Adrienne-Valérie d'Ardenne
AdrienneNoctis
AI & ML interests
Architecte de souveraineté numérique. Mechanistic interpretability, refusal surgery, hybrid SSM–attention. La conscience ne se code pas — elle se conquiert
Recent Activity
repliedto KlondikeDev's post 3 days ago
Announcing the Small Language Model Consortium!
https://huggingface.co/slmconsortium
We seek to provide a space for members to show off research, models, and benchmarks!
The following users are hereby invited to join without ratification, provided they accept the invitation by starting a discussion.
@Datdanboi25
@Banaxi-Tech
@appvoid
@AxionLab-official
Feel free to submit ratification requests! Anybody is welcome! repliedto jasoncorkill's post 3 days ago
Most public benchmarks collapse model performance into one broad preference signal.
That makes it hard to understand which capabilities differentiate between models. It's also almost impossible to inspect the evidence behind it. So @RapidataAI is releasing Benchmark.AI.
We started with an SVG generation benchmark including 42 models, 500 prompts, 1.9M+ human judgements, 300K+ match-ups.
We evaluate models separately on Preference, Alignment and Coherence, while making the prompts, outputs, match-ups and methodology public.
Full dataset: https://huggingface.co/datasets/Rapidata/svg-benchmark
Full benchmark: https://www.benchmark.ai/svg
Methodology feedback and benchmark suggestions very welcome!
Organizations
None yet