Spaces:

Draken1606
/

undertrial-ai

Running

App Files Files Community

undertrial-ai / server

127 kB

Ctrl+K

Ctrl+K

2 contributors

History: 26 commits

Draken1606's picture

3-level curriculum + 7B + reward fixes

9868dfb 3 days ago

__init__.py

160 Bytes
Fix 8 compliance gaps: repeat-action dedup+cache, min-steps hard block, criminal history tool (12th action), efficiency removed from training formula, circular import cleaned, yaml formula synced 14 days ago
adaptive_selector.py

4.7 kB
implemented 14 days ago
app.py

16 kB
---- 13 days ago
case_generator.py

10 kB
implemented 14 days ago
dataset.py

17.8 kB
feat: implement dataset loader, environment, and GRPO training pipeline for undertrial bail prediction 13 days ago
performance_tracker.py

8.47 kB
modified 14 days ago
precedent_db.py

8.28 kB
first commit 15 days ago
requirements.txt

96 Bytes
first commit 15 days ago
reward.py

29.4 kB
3-level curriculum + 7B + reward fixes 3 days ago
schema_drift.py

5.82 kB
Fix B1-B4: add 4 actions to openenv.yaml, export from __init__/client, fix reward range, remove global random.seed 14 days ago
undertrial_environment.py

26.7 kB
feat: implement dataset loader, environment, and GRPO training pipeline for undertrial bail prediction 13 days ago