24 Commits
Author SHA1 Message Date
Kiersten Stokes 7158f4f4ab Add Markdown linter (#2818)
* Add markdown linter to pre-commit hooks

* Reformat existing markdown (excluding lm_eval/tasks/*.md)
2025-03-20 06:23:27 +05:00
Leonid Sinev d4ae963510 [Fix] Replace generic exception classes with a more specific ones (#1989)
* Replace generic exception classes with a more specific ones

* rerun pre-commit to pass linter tests

* Revert "rerun pre-commit to pass linter tests"

This reverts commit 67f88ccf14.

* reduce repetitions in errors or so

* Replace generic exception class with a more specific one
2024-10-22 21:13:46 +05:00
Baber AbbasiandLintang Sutawika 3850e21acd samples is newline delimited (#1930)
* `samples` is newline delimited

* updated git and pre-commit

* appease pre-commit

* nit

* Revert back for now

* Revert for now

---------

Co-authored-by: Lintang Sutawika <[email protected]>
2024-06-13 16:54:06 +07:00
Baber Abbasi e5e35fca08 Vllm update DP+TP (#1508)
* use `@ray.remote` with distributed vLLM

* update versions

* bugfix

* unpin vllm

* fix pre-commit

* added version assertion error

* Revert "added version assertion error"

This reverts commit 8041e9b78e.

* added version assertion for DP

* expand DP note

* add warning

* nit

* pin vllm

* fix typos
2024-03-03 07:35:22 -05:00
Michael Chen 4d7d2f6457 Update README.md (#1398)
Add instructions for non-MacOS users on how to compile janitor_util.cpp so that janitor.py can use it.
2024-02-05 21:00:21 -05:00
LSinev 488759d2c9 Apply some best practices and guideline recommendations to code (#1363)
* raise Exception, not a string

Additional info https://peps.python.org/pep-0352/#exception-hierarchy-changes
https://docs.python.org/3.8/tutorial/errors.html#raising-exceptions

* Apply PEP8 recommendation to prefer isinstance

"Object type comparisons should always use isinstance() instead of comparing types directly"
https://peps.python.org/pep-0008/

* Remove dangerous default mutable values in arguments

https://pylint.readthedocs.io/en/stable/user_guide/messages/warning/dangerous-default-value.html

* Format logging messages with fstring (not with format)

Additional info
https://pylint.readthedocs.io/en/stable/user_guide/messages/warning/logging-format-interpolation.html
There are also discussions about the speed of formatting while logging or some unintended code executions
https://github.com/pylint-dev/pylint/issues/2395
https://stackoverflow.com/a/54368109
but at least one format (fstring one) will be used throughout the project

* Specify utf-8 encoding for `open` explicitly

If not specified, it may be supposed differently in different environments, OSes, and Python versions. See
https://peps.python.org/pep-0597/
https://docs.python.org/3.11/library/locale.html#locale.getencoding
https://docs.python.org/3.10/library/os.html#utf8-mode
https://pylint.readthedocs.io/en/stable/user_guide/messages/warning/unspecified-encoding.html

Helps also if some code from English language tasks is taken as inspiration for tasks in non-English languages.

* Use inline-ignoring comments to pass pre-commit instead of identity process

https://flake8.pycqa.org/en/3.0.1/user/ignoring-errors.html#in-line-ignoring-errors
https://www.flake8rules.com/rules/F841.html

flake8 comments are supported by ruff: https://docs.astral.sh/ruff/linter/#error-suppression
2024-01-28 15:44:08 -05:00
Baber Abbasi 65b8761db9 Switch Linting to ruff (#1166)
* 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
2023-12-20 09:14:46 -05:00
jon-tow f81db68e87 Fix undeclared identifier error 2022-05-10 23:52:16 -04:00
jon-tow 8c997e532c Revert tests/testdata changes and address flake8 issues 2022-05-03 01:07:46 -04:00
Fabrizio Milo d95a433304 fix codespell 2022-05-02 21:39:17 -07:00
Fabrizio Milo 121b7096ab add pre-commit 2022-05-02 18:09:18 -07:00
researcher2 f9b8115158 Update sort_13_gram_buckets.py 2022-03-14 07:06:43 +10:00
researcher2 4411e788b4 More Changes For PR
Add documentation for decontamination.

Improvements to 13-gram generation.
2022-03-14 02:54:39 +10:00
researcher2 f495bfb4f6 Refactor for PR 2022-03-03 16:44:56 +10:00
Leo Gao b246009951 pull stuff into lm_eval.decontamination 2022-02-24 20:01:51 -07:00
researcher2 98d75af053 Changes for PR
Remove arguments from main.py.

Add "decontamination" prefix to ngrams arguments.
2022-02-21 07:43:20 +10:00
Quentin Anthony bb0eafbb02 Added more eval tasks and fixed directory error tasks 2022-01-30 19:23:36 +00:00
researcher2 9b472bc91f Create contamination.py 2022-01-31 02:36:05 +10:00
researcher2 6597c3479d Implement decontamination of evals against training set 13 grams. 2021-12-27 00:02:16 +10:00
researcher2 7549befa4f Add inits 2021-05-12 17:03:29 +10:00
researcher2 d0277a3fbb Update janitor.py
Comment out cpp tests.
2021-05-12 16:55:55 +10:00
researcher2 7cb91943a6 Janitor testing and changes
Small fixes to python version of Janitor, cpp version named properly for import but code doesn't work - may or may not fix in the future.

Add unit tests for python version of Janitor.
2021-05-12 16:48:54 +10:00
researcher2 2a11129d18 Add pile 13gram processing. 2021-05-12 16:46:32 +10:00
& 4de29dcaa5 Moving over training data decontamination code 2021-02-11 20:05:45 -05:00