This commit is contained in:
@@ -0,0 +1,15 @@
|
||||
# Copyright (c) ModelScope Contributors. All rights reserved.
|
||||
import os
|
||||
|
||||
os.environ['CUDA_VISIBLE_DEVICES'] = '0'
|
||||
|
||||
if __name__ == '__main__':
|
||||
from swift import DeployArguments, EvalArguments, eval_main, run_deploy
|
||||
|
||||
# Here's a runnable demo provided. Use the eval_url method for evaluation.
|
||||
# In a real scenario, you can simply remove the deployed context.
|
||||
print(EvalArguments.list_eval_dataset())
|
||||
with run_deploy(
|
||||
DeployArguments(model='Qwen/Qwen2.5-0.5B-Instruct', verbose=False, log_interval=-1, infer_backend='vllm'),
|
||||
return_url=True) as url:
|
||||
eval_main(EvalArguments(model='Qwen2.5-0.5B-Instruct', eval_url=url, eval_dataset=['arc']))
|
||||
@@ -0,0 +1,7 @@
|
||||
# You need to have a deployed model or api service first
|
||||
swift eval \
|
||||
--model '<model_name>' \
|
||||
--eval_backend OpenCompass \
|
||||
--eval_url http://127.0.0.1:8000/v1 \
|
||||
--eval_limit 100 \
|
||||
--eval_dataset gsm8k
|
||||
Reference in New Issue
Block a user