代码库
Run a documented subset of verl-style OPD on one consumer GPU—typed config, Parquet prompts, and PEFT scale-out artifacts.
Python
agentic-rlalignmentconsumer-gpuknowledge-distillationllmllm-agentsllm-alignmenton-policy-distillationpeftpost-trainingqloraqwensingle-gputool-useverl