Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Website
Tasks
HuggingChat
Collections
Languages
Organizations
Community
Blog
Posts
Daily Papers
Learn
Discord
Forum
GitHub
Solutions
Team & Enterprise
Hugging Face PRO
Enterprise Support
Inference Providers
Inference Endpoints
Storage Buckets
Log In
Sign Up
1
4
79
TenAI
PRO
honey90
Follow
kolaslab's profile picture
Anserwise's profile picture
21world's profile picture
14 followers
Ā·
42 following
AI & ML interests
None yet
Recent Activity
reacted
to
SeaWolf-AI
's
post
with ā
about 8 hours ago
Darwin-60B-DUO: Two SOTAs, One Endpoint ā 88.38% on GPQA Diamond š We're excited to release Darwin-60B-DUO, the Darwin family's first DUO model. Take two domain-verified specialists, hide them behind a single OpenAI-compatible endpoint, and let a router decide which one (or both) answers. You see one model, one API ā but get the best of both. The number that matters: on the full 198-question GPQA Diamond, Darwin-60B-DUO hits 88.38%. The constituents alone land at 69.70% (Darwin-28B-REASON) and 77.27% (AWAXIS-Think-31B); a naive cascade only reaches 83.84%. The DUO clears them all. Two small specialists, intelligently routed, beat one big generalist on cost and quality. Both are independently verified ā Darwin-28B-REASON is #3 on the HF GPQA Diamond leaderboard, AWAXIS-Think-31B is #1 on Korea's national K-AI Leaderboard (MSIT). The brains is a Hybrid-A router picking one of five strategies on the fly. Korean ā AWAXIS, English/STEM ā Darwin (single-backend, ~70% of traffic at 1Ć cost). When a Korean answer needs rigorous English reasoning, split_refine fires ā Darwin drafts, AWAXIS polishes; MCQ/short-answer runs both with self-consistency + cross-verify. Net effective cost: only ~1.3Ć a single 30B model. The part the community will care about: the gateway is model-agnostic and Apache-2.0. Point it at any two OpenAI-compatible backends and you've got a DUO in minutes ā teach router.py when to use which, and parallel calls, response merging, and routing transparency via _duo_route are handled for you. Fork it and tell us what you built. Painless deploy: docker compose up for both vLLM backends + gateway; FP8 ~30GB colocates on a single B200/H100. One git clone (~120GB). Text-only for now, streaming in v1.1. Two SOTAs, one endpoint. Come build your own on the Community tab. š š https://huggingface.co/FINAL-Bench/Darwin-60B-DUO
liked
a model
about 8 hours ago
FINAL-Bench/Darwin-60B-DUO
liked
a model
7 days ago
FINAL-Bench/Darwin-28B-Coder
View all activity
Organizations
None yet
spaces
26
Sort:Ā Recently updated
pinned
Sleeping
Agents
Remove Video Background
š
Easily remove your videos background!
pinned
Runtime error
Agents
DALLE 3 XL v2
š„
Sleeping
Agents
WAN 2.1 Fast & security
š„
Running
tenspce
š³
Runtime error
Agents
FLUX LOGO Generator
š
Sleeping
Agents
gradio_workflowbuilder
š
workflow builder
View 26 Spaces
models
1
honey90/TenOS-Ko-28B
Text Generation
ā¢
27B
ā¢
Updated
Apr 26
ā¢
199
datasets
0
None public yet