cleanup

lm_eval/__main__.py

-from lm_eval._cli import CLIParser
+from lm_eval._cli import Eval
 
 
 def cli_evaluate() -> None:
     """Main CLI entry point with subcommand and legacy support."""
-    parser = CLIParser()
+    parser = Eval()
     args = parser.parse_args()
     parser.execute(args)
 

lm_eval/_cli/__init__.py

 """
-CLI subcommands for the Language Model Evaluation Harness.
+CLI subcommands to run from terminal.
 """
 
 from lm_eval._cli.base import SubCommand
-from lm_eval._cli.cli import CLIParser
-from lm_eval._cli.list import ListCommand
+from lm_eval._cli.eval import Eval
+from lm_eval._cli.list import List
 from lm_eval._cli.run import Run
-from lm_eval._cli.validate import ValidateCommand
+from lm_eval._cli.validate import Validate
 
 
 __all__ = [
     "SubCommand",
     "Run",
-    "ListCommand",
-    "ValidateCommand",
-    "CLIParser",
+    "List",
+    "Validate",
+    "Eval",
 ]

lm_eval/_cli/cli.py → lm_eval/_cli/eval.py

@@ -2,13 +2,13 @@ import argparse
 import sys
 import textwrap
 
-from lm_eval._cli.list import ListCommand
+from lm_eval._cli.list import List
 from lm_eval._cli.run import Run
-from lm_eval._cli.validate import ValidateCommand
+from lm_eval._cli.validate import Validate
 
 
-class CLIParser:
-    """Main CLI parser class that manages all subcommands."""
+class Eval:
+    """Main CLI parser that manages all subcommands."""
 
     def __init__(self):
         self._parser = argparse.ArgumentParser(
@@ -45,8 +45,8 @@ class CLIParser:
             dest="command", help="Available commands", metavar="COMMAND"
         )
         Run.create(self._subparsers)
-        ListCommand.create(self._subparsers)
-        ValidateCommand.create(self._subparsers)
+        List.create(self._subparsers)
+        Validate.create(self._subparsers)
 
     def parse_args(self) -> argparse.Namespace:
         """Parse arguments using the main parser."""

lm_eval/_cli/list.py

@@ -4,7 +4,7 @@ import textwrap
 from lm_eval._cli.base import SubCommand
 
 
-class ListCommand(SubCommand):
+class List(SubCommand):
     """Command for listing available tasks."""
 
     def __init__(self, subparsers: argparse._SubParsersAction, *args, **kwargs):
@@ -14,6 +14,7 @@ class ListCommand(SubCommand):
             "list",
             help="List available tasks, groups, subtasks, or tags",
             description="List available tasks, groups, subtasks, or tags from the evaluation harness.",
+            usage="lm-eval list [tasks|groups|subtasks|tags] [--include_path DIR]",
             epilog=textwrap.dedent("""
                 examples:
                   # List all available tasks (includes groups, subtasks, and tags)

lm_eval/_cli/run.py

@@ -17,12 +17,12 @@ class Run(SubCommand):
     """Command for running language model evaluation."""
 
     def __init__(self, subparsers: argparse._SubParsersAction, *args, **kwargs):
-        # Create and configure the parser
         super().__init__(*args, **kwargs)
         self._parser = subparsers.add_parser(
             "run",
-            help="Run language model evaluation",
+            help="Run the evaluation harness on specified tasks",
             description="Evaluate language models on various benchmarks and tasks.",
+            usage="lm-eval run --model <model> --tasks <task1,task2,...> [options]",
             epilog=textwrap.dedent("""
                 examples:
                   # Basic evaluation with HuggingFace model
@@ -42,7 +42,7 @@ class Run(SubCommand):
             formatter_class=argparse.RawDescriptionHelpFormatter,
         )
         self._add_args()
-        self._parser.set_defaults(func=lambda args: self._parser.print_help())
+        self._parser.set_defaults(func=lambda arg: self._parser.print_help())
 
     def _add_args(self) -> None:
         self._parser = self._parser
@@ -281,7 +281,7 @@ class Run(SubCommand):
         )
 
     def execute(self, args: argparse.Namespace) -> None:
-        """Execute the evaluation command."""
+        """Runs the evaluation harness with the provided arguments."""
         from lm_eval.config.evaluate_config import EvaluatorConfig
 
         # Create and validate config (most validation now happens in EvaluationConfig)

lm_eval/_cli/validate.py

@@ -5,7 +5,7 @@ import textwrap
 from lm_eval._cli.base import SubCommand
 
 
-class ValidateCommand(SubCommand):
+class Validate(SubCommand):
     """Command for validating tasks."""
 
     def __init__(self, subparsers: argparse._SubParsersAction, *args, **kwargs):
@@ -15,6 +15,7 @@ class ValidateCommand(SubCommand):
             "validate",
             help="Validate task configurations",
             description="Validate task configurations and check for errors.",
+            usage="lm-eval validate --tasks <task1,task2> [--include_path DIR]",
             epilog=textwrap.dedent("""
                 examples:
                   # Validate a single task
@@ -72,7 +73,7 @@ class ValidateCommand(SubCommand):
             formatter_class=argparse.RawDescriptionHelpFormatter,
         )
         self._add_args()
-        self._parser.set_defaults(func=lambda args: self._parser.print_help())
+        self._parser.set_defaults(func=lambda arg: self._parser.print_help())
 
     def _add_args(self) -> None:
         self._parser.add_argument(