Spaces:
Running
Running
Commit History
4 days ago
-
Add frozen-critic PPO and show objective gradients directly on tokens Running
Verified signatureUse the pinned ORZ 0.5B value critic with per-token GAE and editable values. Replace toy probability-change chips with exact objective gradients, keep collected probabilities fixed, and explain the optimizer/forward-pass distinction. Preserve monochrome RL modes and fix mobile navigation overflow.847dfdc
5 days ago
-
Add frozen-model GRPO rollout and one-step logit sandbox
Verified signature2485c8f
18 days ago
-
Publish Qwen and Gemma layer and attention explorer
Verified signature1022407