lirenqiu
/
scenic
0
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
scenic/scripts
History
lirenqiu f9112ad4a0 Initial commit: Scenic baseline evaluation system 
- Complete baseline evaluation framework for ChatScene and ScenicNL
- Implemented Property 9: Scenic Import Configuration with comprehensive tests
- Added comprehensive documentation and examples
- Includes Scenic, ChatScene, and ScenicNL subprojects
- Property-based testing with Hypothesis framework
- Full command-line interface and configuration management

Features:
- Unified compilation checking using ScenicNL's check_compile
- Resume capability for long-running evaluations
- Detailed error classification and handling
- Statistical analysis and reporting
- Comprehensive test suite with 100+ property test iterations
 		2026-01-11 10:58:59 +08:00
..
01_激活环境.sh Initial commit: Scenic baseline evaluation system 2026-01-11 10:58:59 +08:00
02_配置API密钥.sh Initial commit: Scenic baseline evaluation system 2026-01-11 10:58:59 +08:00
03_模型配置测试.py Initial commit: Scenic baseline evaluation system 2026-01-11 10:58:59 +08:00
04_环境检查.sh Initial commit: Scenic baseline evaluation system 2026-01-11 10:58:59 +08:00
05_配置ChatScene.sh Initial commit: Scenic baseline evaluation system 2026-01-11 10:58:59 +08:00
06_配置ScenicNL.sh Initial commit: Scenic baseline evaluation system 2026-01-11 10:58:59 +08:00