mirror of
https://github.com/GammaTauAI/reflexion-human-eval
synced 2024-11-16 00:12:59 +00:00
11 lines
250 B
Bash
Executable File
11 lines
250 B
Bash
Executable File
python main.py \
|
|
--run_name "testacc_humaneval_py3" \
|
|
--root_dir "root" \
|
|
--dataset_path ./benchmarks/humaneval-py.jsonl.gz \
|
|
--strategy "test-acc" \
|
|
--language "py" \
|
|
--model "gpt-4" \
|
|
--pass_at_k "1" \
|
|
--max_iters "1" \
|
|
--verbose
|