Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Website
Tasks
HuggingChat
Collections
Languages
Organizations
Community
Blog
Posts
Daily Papers
Hardware
Learn
Discord
Forum
GitHub
Solutions
Team & Enterprise
Hugging Face PRO
Enterprise Support
Inference Providers
Inference Endpoints
Storage Buckets
Log In
Sign Up
ποΈ
On Vacation
Michael @ The Kozu Group
Michael-Kozu
2
1
Follow
lwledmund's profile picture
John6666's profile picture
rpfluger's profile picture
7 followers
Β·
10 following
https://ai.kozugroup.com
AI & ML interests
None yet
Recent Activity
liked
a model
11 days ago
convaiinnovations/laya
reacted
to
SeaWolf-AI
's
post
with π
12 days ago
𧬠Darwin-180B-RSI β an AI that learns from itself and knows when it's right π https://huggingface.co/FINAL-Bench/Darwin-180B-RSI 𧬠Darwin β crossbreed and evolve the parent Darwin diagnoses strong parent models like an MRI, inherits only their best parts, and evolves the weak spots β producing a child stronger than its parents. Father model: Qwen3.8-Flash-Next (180B MoE). π§ Rewired paths πΉ 12 full-attention layers Β· πΉ 36 linear-attention layers Β· πΉ 48 shared-expert layers β precision-strengthened π 512 routed experts Β· router Β· vision encoder β untouched β Only 0.02% of the weights changed. π RSI Γ ποΈ ZTC RSI (recursive self-improvement): solve β verify against real answers β learn only the correct reasoning β repeat. ZTC (Zero-Token Confidence): reads the model's internal state once, before answering, and returns the probability the answer is right β zero extra tokens. Returns answer + confidence as JSON. {"answer": "...", "confidence": 0.97, "truncated": false} β¨ Synergy: ZTC finds where the model wavers β RSI learns exactly there β confidence gets sharper. Low confidence = stop, so agents don't act on wrong answers. β‘ Same accuracy, 11% shorter reasoning β faster and cheaper. π https://arxiv.org/abs/2605.14386 π€ https://huggingface.co/FINAL-Bench/Darwin-180B-RSI ποΈ https://huggingface.co/collections/FINAL-Bench/ztc-models-jev-ecosystems π The result β #1 on five Hugging Face official leaderboards π₯ AIME 2026 100% (first perfect score on the board) π₯ HMMT Feb 2026 100% (first perfect score on the board) π₯ GPQA Diamond 94.44% π₯ MMLU-Pro 88.12% π₯ MMMU-Pro 79.48% π 131K-token thinking budget Β· bf16 Β· samples per benchmark listed on the model card. π #Darwin #RSI #ZTC #AIME #HMMT #GPQA #MMLUPro #MMMUPro #OpenSource
new
activity
2 months ago
mradermacher/model_requests:
Quant Request: Michael-Kozu/Deimos-R1, Michael-Kozu/Ganymede-A1, Michael-Kozu/Europa-B1
View all activity
Organizations
models
6
Sort:Β Recently updated
Michael-Kozu/Deimos-R1
Text Generation
β’
5B
β’
Updated
Jul 26
β’
73
β’
2
Michael-Kozu/Ganymede-A1
Text Generation
β’
27B
β’
Updated
Jul 26
β’
1.58k
β’
1
Michael-Kozu/Europa-B1
Text Generation
β’
9B
β’
Updated
Jul 26
β’
25
β’
1
Michael-Kozu/Kuiper-R1
Text Generation
β’
9B
β’
Updated
Jul 18
β’
16
β’
1
Michael-Kozu/Deimos-A4
Text Generation
β’
5B
β’
Updated
Jul 18
β’
29
β’
3
Michael-Kozu/Deimos-A1
Text Generation
β’
5B
β’
Updated
Jul 18
β’
33
β’
2
datasets
3
Sort:Β Recently updated
Michael-Kozu/kozu-reasoning-v1.1
Viewer
β’
Updated
Jul 22
β’
11k
β’
30
Michael-Kozu/Quark
Preview
β’
Updated
Jul 18
β’
37
Michael-Kozu/system-prompt-reasoning-traces
Viewer
β’
Updated
Apr 22
β’
1.45k
β’
72
β’
1