Skip to content

Pull requests: UKGovernmentBEIS/inspect_ai

New pull request New
13 Open 774 Closed
13 Open 774 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Reviews
Filter by reviews
No reviews Review required Approved review Changes requested
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

Remove $ in command-line example
#1043 opened Dec 23, 2024 by bact Loading…
1 of 5 tasks
Fix typos in CHANGELOG.md
#1042 opened Dec 23, 2024 by bact Loading…
1 of 5 tasks
Improve error messages when docker compose containers fail to start
#1041 opened Dec 23, 2024 by andrew-aisi Loading…
1 of 5 tasks
Update tutorial.qmd
#1040 opened Dec 23, 2024 by pravsels Loading…
1 of 5 tasks
llama-cpp-python: Support for logprobs.
#1039 opened Dec 22, 2024 by domdomegg Loading…
2 of 5 tasks
Bump ruff from 0.8.3 to 0.8.4 in the python-packages group dependencies Pull requests that update a dependency file
#1021 opened Dec 19, 2024 by dependabot bot Loading…
Fix metrics returning strings
#1018 opened Dec 18, 2024 by sdtblckgov Loading…
1 of 5 tasks
Add support for OpenAI's JSON-mode (response_format)
#995 opened Dec 13, 2024 by its-emile Loading…
2 of 5 tasks
Factor EvalDescriptor out of SamplesDescriptor, improve JSDoc type annotations and more
#987 opened Dec 11, 2024 by andrei-apollo Loading…
11
Add HTML output support to web browser tool
#959 opened Dec 7, 2024 by farrelmahaztra Loading…
1 of 5 tasks
7
Allow filtering samples by compound expressions including multiple scorers
#911 opened Nov 27, 2024 by amatveiakin Loading…
1
Add test scenario for opening a new page
#680 opened Oct 10, 2024 by art-dsit Loading…
5 tasks
[DRAFT] Quac Benchmark - ASET benchmark
#333 opened Sep 5, 2024 by lauritowal • Draft
1 of 5 tasks
13
ProTip! Exclude everything labeled bug with -label:bug.