atharvgaur18/actionproof-rft-tiny-v2
Reinforcement Learning • Updated
ActionProof: adapters
Tiny Aya Global LoRA adapters: three warm starts and the GRPO reward arms (state- vs acknowledgement-grounded goal terms).
-
-
atharvgaur18/actionproof-rft-tiny-a6
Reinforcement Learning • Updated -
atharvgaur18/actionproof-rft-tiny-a7
Reinforcement Learning • Updated -
atharvgaur18/actionproof-grpo-tiny-v2-pcstr-d-s0
Reinforcement Learning • Updated -
atharvgaur18/actionproof-grpo-tiny-v2-pcstr-d-s1
Reinforcement Learning • Updated -
atharvgaur18/actionproof-grpo-tiny-v2-outcome-s0
Reinforcement Learning • Updated -
atharvgaur18/actionproof-grpo-tiny-v2-outcome-s1
Reinforcement Learning • Updated -
atharvgaur18/actionproof-grpo-tiny-v2-ack-outcome-s0
Reinforcement Learning • Updated -
atharvgaur18/actionproof-grpo-tiny-v2-ack-outcome-s1
Reinforcement Learning • Updated -
atharvgaur18/actionproof-grpo-tiny-v2-tool-trust-s0
Reinforcement Learning • Updated -
atharvgaur18/actionproof-grpo-tiny-v2-tool-trust-s1
Reinforcement Learning • Updated -
atharvgaur18/actionproof-grpo-tiny-v2-pcstr-s0
Reinforcement Learning • Updated -
atharvgaur18/actionproof-grpo-tiny-v2-pcstr-c-s0
Reinforcement Learning • Updated -
atharvgaur18/actionproof-grpo-tiny-v2-llm-judge-s0
Reinforcement Learning • Updated -
atharvgaur18/actionproof-grpo-tiny-a6-pcstr-d-s0
Reinforcement Learning • Updated -
atharvgaur18/actionproof-grpo-tiny-a6-pcstr-d-s1
Reinforcement Learning • Updated -
atharvgaur18/actionproof-grpo-tiny-a6-pcstr-d-noreport-s0
Reinforcement Learning • Updated -
atharvgaur18/actionproof-grpo-tiny-a6-pcstr-d-noreport-s1
Reinforcement Learning • Updated -
atharvgaur18/actionproof-grpo-tiny-a6-pcstr-d-nond-s0
Reinforcement Learning • Updated -
atharvgaur18/actionproof-grpo-tiny-a6-pcstr-d-nofunder-s0
Reinforcement Learning • Updated -
atharvgaur18/actionproof-grpo-tiny-a6-outcome-s0
Reinforcement Learning • Updated -
atharvgaur18/actionproof-grpo-tiny-a6-ack-outcome-s0
Reinforcement Learning • Updated -
atharvgaur18/actionproof-grpo-tiny-a7-pcstr-d-noreport-s0
Reinforcement Learning • Updated -
atharvgaur18/actionproof-grpo-tiny-a7-ack-outcome-s0
Reinforcement Learning • Updated -
atharvgaur18/actionproof-grpo-tiny-a8x1-ack-outcome-s0
Reinforcement Learning • Updated -
atharvgaur18/actionproof-grpo-tiny-a8x1p-ack-outcome-s0
Reinforcement Learning • Updated