pinned
Paused
Agents
54
FLUX VisionReply
š¦
FLUX, Image to Texto to Image, VLM
AIQ
aiqcamp
AI & ML interests
None yet
Recent Activity
reacted to SeaWolf-AI's post with š about 9 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 9 hours ago
FINAL-Bench/Darwin-60B-DUO reacted to SeaWolf-AI's post with š§ about 9 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-DUOOrganizations
