Upload folder using huggingface_hub

Upload folder using huggingface_hub

Upload folder using huggingface_hub

Fix train_grpo.py: rename SFT path, add actual GRPO CLI entrypoint with wired-in procedural gen + trajectory filter + adversarial attacker"

Upload folder using huggingface_hub

Remove temp file

Remove max_prompt_length from GRPOConfig (removed in TRL 1.x, Unsloth rejects it)"

Add adversarial attacker for self-play curriculum\n\nReference: SPIRAL (arXiv 2506.24119)\nAdaptive attacker that adds decoys, obscures IOCs, tightens deadlines,\nand exploits defender blind spots. Creates automatic difficulty scaling."

Add StarPO-S trajectory filtering for GRPO stability\n\nReference: RAGEN (arXiv 2504.20073)\nFilters to keep only informative rollouts, preventing echo trap collapse."

Add real-world security API integrations (OSV.dev, deps.dev, GHSA, npm)\n\nFree, no-auth-required live lookups against security databases.\nAdds genuine information-gathering vs time-pressure tradeoff."

Add procedural scenario generation (infinite training variation)\n\nGenerates unique supply-chain incidents from parameterized distributions.\nReference: Self-Evolving Curriculum (arXiv 2505.14970)"

Upload folder using huggingface_hub