Merge pull request #899 from EleutherAI/fix-scripts

[Refactor] Fix error when calling `lm-eval`

.github/workflows/new_tasks.yml

-# name: Tasks Modified
+name: Tasks Modified
 
-# on:
-#   push:
-#     branches:
-#       - 'big-refactor*'
-#   pull_request:
-#     branches:
-#       - 'big-refactor*'
-#   workflow_dispatch:
-# # comment/edit out the above to stop/change the triggers
-# jobs:
-#   changed_files:
-#     runs-on: ubuntu-latest  # windows-latest || macos-latest
-#     timeout-minutes: 120
-#     name: Scan for changed tasks
-#     steps:
-#       - name: checkout
-#         uses: actions/checkout@v3
-#         with:
-#           fetch-depth: 2  # OR "2" -> To retrieve the preceding commit.
+on:
+  push:
+    branches:
+      - 'big-refactor*'
+  pull_request:
+    branches:
+      - 'big-refactor*'
+  workflow_dispatch:
+# comment/edit out the above to stop/change the triggers
+jobs:
+  changed_files:
+    runs-on: ubuntu-latest  # windows-latest || macos-latest
+    timeout-minutes: 120
+    name: Scan for changed tasks
+    steps:
+      - name: checkout
+        uses: actions/checkout@v3
+        with:
+          fetch-depth: 2  # OR "2" -> To retrieve the preceding commit.
 
-#       # Uses the tj-actions/changed-files@v37 action to check for changes.
-#       # Outputs provided here: https://github.com/tj-actions/changed-files#outputs
-#       # The `files_yaml` input optionally takes a yaml string to specify filters,
-#       # and prepends the filter name to the standard output names.
-#       - name: Check task folders
-#         id: changed-tasks
-#         uses: tj-actions/changed-files@v37.1.2
-#         with:
-#           # tasks checks the tasks folder and api checks the api folder for changes
-#           files_yaml: |
-#             tasks:
-#               - lm_eval/tasks/**
-#             api:
-#               - lm_eval/api/**
-#           write_output_files: true
+      # Uses the tj-actions/changed-files@v37 action to check for changes.
+      # Outputs provided here: https://github.com/tj-actions/changed-files#outputs
+      # The `files_yaml` input optionally takes a yaml string to specify filters,
+      # and prepends the filter name to the standard output names.
+      - name: Check task folders
+        id: changed-tasks
+        uses: tj-actions/changed-files@v37.1.2
+        with:
+          # tasks checks the tasks folder and api checks the api folder for changes
+          files_yaml: |
+            tasks:
+              - lm_eval/tasks/**
+            api:
+              - lm_eval/api/**
+          write_output_files: true
 
-#     # The next step is optional; the files are written to the workspace by default (above).
-#     # so it's just for debugging
-#       - name: Run Tests
-#         if: steps.changed-tasks.outputs.tasks_any_modified == 'true' || steps.changed-tasks.outputs.api_any_modified == 'true'
-#         run: |
-#           echo .github/outputs/tasks_all_changed_and_modified_files.txt >> 'GITHUB_ENV'
-#           echo "One or more test file(s) has changed."
-#           echo "List of all the files that have changed: ${{ steps.changed-tasks.outputs.tasks_all_modified_files }}"
+    # The next step is optional; the files are written to the workspace by default (above).
+    # so it's just for debugging
+      - name: Run Tests
+        if: steps.changed-tasks.outputs.tasks_any_modified == 'true' || steps.changed-tasks.outputs.api_any_modified == 'true'
+        run: |
+          echo .github/outputs/tasks_all_changed_and_modified_files.txt >> 'GITHUB_ENV'
+          echo "One or more test file(s) has changed."
+          echo "List of all the files that have changed: ${{ steps.changed-tasks.outputs.tasks_all_modified_files }}"
 
-#       - name: Set up Python 3.9
-#         if: steps.changed-tasks.outputs.tasks_any_modified == 'true' || steps.changed-tasks.outputs.api_any_modified == 'true'
-#         uses: actions/setup-python@v4
-#         with:
-#           python-version: 3.9
-#           cache: 'pip'
-#           cache-dependency-path: setup.py
-#       - name: Install dependencies
-#         if: steps.changed-tasks.outputs.tasks_any_modified == 'true' || steps.changed-tasks.outputs.api_any_modified == 'true'
-#         run: |
-#             python -m pip install --upgrade pip
-#             pip install -e '.[testing]' --extra-index-url https://download.pytorch.org/whl/cpu
-#     #   Install optional git dependencies
-#     #       pip install bleurt@https://github.com/google-research/bleurt/archive/b610120347ef22b494b6d69b4316e303f5932516.zip#egg=bleurt
-#     #       if [ -f requirements.txt ]; then pip install -r requirements.txt; fi
-#       - name: Test with pytest
-#         # if new tasks are added, run tests on them
-#         if: steps.changed-tasks.outputs.tasks_any_modified == 'true'
-#         run: python -m pytest tests/test_tasks.py -s -vv
-#         # if api is modified, run tests on it
-#       - name: Test more tasks with pytest
-#         env:
-#           API: true
-#         if: steps.changed-tasks.outputs.api_any_modified == 'true'
-#         run: python -m pytest tests/test_tasks.py -s -vv
+      - name: Set up Python 3.9
+        if: steps.changed-tasks.outputs.tasks_any_modified == 'true' || steps.changed-tasks.outputs.api_any_modified == 'true'
+        uses: actions/setup-python@v4
+        with:
+          python-version: 3.9
+          cache: 'pip'
+          cache-dependency-path: setup.py
+      - name: Install dependencies
+        if: steps.changed-tasks.outputs.tasks_any_modified == 'true' || steps.changed-tasks.outputs.api_any_modified == 'true'
+        run: |
+            python -m pip install --upgrade pip
+            pip install -e '.[testing]' --extra-index-url https://download.pytorch.org/whl/cpu
+    #   Install optional git dependencies
+    #       pip install bleurt@https://github.com/google-research/bleurt/archive/b610120347ef22b494b6d69b4316e303f5932516.zip#egg=bleurt
+    #       if [ -f requirements.txt ]; then pip install -r requirements.txt; fi
+      - name: Test with pytest
+        # if new tasks are added, run tests on them
+        if: steps.changed-tasks.outputs.tasks_any_modified == 'true'
+        run: python -m pytest tests/test_tasks.py -s -vv
+        # if api is modified, run tests on it
+      - name: Test more tasks with pytest
+        env:
+          API: true
+        if: steps.changed-tasks.outputs.api_any_modified == 'true'
+        run: python -m pytest tests/test_tasks.py -s -vv

.github/workflows/unit_tests.yml

@@ -43,35 +43,35 @@ jobs:
 #       # mypy turned off for now
 #    - name: Lint with mypy
 #      run: mypy . --ignore-missing-imports --check-untyped-defs --explicit-package-bases --warn-unreachable
-# Job 2
-#   testcpu:
-#     name: CPU Tests
-#     runs-on: ubuntu-latest
-#     strategy:
-#       matrix:
-#         python-version: [ "3.8", "3.9", "3.10", "3.11" ]
-#     timeout-minutes: 30
-#     steps:
-#     - name: Checkout Code
-#       uses: actions/checkout@v3
-#     - name: Set up Python ${{ matrix.python-version }}
-#       uses: actions/setup-python@v4
-#       with:
-#         python-version: ${{ matrix.python-version }}
-#         cache: pip
-#         cache-dependency-path: setup.py
-#     - name: Install dependencies
-#       run: |
-#         python -m pip install --upgrade pip
-#         pip install -e '.[testing,anthropic,sentencepiece]' --extra-index-url https://download.pytorch.org/whl/cpu
-# #         Install optional git dependencies
-# #                pip install bleurt@https://github.com/google-research/bleurt/archive/b610120347ef22b494b6d69b4316e303f5932516.zip#egg=bleurt
-# #        if [ -f requirements.txt ]; then pip install -r requirements.txt; fi
-#     - name: Test with pytest
-#       run: python -m pytest --showlocals -s -vv -n=auto --ignore=tests/tests_master --ignore=tests/extra
-#     - name: Archive artifacts
-#       uses: actions/upload-artifact@v3
-#       with:
-#         name: output_results
-#         path: |
-#           test_logs/*
+Job 2
+  testcpu:
+    name: CPU Tests
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python-version: [ "3.8", "3.9", "3.10", "3.11" ]
+    timeout-minutes: 30
+    steps:
+    - name: Checkout Code
+      uses: actions/checkout@v3
+    - name: Set up Python ${{ matrix.python-version }}
+      uses: actions/setup-python@v4
+      with:
+        python-version: ${{ matrix.python-version }}
+        cache: pip
+        cache-dependency-path: setup.py
+    - name: Install dependencies
+      run: |
+        python -m pip install --upgrade pip
+        pip install -e '.[testing,anthropic,sentencepiece]' --extra-index-url https://download.pytorch.org/whl/cpu
+#         Install optional git dependencies
+#                pip install bleurt@https://github.com/google-research/bleurt/archive/b610120347ef22b494b6d69b4316e303f5932516.zip#egg=bleurt
+#        if [ -f requirements.txt ]; then pip install -r requirements.txt; fi
+    - name: Test with pytest
+      run: python -m pytest --showlocals -s -vv -n=auto --ignore=tests/tests_master --ignore=tests/extra
+    - name: Archive artifacts
+      uses: actions/upload-artifact@v3
+      with:
+        name: output_results
+        path: |
+          test_logs/*

README.md

@@ -9,8 +9,8 @@ We’d like your help to test it out! you can help by:
 2. Porting tasks supported in the previous version of the harness to the new YAML configuration format. Please check out our [task implementation guide](https://github.com/EleutherAI/lm-evaluation-harness/blob/big-refactor/docs/new_task_guide.md) for more information.
 
 If you choose to port a task not yet completed according to [our checklist](https://github.com/EleutherAI/lm-evaluation-harness/blob/big-refactor/lm_eval/tasks/README.md), then you can contribute it by opening a PR containing [Refactor] in the name with:
-- A command of the form `python main.py --model hf --model_args ..... --tasks <task name> ...` which will run the task in the `master` branch, and what the score is
-- A command of the form `python main.py --model hf --model_args ..... --tasks <task name> ...` to run the task in your PR branch to `big-refactor`, and what the resulting score is, to show that we achieve equality between the two implementations.
+- A command of the form `python -m lm_eval --model hf --model_args ..... --tasks <task name> ...` which will run the task in the `master` branch, and what the score is
+- A command of the form `python -m lm_eval --model hf --model_args ..... --tasks <task name> ...` to run the task in your PR branch to `big-refactor`, and what the resulting score is, to show that we achieve equality between the two implementations.
 
 Lastly, we'll no longer be accepting new feature requests beyond those that are already open to the master branch as we carry out this switch to the new version over the next week, though we will be accepting bugfixes to `master` branch and PRs to `big-refactor`. Feel free to reach out in the #lm-thunderdome channel of the EAI discord for more information.
 
@@ -67,7 +67,7 @@ To evaluate a model hosted on the [HuggingFace Hub](https://huggingface.co/model
 
 
 ```bash
-python main.py \
+python -m lm_eval \
     --model hf \
     --model_args pretrained=EleutherAI/gpt-j-6B \
     --tasks hellaswag \
@@ -78,7 +78,7 @@ python main.py \
 Additional arguments can be provided to the model constructor using the `--model_args` flag. Most notably, this supports the common practice of using the `revisions` feature on the Hub to store partially trained checkpoints, or to specify the datatype for running a model:
 
 ```bash
-python main.py \
+python -m lm_eval \
     --model hf \
     --model_args pretrained=EleutherAI/pythia-160m,revision=step100000,dtype="float" \
     --tasks lambada_openai,hellaswag \
@@ -91,7 +91,7 @@ Models that are loaded via either `transformers.AutoModelForCausalLM` (autoregre
 Batch size selection can be automated by setting the  ```--batch_size``` flag to ```auto```. This will perform automatic detection of the largest batch size that will fit on your device. On tasks where there is a large difference between the longest and shortest example, it can be helpful to periodically recompute the largest batch size, to gain a further speedup. To do this, append ```:N``` to above flag to automatically recompute the largest batch size ```N``` times. For example, to recompute the batch size 4 times, the command would be:
 
 ```bash
-python main.py \
+python -m lm_eval \
     --model hf \
     --model_args pretrained=EleutherAI/pythia-160m,revision=step100000,dtype="float" \
     --tasks lambada_openai,hellaswag \
@@ -99,7 +99,7 @@ python main.py \
     --batch_size auto:4
 ```
 
-Alternatively, you can use `lm-eval` instead of `python main.py` to call lm eval from anywhere.
+Alternatively, you can use `lm-eval` or `lm_eval` instead of `python -m lm_eval` to call lm eval from anywhere.
 
 ### Multi-GPU Evaluation with Hugging Face `accelerate`
 
@@ -108,7 +108,7 @@ To parallelize evaluation of HuggingFace models across multiple GPUs, we allow f
 The first is performed by launching evaluation via the `accelerate` library as follows:
 
 ```
-accelerate launch main.py \
+accelerate launch -m lm_eval \
     --model hf \
     --tasks lambada_openai,arc_easy \
     --batch_size 16 \
@@ -121,7 +121,7 @@ If your model is *is too large to be run on a single one of your GPUs* then you
 
 We also provide an second method to run these large models: use of the `parallelize` argument.
 ```
-python main.py \
+python -m lm_eval \
     --model hf \
     --model_args pretrained=EleutherAI/pythia-12b,parallelize=True
     --tasks lambada_openai,arc_easy \
@@ -136,7 +136,7 @@ To pass even more advanced keyword arguments to `accelerate`, we allow for the f
 
 Note that this method naively splits models across GPUs, resulting in only a single GPU performing work at any point in time, and so is much slower than launching with `accelerate launch`, possibly by a factor of the total # of GPUs.
 
-**Note that this option requires launching evaluation via `python main.py` rather than `accelerate launch main.py`.**
+**Note that this option requires launching evaluation via `python -m lm_eval` rather than `accelerate launch -m lm_eval`.**
 
 To use `accelerate` with the `lm-eval` command, use
 ```
@@ -167,7 +167,7 @@ Our library supports language models served via the OpenAI Completions API as fo
 
 ```bash
 export OPENAI_API_SECRET_KEY=YOUR_KEY_HERE
-python main.py \
+python -m lm_eval \
     --model openai-completions \
     --model_args engine=davinci \
     --tasks lambada_openai,hellaswag
@@ -198,7 +198,7 @@ This will write out one text file for each task.
 To verify the data integrity of the tasks you're performing in addition to running the tasks themselves, you can use the `--check_integrity` flag:
 
 ```bash
-python main.py \
+python -m lm_eval \
     --model openai \
     --model_args engine=davinci \
     --tasks lambada_openai,hellaswag \
@@ -209,7 +209,7 @@ python main.py \
 
 For models loaded with the HuggingFace  `transformers` library, any arguments provided via `--model_args` get passed to the relevant constructor directly. This means that anything you can do with `AutoModel` can be done with our library. For example, you can pass a local path via `pretrained=` or use models finetuned with [PEFT](https://github.com/huggingface/peft) by taking the call you would run to evaluate the base model and add `,peft=PATH` to the `model_args` argument:
 ```bash
-python main.py \
+python -m lm_eval \
     --model hf \
     --model_args pretrained=EleutherAI/gpt-j-6b,parallelize=True,load_in_4bit=True,peft=nomic-ai/gpt4all-j-lora \
     --tasks openbookqa,arc_easy,winogrande,hellaswag,arc_challenge,piqa,boolq \
@@ -219,7 +219,7 @@ python main.py \
 [GPTQ](https://github.com/PanQiWei/AutoGPTQ) quantized models can be loaded by specifying their file names in `,gptq=NAME` (or `,gptq=True` for default names) in the `model_args` argument:
 
 ```bash
-python main.py \
+python -m lm_eval \
     --model hf \
     --model_args pretrained=model-name-or-path,gptq=model.safetensors,gptq_use_triton=True \
     --tasks hellaswag

docs/decontamination.md

@@ -2,11 +2,11 @@
 
 ## Usage
 
-Simply add a "--decontamination_ngrams_path" when running main.py. The provided directory should contain
+Simply add a "--decontamination_ngrams_path" when running \__main\__.py. The provided directory should contain
 the ngram files and info.json produced in "Pile Ngram Generation" further down.
 
 ```bash
-python main.py \
+python -m lm_eval \
     --model gpt2 \
     --device 0 \
     --tasks sciq \

docs/interface.md

@@ -4,7 +4,7 @@ This document details the interface exposed by `lm-eval` and provides details on
 
 ## Command-line Interface
 
-A majority of users run the library by cloning it from Github and running the `main.py` script.
+A majority of users run the library by cloning it from Github, installing the package as editable, and running the `python -m lm_eval` script.
 
 Equivalently, running the library can be done via the `lm-eval` entrypoint at the command line.
 

docs/model_guide.md

@@ -70,9 +70,9 @@ smth smth tokenizer-agnostic
 
 Congrats on implementing your model! Now it's time to test it out.
 
-To make your model usable via the command line interface to `lm-eval` using `main.py`, you'll need to tell `lm-eval` what your model's name is.
+To make your model usable via the command line interface to `lm-eval` using `python -m lm_eval`, you'll need to tell `lm-eval` what your model's name is.
 
-This is done via a *decorator*, `lm_eval.api.registry.register_model`. Using `register_model()`, one can both tell the package what the model's name(s) to be used are when invoking it with `python main.py --model <name>` and alert `lm-eval` to the model's existence.
+This is done via a *decorator*, `lm_eval.api.registry.register_model`. Using `register_model()`, one can both tell the package what the model's name(s) to be used are when invoking it with `python -m lm_eval --model <name>` and alert `lm-eval` to the model's existence.
 
 ```python
 from lm_eval.api.registry import register_model

docs/new_task_guide.md

@@ -258,7 +258,7 @@ You can do this via adding the Python snippet
 from lm_eval.tasks import include_task_folder
 include_task_folder("/path/to/yaml/parent/folder")
 ```
-to the top of any Python file that is run or imported when performing evaluation, such as `main.py`.
+to the top of any Python file that is run or imported when performing evaluation, such as `\_\_main\_\_.py`.
 
 Passing `--tasks /path/to/yaml/file` is also accepted.
 

main.py → lm_eval/__main__.py

@@ -12,10 +12,9 @@ from lm_eval.api.registry import ALL_TASKS
 from lm_eval.logger import eval_logger, SPACING
 from lm_eval.tasks import include_task_folder
 
-os.environ["TOKENIZERS_PARALLELISM"] = "false"
+from typing import Union
 
-
-def parse_args() -> argparse.Namespace:
+def parse_eval_args() -> argparse.Namespace:
     parser = argparse.ArgumentParser(formatter_class=argparse.RawTextHelpFormatter)
     parser.add_argument("--model", required=True, help="Name of model e.g. `hf`")
     parser.add_argument(
@@ -100,8 +99,13 @@ def parse_args() -> argparse.Namespace:
     return parser.parse_args()
 
 
-def main() -> None:
-    args = parse_args()
+def cli_evaluate(args: Union[argparse.Namespace, None] = None) -> None:
+
+    if not args:
+        # we allow for args to be passed externally, else we parse them ourselves
+        args = parse_eval_args()
+
+    os.environ["TOKENIZERS_PARALLELISM"] = "false"
 
     if args.limit:
         eval_logger.warning(
@@ -212,5 +216,5 @@ def main() -> None:
             print(evaluator.make_table(results, "groups"))
 
 
-if __name__ == "__main__":
-    main()
+if __name__ == "__main__":  
+    cli_evaluate()

pyproject.toml

@@ -47,8 +47,8 @@ lm_eval = ["**/*.yaml", "tasks/**/*"]
 examples = ["**/*.yaml"]
 
 [project.scripts]
-lm-eval = "main:main"
-lm_eval = "main:main"
+lm-eval = "lm_eval.__main__:cli_evaluate"
+lm_eval = "lm_eval.__main__:cli_evaluate"
 
 [project.urls]
 Homepage = "https://github.com/EleutherAI/lm-evaluation-harness"