Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Website
Tasks
HuggingChat
Collections
Languages
Organizations
Community
Blog
Posts
Daily Papers
Hardware
Learn
Discord
Forum
GitHub
Solutions
Team & Enterprise
Hugging Face PRO
Enterprise Support
Inference Providers
Inference Endpoints
Storage Buckets
Log In
Sign Up
๐ค
Open to Collab
Eric
PRO
Dorman11
1
1
9
Follow
0001AMA's profile picture
Datdanboi25's profile picture
NILKNARFGonzo's profile picture
6 followers
ยท
36 following
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
reacted
to
maglun
's
post
with ๐
22 minutes 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.
replied
to
maglun
's
post
22 minutes 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.
liked
a model
33 minutes ago
moonshotai/Kimi-K3
View all activity
Organizations
Dorman11
's buckets
2
Sort:ย Recently updated
Dorman11/datasetdb
5.48 MB
Dorman11/slop-classification-bucket
61.3 kB