Spaces:

agentDebugger
/

AgentDebugger-training-v3

Sleeping

App Files Files Community

AgentDebugger-training-v3 / training

21.6 kB

Ctrl+K

Ctrl+K

5 contributors

History: 15 commits

shank

Auto-detect GPU: bfloat16+batch2+gen8 on A100, float16+batch1+gen4 on T4 — same script works on both

ea6fe4e 4 months ago

train_grpo.py
21.6 kB
Auto-detect GPU: bfloat16+batch2+gen8 on A100, float16+batch1+gen4 on T4 — same script works on both 4 months ago