GitLab

* overhaul `ContextSampler`

* refactor masakhapos

* move multi_target to `exact_match`

* remove doc_to_choice from `boolq-seq2seq`

* remove doc_to_choice in generation process_results

* Remove unused `doc_to_choice` and fix superglue whitespaces

* require multiple_inputs and multiple_targets to be explicitly set in taskconfig

* fix copa; better logging in task init

* fix doc_to_target to return int rather than str (deprecated)

* fix processing regression; recursively parse lists fron template

* remove redundant jinja parsing logic

* remove promptsource

* for multiple_inputs use `doc_to_text: list[str]``

* Refactor `ContextSampler` `fewshot_context`

* fix multiple_input context

* fix `target_delimiter` with `gen_prefix`

* `doc_to_text` is list for multiple_inputs

* Refactor `count_bytes` and `count_words` methods to `@staticmethod`

* make has_*(train/test/validation) to properties

* remove `multi_target` `generate_until`

* `fix doc_to_target/multiple_targets handling add tests

* rename `multi_target` to `multiple_targets`

* evalaute list when multiple targets

* allow doc_to_target to return list

* Remove gen_prefix space and add warning (#3239)

* Remove gen_prefix space and add warning

* fix null gen_prefix bug again

* use git tests

---------
Co-authored-by: Boaz Ben-Dov <bendboaz@gmail.com>

* Add support for OVModelForSeq2SeqLM

* Add test

* improve include-path precedence handling

* test: add task for test

* add test for include path precedence handling

* Refactor `test_include_path.py`

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

* Added missing fixture in test_unitxt_tasks.py

* pacify pre-commit

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

* check for chat for warning

* add test

* remove yaml extension from some evalita configs

* move unitxt to own test script

* fix CI test

* git push --force
correctly processes both formats of model_args: string and dictionary both

* exctract to function for better test

* nit

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

* [FIX] Initial code to disable multi-proc for stderr

* add docs; align no-mp bootstrap with mp

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

* fix: bug in acc_mutual_info slicing; add `target_delimiter` to uncond choices

* add tests

* switch MMLU to cais/mmlu

* switch back to tj-actions/changed-files

* cache HF folder

* Add INCLUDE tasks

* pacify pre-commit

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

* Add a test for a custom unitxt task

* Update task.py to bring in line with breaking change in v1.17.2

* Fix lint

* Enable steering HF models
Co-authored-by: Matthew Khoriaty <matthewkhoriaty2026@u.northwestern.edu>

* increase HF download timeout

* Update readme; improve steering vector device handling

* Update latest news

* remove HF timeout increase

* fix tests

* ignore sae lens test

* fix accidental force push

---------
Co-authored-by: Matthew Khoriaty <matthewkhoriaty2026@u.northwestern.edu>

* initial components to support sglang

* init of class SGLangLM

* draft for generate_until of SGLang model

* mock loglikelihood

* initial loglikelihood_tokens

* todo: fix bug of sglang engine init

* implement generation tasks and test

* support output type loglikelihood and loglikelihood_rolling (#1)

* .

* loglikelihood_rolling

* /

* support dp_size>1

* typo

* add tests and clean code

* skip tests of sglang for now

* fix OOM error of sglang pytest

* finish test for sglang

* add sglang to readme

* fix OOM of tests and clean SGLang model

* update readme

* clean pyproject and add tests for evaluator

* add accuracy tests and it passed locally

* add notes for test

* Update README.md

update readme

* pre-commit

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

* update pre-commit

* make utility function to handle `until`

* fix text

* fix test task

* dont call lm.chat_template each time

* Add metabench (Kipnis et al. 2024)

* Update metabench tasks for full replication of original benchmarks, using publicly available datasets

* Remove unnecessary import

* Add permute versions of each task, where the answer orders are randomly shuffled.

* Add metabench group for easier evaluations

* Fix mmlu counts after removing duplicate

* Add secondary datasets

* Fix f-string error

* Fix f-string error for permute processing

* Add original hash to outputs for easy matching to original results

* Add line break at end of utils files

* Remove extra line from winogrande

* Reformat for linters

* fix multiple input test

* appease pre-commit

* Add metabench to tasks README

* fix multiple input `test_doc_to_text`

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

* switch `max_tokens` for `max_completion_tokens`. OpenAI ChatCompletions

* remove stop, temp=1 for o1

* add chat assertion

* HF_DATASETS_TRUST_REMOTE_CODE = True for task tests

* move warning

* support gptqmodel

* code opt

* add gptqmodel option

* Update huggingface.py

* Update pyproject.toml

* gptqmodel version upgraded to 1.0.6

* GPTQModel version upgraded to 1.0.8

* Update pyproject.toml

* fix ruff-format error

* add gptqmodel test

* Update gptqmodel test model

* skip cuda

* python3.8 compatible

* Update README.md

* Update README.md

---------
Co-authored-by: CL-ModelCloud <cl@modelcloud.ai>

* add newlines to task descriptions; increment versions

* fix task tests (with groups)

* Apply suggestions from code review

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

* change glianorex to test set

* nit

* fix test; doc_to_target can be str for multiple_choice

* nit

* Treat python tasks same as yaml tasks.

* Add tests.

* Re-add fixture decorators.

* Fix typing specification error for Python 3.9.