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
2
7
Minseo Kim
MinseoKim-03
Follow
honey90's profile picture
mayafree's profile picture
SeaWolf-AI's profile picture
4 followers
ยท
8 following
AI & ML interests
None yet
Recent Activity
reacted
to
SeaWolf-AI
's
post
with ๐ฅ
11 days ago
Darwin-60B-DUO: Two SOTAs, One Endpoint โ 88.38% on GPQA Diamond ๐ 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 โ 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 โ 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 โ AWAXIS, English/STEM โ Darwin (single-backend, ~70% of traffic at 1ร cost). When a Korean answer needs rigorous English reasoning, split_refine fires โ Darwin drafts, AWAXIS polishes; MCQ/short-answer runs both with self-consistency + cross-verify. Net effective cost: only ~1.3ร 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 โ 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. ๐ ๐ https://huggingface.co/FINAL-Bench/Darwin-60B-DUO
liked
a model
11 days ago
FINAL-Bench/Darwin-60B-DUO
liked
a model
19 days ago
VIDraft/lastbrain-engine
View all activity
Organizations
None yet
MinseoKim-03
's activity
All
Models
Datasets
Spaces
Buckets
Papers
Collections
Community
Posts
Upvotes
Likes
Articles
liked
a model
11 days ago
FINAL-Bench/Darwin-60B-DUO
Text Generation
โข
Updated
5 days ago
โข
673
โข
32
liked
2 models
19 days ago
VIDraft/lastbrain-engine
Any-to-Any
โข
Updated
Apr 18
โข
37
โข
7
Anserwise/AWAXIS-KR-31B
Image-Text-to-Text
โข
52B
โข
Updated
3 days ago
โข
262
โข
3
liked
a model
22 days ago
FINAL-Bench/Darwin-28B-REASON
Text Generation
โข
27B
โข
Updated
5 days ago
โข
795
โข
30
liked
3 models
about 1 month ago
FINAL-Bench/Darwin-28B-Opus
Text Generation
โข
28B
โข
Updated
5 days ago
โข
381
โข
31
FINAL-Bench/Darwin-9B-NEG
Text Generation
โข
10B
โข
Updated
5 days ago
โข
584
โข
47
FINAL-Bench/Darwin-36B-Opus
Text Generation
โข
35B
โข
Updated
5 days ago
โข
1.93k
โข
71