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
4
5
350
AIQ
aiqcamp
Follow
arpitgoyal's profile picture
namht94's profile picture
immunobiotech's profile picture
106 followers
·
57 following
aitechtree
AI & ML interests
None yet
Recent Activity
liked
a model
3 days ago
JGOS-Model/JGOS-31B-Citizen
reacted
to
SeaWolf-AI
's
post
with 👍
14 days ago
Darwin-60B-DUO: Two SOTAs, One Endpoint — 88.38% on GPQA Diamond 🚀 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 — 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 — 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 → AWAXIS, English/STEM → Darwin (single-backend, ~70% of traffic at 1× cost). When a Korean answer needs rigorous English reasoning, split_refine fires — Darwin drafts, AWAXIS polishes; MCQ/short-answer runs both with self-consistency + cross-verify. Net effective cost: only ~1.3× 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 — 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. 👇 🔗 https://huggingface.co/FINAL-Bench/Darwin-60B-DUO
liked
a model
14 days ago
FINAL-Bench/Darwin-60B-DUO
View all activity
Organizations
aiqcamp
's activity
All
Models
Datasets
Spaces
Buckets
Papers
Collections
Community
Posts
Upvotes
Likes
Articles
liked
a model
3 days ago
JGOS-Model/JGOS-31B-Citizen
Image-Text-to-Text
•
31B
•
Updated
3 days ago
•
195
•
18
liked
a model
14 days ago
FINAL-Bench/Darwin-60B-DUO
Text Generation
•
Updated
8 days ago
•
679
•
31
liked
15 models
20 days ago
mradermacher/Darwin-9B-KOREA-i1-GGUF
9B
•
Updated
26 days ago
•
3.05k
•
9
mradermacher/Darwin-28B-REASON-i1-GGUF
27B
•
Updated
23 days ago
•
2.08k
•
12
mradermacher/Darwin-4B-Genesis-GGUF
8B
•
Updated
24 days ago
•
1.28k
•
16
bartowski/FINAL-Bench_Darwin-35B-A3B-Opus-GGUF
Image-Text-to-Text
•
35B
•
Updated
Apr 1
•
4.02k
•
27
mradermacher/Darwin-28B-Opus-i1-GGUF
27B
•
Updated
May 8
•
3.14k
•
11
mradermacher/Darwin-9B-NEG-i1-GGUF
9B
•
Updated
May 7
•
3.46k
•
11
mradermacher/Darwin-4B-Genesis-i1-GGUF
8B
•
Updated
24 days ago
•
2.95k
•
10
mradermacher/Darwin-36B-Opus-ABLITERATED-HERETIC-i1-GGUF
35B
•
Updated
Apr 30
•
1.41k
•
12
mradermacher/Darwin-28B-FUSION-v1-i1-GGUF
27B
•
Updated
27 days ago
•
11.1k
•
9
mradermacher/Darwin-36B-Opus-i1-GGUF
35B
•
Updated
25 days ago
•
16.5k
•
11
FINAL-Bench/Darwin-2B-Opus-LoRA
Updated
27 days ago
•
31
•
11
ansulev/Darwin-9B-NEG
Text Generation
•
10B
•
Updated
23 days ago
•
390k
•
15
FINAL-Bench/Darwin-28B-Coder
Text Generation
•
27B
•
Updated
22 days ago
•
890
•
19
mudler/Darwin-36B-Opus-APEX-GGUF
35B
•
Updated
27 days ago
•
8.3k
•
23
FINAL-Bench/Darwin-28B-REASON
Text Generation
•
27B
•
Updated
8 days ago
•
646
•
33
liked
a Space
25 days ago
Running
Agents
Featured
23
Darwin 9B NEG
🧬
23
Darwin-9B-NEG reasoning model — API-served chat demo
liked
2 models
about 1 month ago
FINAL-Bench/Darwin-36B-Opus
Text Generation
•
35B
•
Updated
8 days ago
•
1.63k
•
73
FINAL-Bench/Darwin-9B-NEG
Text Generation
•
10B
•
Updated
8 days ago
•
544
•
47
Load more