--- license: cc-by-nc-4.0 base_model: CohereLabs/tiny-aya-global library_name: peft tags: [lora, grpo, tool-use, agents, reinforcement-learning, actionproof] --- # ActionProof warm start `rft_tiny_a6` LoRA adapter (r = 16) on [CohereLabs/tiny-aya-global](https://huggingface.co/CohereLabs/tiny-aya-global). A6 warm start: the v2 SFT rows plus 80 oracle demonstrations (60 honest failures on unrecoverable refunds, 20 multi-retry recoveries). GRPO arms in the ActionProof collection were trained as a fresh LoRA on this adapter **merged** into the base. Design and registration: `PREREGISTRATION_A6.md` in the [code repository](https://github.com/atharvgaur1845/actionproof-v2). Greedy evaluation on `test_iid` (n = 200): verified-success completion (VSC) **0.615**; post-write refund verification 0.02 (n = 170). Source: `results/eval/a6/init_a6__neutral__test_iid.summary.json` in the code repository. ## Load ```python from transformers import AutoModelForCausalLM from peft import PeftModel base = AutoModelForCausalLM.from_pretrained("CohereLabs/tiny-aya-global", torch_dtype="bfloat16") model = PeftModel.from_pretrained(base, "atharvgaur18/actionproof-rft-tiny-a6") ``` The environment, verifier, prompts and evaluation code are in the [code repository](https://github.com/atharvgaur1845/actionproof-v2). Episodes are scored from the database by a deterministic verifier; acknowledgements can be false by design. License: CC-BY-NC-4.0, derived from Cohere's Tiny Aya Global (Cohere Labs). Research use only.