Add pre-training audit scripts, OpenEnv manifest, and tune Parlay training/env (GRPO 1.5B default, min-reward filters, weighted data gen, hiring ZOPA+drift, veteran/opponent prompts, Docker/docs) df724f2 sh4shv4t commited on 30 days ago
feat: split Gemini 2.5 Flash (demo) and Flash-Lite (data), SFT threshold 0.3, favicon + check_gemini 9d82eed sh4shv4t commited on Apr 23