GitLab

* fix incorrect lookback protections

* bump generate_until task versions

* auto-batch requires len of iter

* handle case when batch_size="auto:N"

* fix group

* siqa: default.yml -> default.yaml

* max_gen_toks -> self.max_gen_toks

* add ids to task tests

* fix siqa

* fix gen_kwargs for openai-chat

* refactor dataloader

* cleanup + add docs

* change arg

* renamed Collator and added testing

* parametrized test for Collator

* appease pre-commit

* added edge case batch 0 (no batching)

* fix typos

---------
Co-authored-by: Hailey Schoelkopf <65563625+haileyschoelkopf@users.noreply.github.com>

* Add retry error handler

* fixup! Add retry error handler

* Move to utils.py

* Run isort on utils.py

* Catch multiple exceptions

* Update LMs with exception handler

* Fixes to anthropic retry handler

* fix callback kwarg

* Update textsynth.py

* fix python 3.8 incompatibility

* fix indenterror I introduced

* placate linter?

* Update on_exception_callback kwarg name

* fixup! Merge branch 'main' into add-retry-error-handler

* fixup! fixup! Merge branch 'main' into add-retry-error-handler

* Merge conflicts are fun

* Run pre-commit

---------
Co-authored-by: Hailey Schoelkopf <65563625+haileyschoelkopf@users.noreply.github.com>

* add ruff and isort. remove black and flake8

* remove unnecessary dependencies

* remove dependency from table

* change order

* ran ruff

* check 3.9

* exclude evaluator

* update CI workflow

* use ruff config in pyproject.toml

* test

* add isort rules to ruff

* sort imports

* import `make_table`

* try stages for no-commit-to-branch

* turn on mypy for pre-commit

* test

* test

* test

* change no-commit-to-branch to default

* nits

* fixed dependency

enables tasks of different group but same task_alis (for example, if evaluating on different versions of MMLU

This adds a bunch of simple annotations suggested by https://github.com/JelleZijlstra/autotyping.