Herbie Bradley
Herbie Bradley
- [x] Expected Calibration Error metric - Implemented calibration versions of all major multiple-choice benchmarks: - [x] LogiQA - [ ]
This PR is for general improvements to GeoGraph necessary to run our case studies. So far, this PR contains code to improve the loading speed for all geographs and updates...
I suggest we add an issue to resolve this compatibility issue and remember to unpin it again after (or at least give a loose requirement). It comes from a problem...
Nice - I agree with your analysis, thank you for clarifying! Regarding the proposed solution: Yes I think that works! (: How intensive is the merge operation? Does the sequential...
A scraper for GitHub diffs, given a JSONL containing for each commit, the hash, commit message, and repository name as a string. This uses PyArrow via `dask` to save to...
## GitHub Diffs ## Description Dataset is on BigQuery as a table of commit hashes and messages. ## Procedure From commit hash and message, produce dict containing: - Raw files...