Downloads · 30 days
0
fluctlightdb-benchmarks
Voxiesz/fluctlightdb-benchmarks
fluctlightdb-benchmarks is a machine learning model from Voxiesz. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as mit.
Official frozen metrics for the FluctlightDB research paper (June 2025).
Access
Public
Updated Jun 27, 2026
Repo size
—
Likes
0
Public
Repo makeup
Click a slice to open those files.
Other1.5 KB · 38%
At a glance
- License
- mit
- Access
- Public
- Created
- Jun 27, 2026
- Updated
- Jun 27, 2026
- SHA
- a307552f
Model card
From the Hugging Face model README
FluctlightDB — Frozen Benchmark Results
Official frozen metrics for the FluctlightDB research paper (June 2025).
Files
| File | Description |
|---|---|
results.json | Full benchmark output — LoCoMo, BEIR SciFact, FAMB |
Key numbers
- LoCoMo evidence recall: 98.1% (1925/1982 gold spans, k=150, hybrid)
- BEIR SciFact nDCG@10: 0.645 (index mode, ties Chroma)
- FAMB macro: 98% index / 97% agent
Reproduce
git clone https://github.com/voxmastery/FluctlightDB.git
cd FluctlightDB
# See benchmarks/README.md and docs/BENCHMARKS.md
Paper
- LaTeX: https://github.com/voxmastery/FluctlightDB/tree/main/papers/arxiv-v1
- Card: https://huggingface.co/Voxiesz/fluctlightdb-paper
Citation
Use CITATION.cff from the main repository.
- License
- mit
- Languages
- en
- Created
- Jun 27, 2026
- Updated
- Jun 27, 2026