temp save; temp hold on for rejection sample CoT; try direct RL with raw stepwise data first

This commit is contained in:
2025-06-30 10:29:00 +00:00
parent 7f4fc8b05b
commit 5e632c53ac
10 changed files with 1119 additions and 4 deletions

2
.gitignore vendored
View File

@@ -1,5 +1,7 @@
output/
result/
sample/sample_output/
sample/tmp_dataset_gen/
sample/output_data/
*__pycache__/