Hugging Face's logo
Eric's picture
🤝 Open to Collab

Eric PRO

Dorman11
1 1 9
maglun's profile picture Banaxi-Tech's profile picture NILKNARFGonzo's profile picture
·

AI & ML interests

Currently training Endeavor, a SLM model! Interests include: Agentic security, Machine Learning, Reinforcement Learning, PyTorch and all around web dev ninja! Level II Specialist working in Cyber Security field.

Recent Activity

updated a Space about 1 hour ago
Dorman11/open-mythos-run
updated a bucket about 1 hour ago
Dorman11/datasetdb
reacted to maglun's post with 🚀 about 23 hours ago
I work on quantizing models to run efficiently on local hardware, and kept being curious how existing quants spend their "bit budget" during optimization and built a local tool to explore. Many quants apply one setting across all tensors, but some do more interesting things: the model in the screenshot holds attention K at 4.5 bits while Q/V/O get 8.5, and protects layer 0 MLP. It turned out useful enough that I made it public: https://tensorlens.dev Explore any HF model in the browser without downloading it. The anatomy map is read from the safetensors header via a range request, and only tensors you click ever stream. Large tensors are sampled rather than streamed in full. Limitations: safetensors only (no GGUF yet), some exotic variants don't work yet, and gated repos aren't supported yet. Feedback very welcome, especially models that break it.
View all activity

Organizations

BananaMind Model Previewers's profile picture North ML Previews's profile picture