GitLab

Merge branch 'group-agg-rework' of https://github.com/EleutherAI/lm-evaluation-harness into group-agg-rework

Merge branch 'group-agg-rework' of https://github.com/EleutherAI/lm-evaluation-harness into group-agg-rework

* initial_implementation (test has to be proceeded)

* minor fix

* revised task name and implemented new task

* minor fixes

* new tasks implement

* minor fix

* added 'prompt injection' task

* delete prompt injection task (will be implemented at next PR)

* trust remote code

* Update lm_eval/tasks/inverse_scaling/README.md
Co-authored-by: Hailey Schoelkopf <65563625+haileyschoelkopf@users.noreply.github.com>

* added readme

* Update lm_eval/tasks/README.md

* Update lm_eval/tasks/inverse_scaling/_inverse_scaling_mc_yaml

* Update lm_eval/tasks/inverse_scaling/README.md
Co-authored-by: Hailey Schoelkopf <65563625+haileyschoelkopf@users.noreply.github.com>

* Update lm_eval/tasks/inverse_scaling/_inverse_scaling_mc_yaml
Co-authored-by: Hailey Schoelkopf <65563625+haileyschoelkopf@users.noreply.github.com>

* Update README.md

* precommit?

* run precommit on readme

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

* adds leaderboard tasks

* Delete lm_eval/tasks/leaderboard/leaderboard_chat_template.yaml

* add readme

* Delete lm_eval/tasks/leaderboard/mmlu_pro/mmlu_pro_chat_template.yaml

* modify readme

* fix bbh task

* fix bbh salient task

* modify the readme

* Delete lm_eval/tasks/leaderboard/ifeval/README.md

* Delete lm_eval/tasks/leaderboard/math/README.md

* add leaderboard to the tasks repertory

* add anouncment about new leaderbaord tasks

* linting

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

* installs ifeval dependency in new_task github workflow

---------
Co-authored-by: Nathan Habib <nathan.habib@huggingface.com>
Co-authored-by: Hailey Schoelkopf <65563625+haileyschoelkopf@users.noreply.github.com>

* batch commit

* :Revert "batch commit"

This reverts commit d859d1ca.

* batch commit

* checkout from main

* checkout from main

* checkout from main

* checkout from main

* checkout from main

* cleanup

* cleanup

* cleanup

* cleanup

* cleanup

* cleanup

* add chat template

* refactor token padding

* nit

* nit

* check on failing test

* check transformers version

* remove transformers pin

* add ids to test

* nit

* fixup

* fix bos bug

* nit

* fixup! fix bos bug

* increase tolerance for table test

* don't detokenize vllm logprobs

* Update lm_eval/models/utils.py
Co-authored-by: Hailey Schoelkopf <65563625+haileyschoelkopf@users.noreply.github.com>

* pre-commit run --all-files

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

Bug:

```
python -m scripts.write_out --task scrolls_quality --output_base_path ~/workspace/
Traceback (most recent call last):
  File "<frozen runpy>", line 198, in _run_module_as_main
  File "<frozen runpy>", line 88, in _run_code
  File "/lm-evaluation-harness/scripts/write_out.py", line 92, in <module>
    main()
  File "/lm-evaluation-harness/scripts/write_out.py", line 51, in main
    task_dict = tasks.get_task_dict(task_names, task_manager)
                ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/lm-evaluation-harness/lm_eval/tasks/__init__.py", line 423, in get_task_dict
    task_name_from_string_dict = task_manager.load_task_or_group(
                                 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/lm-evaluation-harness/lm_eval/tasks/__init__.py", line 271, in load_task_or_group
    collections.ChainMap(*map(self._load_individual_task_or_group, task_list))
  File "/lm-evaluation-harness/lm_eval/tasks/__init__.py", line 162, in _load_individual_task_or_group
    return load_task(task_config, task=name_or_config, group=parent_name)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/lm-evaluation-harness/lm_eval/tasks/__init__.py", line 148, in load_task
    task_object = config["class"]()
                  ^^^^^^^^^^^^^^^^^
  File "/lm-evaluation-harness/lm_eval/tasks/scrolls/task.py", line 120, in __init__
    super().__init__()
  File "/lm-evaluation-harness/lm_eval/api/task.py", line 703, in __init__
    self._config = TaskConfig(**config)
                   ^^^^^^^^^^^^^^^^^^^^
TypeError: lm_eval.api.task.TaskConfig() argument after ** must be a mapping, not NoneType
```

* make MMLU trust remote code to fix tests

* remove trust remote code

* Update interface.md

update interface to remove link to really outdated commit of evaluator.py

* switch to relative referencing?

* Update interface.md

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

* separate out optimum/neuralmagic tests to separate job

* fix vllm tests

* fix bug in --trust_remote_code

* use datasets.config instead intentionally

* fix remote code issue?