the Parametric UMAP FAQ and review the referenced model files in IBM's responsible-prompting-api repository. Determine whether the project can document supported ways to reduce or compress encoder files for loading at Flask startup; done means the FAQ contains concrete, verified guidance for this use case.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- flask, python
- Domain
- backend, machine-learning
- Issue type
- Documentation
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100