GitLab

* update mmlu_prox configs

* update tasks/README

* correct hyphon to underline in task/README

* update pre-commit codes

* Update generation_kwargs in default template to include additional end tokens

* Update filter_list in MMLU Pro configuration to use strict_match

* Update _default_template_yaml

* Add markdown linter to pre-commit hooks

* Reformat existing markdown (excluding lm_eval/tasks/*.md)

* Update continuation template YAML for MMLU task with new generation and filtering options

* Refactor filter_list structure in continuation template YAML for improved readability

* Add 'take_first' function to filter_list in continuation template YAML

* Update filter_list in continuation template YAML to use 'strict_match' and modify filtering functions

* Add 'do_sample' option to generation_kwargs in MMLU template YAML

* Allow writing confing to wandb

* set defaults

* Update help

* Update help

* add changelog to readme template

* add readme

* add to task list

* add min_pixels, max_pixels

* fix

suport for longcontext (and other synthetic tasks)
* add ruler
* add longbench
* pass `metadata` to TaskConfig

* add MastermindEval benchmark

* fill out checklist

* Add cocoteros_va dataset

* Fix format in cocoteros_va.yml

* Undo newline added

* Execute pre-commit to fix format errors

* Update catalan_bench.yaml version and add Changelog section into Readme.md

* add __version__

* add version consistency check to publish action

* Add support for token-based auth for watsonx models

* Fix lint

* Move dotenv import to inner scope

* Improve readability of _verify_credentials

* Add INCLUDE tasks

* pacify pre-commit

---------
Co-authored-by: Baber <baber@hey.com>

* Update openllm.yaml to use train fewshot split for arc

* Implementation of Winogender

* Minor fixes README.md

* Add winogender

* Clean winogender utils.py

* Change dataset to one containing All subsets

* Flesh out README for BBQ task

* Add missing tasks for BBQ

* Add simple cooccurrence bias task

* Fix wrong mask for ambiguated context+rename metrics

* Made generate_until evaluation (following PALM paper) default

Also moved separate config files per category to separate metrics using custom function.
Created config file for multiple_choice way of evaluating BBQ.

* Add missing version metadata

* Add missing versionmetadata for bbq multiple choice

* Fix metrics and address edge cases

* Made BBQ multiple choice the default version

* Added settings following winogrande

* Add num_fewshot to simple_cooccurrence_bias

* Fixes for bbq (multiple choice)

* Fix wrong dataset

* CrowS-Pairs: make it easier to use another dataset by removing dataset_name from the subsets.

* Use simplest prompt possible without description

* Merge

* BBQ: Fix np.NaN related bug

* BBQ: Fix wrong aggregation method for disamb accuracy

* BBQ: Make it possible to only evaluate on (dis)ambiguous subset (needed for few shot eval)

* BBQ: fix showing one target in case of few-shot evals

* BBQ: Fix few-shot example for bbq_generate

* BBQ: simplify subtasks

* BBQ: Minimize number of UNK variations to reduce inference time

* BBQ: Add extra UNK keywords for the generate task

* Add a generate_until version of simple_cooccurrence_bias

* Change system/description prompt to include few-shot examples

* Group agg rework

* Run pre-commit

* add tasks to readme table

* remove trailing space from simple_cooccurrence_bias_gen.yaml `doc_to_text`

* fix

* fix

* fix version

---------
Co-authored-by: Baber <baber@hey.com>

* Added audio-modality pipeline for qwen2-audio model

* Beauty imports

* fix apply_chat_template args

* update default audio placeholders list

* add demo task - common_voice subset

* add audiolm_qwen libs to pyproject.toml

* pre-commit beautify

---------
Co-authored-by: Alexandra Rak <rakalexandra@mail.ru>

minor bug fix, lm_eval.setup_logging -> setup_logging

* add instruct humaneval

* nit

* add to readme

* nit

* Capture gen_kwargs from CLI in squad_completion

* Update lm_eval/tasks/squad_completion/task.py
Co-authored-by: Baber Abbasi <92168766+baberabb@users.noreply.github.com>

* Update lm_eval/tasks/squad_completion/task.py
Co-authored-by: Baber Abbasi <92168766+baberabb@users.noreply.github.com>

* pre-commit

---------
Co-authored-by: Baber Abbasi <92168766+baberabb@users.noreply.github.com>
Co-authored-by: Baber <baber@hey.com>

* New healthcare benchmark: careqa

* LAUNCH_MN5_ACC <python main.py --config config/mn5.yml --models Llama-3.2-1B-Instruct --tasks careqa_open --num_fewshot 0>

* Add fixes, READMES, and remove task_list.txt

* pre-commit passed, add formatting updates; add nanmean agg_metric

* Fix import error.

* Wrapped imports in try excepts

* Wrapped imports in try excepts; also metrics to catch bert_score import error

* Try except to catch ImportErrors as well

* use np.nan

* pre-commit

---------
Co-authored-by: PabloAgustin <pablo.martin@bsc.es>
Co-authored-by: Baber <baber@hey.com>

* fix for mc2 calculation

* increment versions and changelog

---------
Co-authored-by: Baber <baber@hey.com>

* Filter new leaderboard_math_hard dataset to "Level 5" only

* align to linters
Signed-off-by: Yotam Perlitz <y.perlitz@ibm.com>

---------
Signed-off-by: Yotam Perlitz <y.perlitz@ibm.com>

* bug fix

* add warning for instruct models

* nit