Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Fix lm_eval.tasks' has no attribute 'initialize_tasks' error #488

Merged
merged 1 commit into from
May 6, 2024
Merged

Fix lm_eval.tasks' has no attribute 'initialize_tasks' error #488

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion recipes/evaluation/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -28,7 +28,7 @@ Before running the evaluation script, ensure you have all the necessary dependen
Clone the lm-evaluation-harness repository and install it:

```bash
git clone https://github.com/matthoffner/lm-evaluation-harness.git
git clone https://github.com/EleutherAI/lm-evaluation-harness.git
cd lm-evaluation-harness
pip install -e .

Expand Down
18 changes: 7 additions & 11 deletions recipes/evaluation/eval.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,7 +11,7 @@

import numpy as np
import lm_eval
from lm_eval import evaluator, tasks
from lm_eval import tasks
from lm_eval.utils import make_table


Expand Down Expand Up @@ -73,20 +73,19 @@ def handle_output(args, results, logger):


def load_tasks(args):
tasks.initialize_tasks()
if args.open_llm_leaderboard_tasks:
current_dir = os.getcwd()
config_dir = os.path.join(current_dir, "open_llm_leaderboard")
lm_eval.tasks.include_path(config_dir)
return [
task_manager = tasks.TaskManager(include_path=config_dir)
return task_manager, [
"arc_challenge_25_shot",
"hellaswag_10_shot",
"truthfulqa_mc2",
"winogrande_5_shot",
"gsm8k",
"mmlu",
]
return args.tasks.split(",") if args.tasks else []
return None, args.tasks.split(",") if args.tasks else []


def parse_eval_args():
Expand Down Expand Up @@ -190,21 +189,18 @@ def parse_eval_args():
default=None,
help="Additional path to include if there are external tasks.",
)
parser.add_argument(
"--decontamination_ngrams_path", default=None
) # Not currently used
return parser.parse_args()


def evaluate_model(args):
try:
task_list = load_tasks(args)
task_manager, task_list = load_tasks(args)
# Customized model such as Quantized model etc.
# In case you are working with a custom model, you can use the following guide to add it here:
# https://github.com/EleutherAI/lm-evaluation-harness/blob/main/docs/interface.md#external-library-usage

# Evaluate
results = evaluator.simple_evaluate(
results = lm_eval.simple_evaluate(
model=args.model,
model_args=args.model_args,
tasks=task_list,
Expand All @@ -214,11 +210,11 @@ def evaluate_model(args):
device=args.device,
use_cache=args.use_cache,
limit=args.limit,
decontamination_ngrams_path=args.decontamination_ngrams_path,
check_integrity=args.check_integrity,
write_out=args.write_out,
log_samples=args.log_samples,
gen_kwargs=args.gen_kwargs,
task_manager=task_manager,
)
handle_output(args, results, logger)

Expand Down
Loading