3-level

3-level curriculum + 7B + reward fixes

Add training evidence: curriculum results, plots (LFS), parse_job_log helper

changed model

training script

----

feat: implement GRPO training pipeline for bail assessment model and update README credits

feat: implement dataset loader, environment, and GRPO training pipeline for undertrial bail prediction

implemented

Rewrite README as full hackathon submission doc with env design, reward formula, curriculum, training arch

Implement client.py HTTP methods + add HF Spaces README metadata

Fix Dockerfile for HF Spaces non-root user + update README URLs

first commit