You cannot select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
reflexion-human-eval/programming_runs
Noah Shinn 34ab94a3b3 start run instructions 1 year ago
..
executors reinit submodules 1 year ago
generators start v2 1 year ago
human-eval start v2 1 year ago
lazzzy@404c06a5bf reinit submodules 1 year ago
root start v2 1 year ago
README.md start run instructions 1 year ago
dataset_random_sample.py start v2 1 year ago
evaluate_leet_results.py start v2 1 year ago
evaluate_rs_leet_results.py start v2 1 year ago
generate_dataset.py start v2 1 year ago
humaneval_result_sort.py start v2 1 year ago
immediate_refinement.py start v2 1 year ago
immediate_reflexion.py start v2 1 year ago
main.py start v2 1 year ago
reflexion.py start v2 1 year ago
reflexion_ucs.py start v2 1 year ago
requirements.txt start v2 1 year ago
run_immediate_refinement.sh start v2 1 year ago
run_immediate_reflexion.sh start v2 1 year ago
run_reflexion.sh start run instructions 1 year ago
run_reflexion_humaneval_30.sh start v2 1 year ago
run_reflexion_py_leet.sh start v2 1 year ago
run_reflexion_rs_leet.sh start v2 1 year ago
run_reflexion_ucs.sh start v2 1 year ago
run_simple.sh start v2 1 year ago
run_simple_py_leet.sh start v2 1 year ago
run_simple_rs_leet.sh start v2 1 year ago
run_testacc.sh start v2 1 year ago
simple.py start v2 1 year ago
simple_mbpp_py2_logs start v2 1 year ago
simple_mbpp_py_logs start v2 1 year ago
test.py start v2 1 year ago
test_acc.py start v2 1 year ago
utils.py start v2 1 year ago
validate_py_results.py start v2 1 year ago
validate_rs_results.py start v2 1 year ago

README.md

Programming runs

Reflexion programming v2 is not released yet but will be available in a few days after the code is cleaned up