haffner/Darwin-4B-Genesis-heretic-GGUF
7B • Updated • 3.66k • 5
Jinki Jeong PRO
Anserwise
AI & ML interests
None yet
Recent Activity
liked a model about 6 hours ago
haffner/Darwin-4B-Genesis-heretic-GGUF liked a model about 6 hours ago
zeropointnine/Darwin-TTS-1.7B-Cross-Qwen3Tokenizer liked a model about 6 hours ago
FlatFootInternational/Darwin-9B-NEG-mlx-fp16Organizations
None yet
liked 8
models about 6 hours ago
zeropointnine/Darwin-TTS-1.7B-Cross-Qwen3Tokenizer
Text-to-Speech • 2B • Updated • 43 • 5
FlatFootInternational/Darwin-9B-NEG-mlx-fp16
Text Generation • 9B • Updated • 88 • 5
tomasmcm/Darwin-4B-Genesis-mlx-4Bit
Text Generation • 1B • Updated • 73 • 5
k0valik/Darwin-28B-Coder-IQ4_XS12.9GiB-GGUF
Text Generation • 27B • Updated • 715 • 5
hiiamboris/Darwin-28B-Coder-Q4_K_M-GGUF
Text Generation • 27B • Updated • 320 • 5
mradermacher/Darwin-28B-Coder-i1-GGUF
27B • Updated • 1.82k • 6
mradermacher/Darwin-28B-Coder-GGUF
27B • Updated • 1.73k • 7
liked a
model 3 days ago
reacted to SeaWolf-AI's post with 🔥 3 days ago
Post
4128
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.
👇
🔗 FINAL-Bench/Darwin-60B-DUO
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.
👇
🔗 FINAL-Bench/Darwin-60B-DUO
liked a
model 8 days ago
liked 6
models 9 days ago
atmzed/Darwin-4B-Genesis-mlx-fp16
Text Generation • 8B • Updated • 136 • 4
atmzed/Darwin-4B-David-mlx-fp16
Text Generation • 8B • Updated • 152 • 4
SeaWolf-AI/Darwin-gemma-4-E4B-it-x-Gemma-4-E4B-Claude-4-08292
Updated • 6
mradermacher/Darwin-28B-KOREA-GGUF
27B • Updated • 1.24k • 8
mradermacher/Darwin-28B-KR-Legal-GGUF
27B • Updated • 853 • 8
mradermacher/Darwin-28B-REASON-GGUF
27B • Updated • 1.5k • 10
liked 3
models 10 days ago