Spaces:

Humanlearning
/

Cyber_analyst-round1

Sleeping

7.96 kB

Ctrl+K

1 contributor

feat: implement core RL training infrastructure, including GRPO training, evaluation utilities, custom environments, and Modal-based execution scripts.

3807ea3 about 1 month ago

configs
feat: implement core RL training infrastructure, including GRPO training, evaluation utilities, custom environments, and Modal-based execution scripts. about 1 month ago
eval_before_after.py

1.25 kB
feat: implement core RL training infrastructure, including GRPO training, evaluation utilities, custom environments, and Modal-based execution scripts. about 1 month ago
reward_funcs.py

711 Bytes
feat: implement core RL training infrastructure, including GRPO training, evaluation utilities, custom environments, and Modal-based execution scripts. about 1 month ago
rollout.py

3.32 kB
feat: implement core RL training infrastructure, including GRPO training, evaluation utilities, custom environments, and Modal-based execution scripts. about 1 month ago
trackio_utils.py

1.25 kB
feat: implement core RL training infrastructure, including GRPO training, evaluation utilities, custom environments, and Modal-based execution scripts. about 1 month ago
train_grpo.py

1.22 kB
feat: implement core RL training infrastructure, including GRPO training, evaluation utilities, custom environments, and Modal-based execution scripts. about 1 month ago