google-research / google-research/tabfm
Document available context-caching parameters in the README
- Dominant language
- Python
- Stars
- 2.6k
- Forks
- 270
- Avg merge
- 1d 7h
- Merged PRs (30d)
- 1
Description
The context-caching options added in #62 (cache_context, maybe_quantize_kv_cache, and keep_cache_on_device) are available on TabFMClassifier and TabFMRegressor, but are not currently mentioned in the README.
It would be useful to document how to enable them and their defaults. A short addition alongside the existing usage examples could make these options easier to discover.
I’m happy to submit a PR for this.
Contributor guide
Research direction
Start in the README beside the existing usage examples, then review the context-caching options added in #62 for TabFMClassifier and TabFMRegressor. Document how to enable cache_context, maybe_quantize_kv_cache, and keep_cache_on_device, including their defaults; done means users can discover and configure all three options.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- documentation
- Issue type
- Documentation
- Difficulty
- 1/5
- Estimated time
- Under an hour
- Activity status
- Active
- Clarity
- Clearly specified
- Newbie friendliness
- 88/100