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 be94bc418b fix code block instruction always python 1 year ago
..
benchmarks better messages 1 year ago
executors reinit submodules 1 year ago
generators fix code block instruction always python 1 year ago
human-eval start v2 1 year ago
lazzzy@404c06a5bf reinit submodules 1 year ago
root add logs 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 added model class 1 year ago
immediate_reflexion.py added model class 1 year ago
main.py added model class 1 year ago
reflexion.py added model class 1 year ago
reflexion_ucs.py added model class 1 year ago
requirements.txt fix literal import 1 year ago
run_immediate_refinement.sh start v2 1 year ago
run_immediate_reflexion.sh start v2 1 year ago
run_reflexion.sh better messages 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_starchat_multi.sh scripts 1 year ago
run_reflexion_startchat.sh change name 1 year ago
run_reflexion_ucs.sh add runscripts 1 year ago
run_seq.sh scripts 1 year ago
run_simple.sh better messages 1 year ago
run_simple_py_leet.sh start v2 1 year ago
run_simple_rs_leet.sh start v2 1 year ago
run_simple_starchat_multi.sh scripts 1 year ago
run_testacc.sh start v2 1 year ago
simple.py better messages 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