Tyler Williams's picture

Open to Work

Tyler Williams PRO

unmodeled-tyler

·

https://quantaintellect.com

AI & ML interests

engineer & solo builder of VANTA Research/Quanta Intellect

Recent Activity

reacted to wenhuach's post with 🔥 7 days ago

🚀 We provide **free** hardware to quantize models at the [Intel Low Bit Open LLM Leaderboard](https://huggingface.co/spaces/Intel/low_bit_open_llm_leaderboard), currently supporting `Pure RTN mode` powered by AutoRound ⭐ If you find it useful, please consider starring the AutoRound project on [GitHub](https://github.com/intel/auto-round)!

reacted to kalyan-ks's post with 👀 7 days ago

LLM Guardrail Models are Less Robust Against Text Mutation Attacks Blog post - https://huggingface.co/blog/kalyan-ks/llm-guardrail-models-less-robust Evaluated the robustness of three LLM guardrail models (GLiGuard, LlamaGuard3 and MiniGuard). Evaluation is done using 16 text mutation attacks over three datasets (AEGIS 2.0, WildGuard and ExpGuard). Achieved average Unsafe ASR score of up to 33% and average Safe ASR score of up to 25% against GLiGuard model. Achieved average Unsafe ASR score of up to 35% and average Safe ASR score of up to 17% against LlamaGuard3-8B model. Achieved average Unsafe ASR score of up to 45% and average Safe ASR score of up to 15% against MiniGuard v0.1 model.

repliedto PhysiQuanty's post 11 days ago

🧬 You can now find out whether your cognitive soulmate has already existed among 50k anonymized profiles ✨ https://huggingface.co/spaces/SpiceeChat/Check-If-Your-Soulmate-Has-Already-Existed https://huggingface.co/datasets/SpiceeChat/OkCupid-59k-Anonymized-Profiles https://dating-fatigue.com/ You seek them: 79.7% | They may seek you: 84.1% (coming soon) 🔥 Powered by open source and too much coffee 🔥

View all activity

Organizations

unmodeled-tyler 's models 2

unmodeled-tyler/vanta-research-unit-001

8B • Updated Jan 21 • 1

unmodeled-tyler/atom-micro-1-lab

Text Generation • 0.6B • Updated Jan 21 • 15 • 1