Spaces:

sh4shv4t
/

Parlay

Paused

App Files Files Community

Parlay / agent

66 kB

Ctrl+K

Ctrl+K

1 contributor

History: 12 commits

sh4shv4t's picture

feat: training results page + SFT Colab notebook

108bc34 about 1 month ago

__init__.py

379 Bytes
feat: split Gemini 2.5 Flash (demo) and Flash-Lite (data), SFT threshold 0.3, favicon + check_gemini about 1 month ago
gemini_client.py

20.5 kB
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) about 1 month ago
hf_opponent.py

5.51 kB
feat: training results page + SFT Colab notebook about 1 month ago
personas.py

6.54 kB
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) about 1 month ago
runner.py

12 kB
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) about 1 month ago
tom_tracker.py

7.97 kB
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) about 1 month ago
tom_tracker_bayesian.py

13.1 kB
feat: flash-lite for data-gen and flash for UI; remove training page; card tests; --quiet data gen; data/ inspect path; random baseline; GRPO env wrapper; reward fixes (buyer ZOPA, ToM signals); drift + Brier metrics; Bayesian ToM module about 1 month ago