Skip to content

Commit 638f7f2

Browse files
authored
fix: remove the alpha suffix in run_benchmark.py (#179)
## What does this PR do? Remove the alpha suffix of evaluate_rows after the new pkg release ## Test Plan test with `llama-stack-client --endpoint xxx eval run-benchmark "meta-reference-mmlu-cot" --model-id "meta-llama/Llama-3.1-8B-Instruct" --output-dir "/home/markchen1015/" --num-examples 5` and the eval finished successfully ![Screenshot 2025-03-04 at 11 35 03 PM](https://github.com/user-attachments/assets/3cfb6e99-c9b1-409b-b880-98ae3d14b9eb)
1 parent 96749af commit 638f7f2

File tree

1 file changed

+1
-1
lines changed

1 file changed

+1
-1
lines changed

src/llama_stack_client/lib/cli/eval/run_benchmark.py

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -101,7 +101,7 @@ def run_benchmark(
101101
output_res = {}
102102

103103
for i, r in enumerate(tqdm(rows.rows)):
104-
eval_res = client.eval.evaluate_rows_alpha(
104+
eval_res = client.eval.evaluate_rows(
105105
benchmark_id=benchmark_id,
106106
input_rows=[r],
107107
scoring_functions=scoring_functions,

0 commit comments

Comments
 (0)