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
♾️
Thinking
Wop
wop
85
32
466
Follow
FLIPTRIGGA's profile picture
AxionLab-official's profile picture
jobicy's profile picture
48 followers
·
149 following
https://bench-labs-org.github.io
koo1140
AI & ML interests
AI research AGI
Recent Activity
reacted
to
Gjusev
's
post
with 🔥
1 day ago
I retracted my own launch claim in public commits, then shipped what survived. MK-SH-1 is a 140M decision model I built on an open encoder. It returns calibrated probabilities, a choice, and an explicit abstention below a frozen gate (tau = 0.79, written down before the curve existed). ECE 0.016 · 90% coverage in-sample; held-out numbers in the card · 106 ms on CPU. https://huggingface.co/Gjusev/MK-SH-1 Demo https://huggingface.co/spaces/Gjusev/MK-SH-1-demo Full record, retraction included https://github.com/Gjusev/MK-SH-1
reacted
to
tardellirs
's
post
with 🔥
2 days ago
Crivo-150M is now on the Pareto frontier of the Decision Index 🎯 Scored by the maintainers on the private tests: Full 22.21, the best of all submissions at or below 150M and higher than every model below 0.75B, including models up to 4× its size. Median latency on the board's GPU: 13 ms. It is a 149M typed-decision encoder (Ettin / ModernBERT): a state plus choice, noul or score questions in, a probability for every option out, in one forward pass. Trained on open data only. Next: tasks from new domains, the weak spot of every small encoder on the board. https://huggingface.co/tardellirs/crivo-150m https://huggingface.co/spaces/multimodalart/jev-decision-index Thanks to @multimodalart for the Decision Index and its open kit, @orionweller and the Ettin team, @tomaarsen for the Ettin rerankers, @hotchpotch for the Bekko System One data and @sileod for tasksource.
reacted
to
wayneworkman2012
's
post
with 👀
2 days ago
To all the inference providers behind the HuggingFace router - if you want me to use your services you will have to serve native-precision models. I'm not paying for FP8 when I can run in bf16 locally.
View all activity
Organizations
wop
's datasets
20
Sort: Recently updated
wop/re-think-compressed
Updated
Jul 30
•
7
wop/Ultra-distill
Updated
Jul 22
•
5
•
1
wop/Human-Essence-Dataset
Viewer
•
Updated
Jun 13
•
27
•
6
•
1
wop/debug-self
Viewer
•
Updated
Jun 13
•
1
•
20
wop/smallestdata-sft
Viewer
•
Updated
Jun 10
•
19
•
23
•
1
wop/Super-Intelligence-Immersive
Viewer
•
Updated
Jun 10
•
2
•
9
wop/Cosmos-T3-06-09-2026
Viewer
•
Updated
Jun 9
•
295k
•
32
•
1
wop/miniconveserations
Viewer
•
Updated
Jun 9
•
16
•
3
wop/instantShot
Viewer
•
Updated
Jun 7
•
177
•
12
•
1
wop/TinyData
Viewer
•
Updated
Jun 6
•
1.64k
•
11
•
2
wop/Generic-Chat-Prompts-Tier1
Viewer
•
Updated
Jun 4
•
172
•
4
wop/minitron-dataset
Viewer
•
Updated
Jun 3
•
288k
•
22
•
1
wop/XXXXXL-chain-of-thought
Viewer
•
Updated
Jun 2
•
5.79M
•
75
•
5
wop/my-personal-codex-data
Viewer
•
Updated
May 29
•
57
•
98
wop/simple-math-x8_000_000
Viewer
•
Updated
May 17
•
8M
•
16
•
2
wop/Unlimited-Creativity-Chain-of-Thought
Viewer
•
Updated
Mar 1
•
6
•
17
•
2
wop/Extreme-Reasoning-CoT
Viewer
•
Updated
Feb 28
•
18
•
10
•
2
wop/just-user-prompts
Viewer
•
Updated
Feb 24
•
825k
•
32
•
1
wop/Romanian_Language
Viewer
•
Updated
Sep 23, 2024
•
1
•
8
wop/discord_chats_1709
Viewer
•
Updated
Dec 8, 2023
•
1.71k
•
14