Models
Datasets
Spaces
Buckets new
Docs
Enterprise
Pricing
- Website
- Community
- Solutions
Log In
Sign Up

Spaces:

dnanh
/

vilexagent

Paused

App Files Files Community

Fetching metadata from the HF Docker repository...

vilexagent / evaluation

298 kB

Ctrl+K

Ctrl+K

2 contributors

History: 2 commits

Nhat Anh

phase 4: Complete agent UI and final evaluation run

1b14988 3 months ago

results
phase 4: Complete agent UI and final evaluation run 3 months ago
__init__.py

0 Bytes
Phase 3: full 30-question evaluation complete - ViLexAgent groundedness 4.35 vs 2.20 baseline 3 months ago
benchmark.json

18.3 kB
Phase 3: full 30-question evaluation complete - ViLexAgent groundedness 4.35 vs 2.20 baseline 3 months ago
build_benchmark.py

19.7 kB
Phase 3: full 30-question evaluation complete - ViLexAgent groundedness 4.35 vs 2.20 baseline 3 months ago
run_evaluation.py

40.5 kB
phase 4: Complete agent UI and final evaluation run 3 months ago