mirror of
https://github.com/ml-explore/mlx-examples.git
synced 2025-06-24 09:21:18 +08:00
f2619f507c
* Add support for multiturn fewshot examples and chat templates Added two new arguments to the evaluation script: `--fewshot-as-multiturn` and `--apply-chat-template` which correspond to lm_eval options of similar names and are very often used to ensure apples-to-apples comparisons of lm_evaluation results * Add HF overrides for methods needed by added options * don't add duplicate bos --------- Co-authored-by: Awni Hannun <awni@apple.com>
68 lines
1.6 KiB
YAML
68 lines
1.6 KiB
YAML
version: 2.1
|
|
|
|
orbs:
|
|
apple: ml-explore/pr-approval@0.1.0
|
|
|
|
jobs:
|
|
linux_build_and_test:
|
|
docker:
|
|
- image: cimg/python:3.9
|
|
|
|
steps:
|
|
- checkout
|
|
- run:
|
|
name: Run style checks
|
|
command: |
|
|
pip install pre-commit
|
|
pre-commit run --all
|
|
if ! git diff --quiet; then echo 'Style checks failed, please install pre-commit and run pre-commit run --all and push the change'; exit 1; fi
|
|
|
|
mlx_lm_build_and_test:
|
|
macos:
|
|
xcode: "15.2.0"
|
|
resource_class: macos.m1.large.gen1
|
|
steps:
|
|
- checkout
|
|
- run:
|
|
name: Install dependencies
|
|
command: |
|
|
brew install python@3.9
|
|
python3.9 -m venv env
|
|
source env/bin/activate
|
|
pip install --upgrade pip
|
|
pip install unittest-xml-reporting
|
|
cd llms/
|
|
pip install -e ".[test]"
|
|
- run:
|
|
name: Run Python tests
|
|
command: |
|
|
source env/bin/activate
|
|
python -m xmlrunner discover -v llms/tests -o test-results/
|
|
- store_test_results:
|
|
path: test-results
|
|
|
|
workflows:
|
|
build_and_test:
|
|
when:
|
|
matches:
|
|
pattern: "^(?!pull/)[-\\w]+$"
|
|
value: << pipeline.git.branch >>
|
|
jobs:
|
|
- mlx_lm_build_and_test
|
|
- linux_build_and_test
|
|
|
|
prb:
|
|
when:
|
|
matches:
|
|
pattern: "^pull/\\d+(/head)?$"
|
|
value: << pipeline.git.branch >>
|
|
jobs:
|
|
- hold:
|
|
type: approval
|
|
- apple/authenticate:
|
|
context: pr-approval
|
|
- mlx_lm_build_and_test:
|
|
requires: [ hold ]
|
|
- linux_build_and_test:
|
|
requires: [ hold ]
|