Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Log In
Sign Up
Open to Collab
36
2
50
Troy Schultz
PRO
TroyDoesAI
Follow
fivehanz's profile picture
0a9bbf5d's profile picture
croqaz's profile picture
202 followers
Ā·
86 following
TroyDoesAI
troyandrewschultz
AI & ML interests
Contact Me ~ Open For Work ~ Contract or W2
Recent Activity
reacted
to
SeaWolf-AI
's
post
with š„
16 days ago
𧬠Darwin-35B-A3B-Opus ā The Child That Surpassed Both Parents What if a merged model could beat both its parents? We proved it can. Darwin-35B-A3B-Opus is a 35B MoE model (3B active) built with our Darwin V5 engine ā the first evolution system that CT-scans parent models before merging them. š¤ Model: https://huggingface.co/FINAL-Bench/Darwin-35B-A3B-Opus The result speaks for itself: GPQA Diamond 90.0%, versus Father (Qwen3.5-35B-A3B) at 84.2% and Mother (Claude 4.6 Opus Distilled) at 85.0%. That's +6.9% over Father and +5.9% over Mother. Not a tradeoff ā a genuine leap. Meanwhile, MMMLU sits at 85.0% (Father: 85.2%), multimodal is fully intact, and all 201 languages are preserved. How? Model MRI changed everything. Traditional merging is guesswork. Darwin V4 added evolution. Darwin V5 added X-ray vision. Model MRI scans each parent layer by layer and discovers: Mother's L34āL38 is the reasoning engine (peak cosine distance), 50ā65% of Mother's experts are dead (killed by text-only distillation), and Father is a healthy generalist with every expert alive. The prescription: transplant Mother's reasoning brain at L38 (90% weight), replace her dead experts with Father's living ones, and let Father's router handle the output layer. Reasoning went up. Versatility stayed intact. No tradeoff ā just evolution. 35B total, 3B active (MoE) Ā· GPQA Diamond 90.0% Ā· MMMLU 85.0% (201 languages) Ā· Multimodal Image & Video Ā· 262K native context Ā· 147.8 tok/s on H100 Ā· Runs on a single RTX 4090 (Q4) Ā· Apache 2.0 Darwin V5's full algorithm and technical details will be released alongside an upcoming paper. š Live Demo: https://huggingface.co/spaces/FINAL-Bench/Darwin-35B-A3B-Opus š FINAL Bench Leaderboard: https://huggingface.co/spaces/FINAL-Bench/Leaderboard š ALL Bench Leaderboard: https://huggingface.co/spaces/FINAL-Bench/all-bench-leaderboard Built by VIDRAFT Ā· Supported by the Korean Government GPU Support Program
new
activity
16 days ago
blascotobasco/Mistral-NeMoE-12B-16E:
Wow what a cool experiment
liked
a model
16 days ago
blascotobasco/Mistral-NeMoE-12B-16E
View all activity
Organizations
TroyDoesAI
's models
140
Sort:Ā Recently updated
TroyDoesAI/ShortCircuit-MoE
Text Generation
ā¢
25B
ā¢
Updated
Jul 27, 2024
ā¢
13
TroyDoesAI/ShortCircuit
Text Generation
ā¢
8B
ā¢
Updated
Jul 27, 2024
ā¢
4
TroyDoesAI/Unbiased-Personality
Text Generation
ā¢
8B
ā¢
Updated
Jul 26, 2024
TroyDoesAI/BlackSheep-RP-8B
Text Generation
ā¢
8B
ā¢
Updated
Jul 26, 2024
ā¢
3
TroyDoesAI/Llama-3.1-13B-Instruct
Text Generation
ā¢
13B
ā¢
Updated
Jul 25, 2024
ā¢
4
TroyDoesAI/Unhinged
Text Generation
ā¢
7B
ā¢
Updated
Jul 23, 2024
TroyDoesAI/Llama-3.1-8B-Instruct
Text Generation
ā¢
8B
ā¢
Updated
Jul 23, 2024
ā¢
581
ā¢
ā¢
3
TroyDoesAI/DirectionLess
Text Generation
ā¢
7B
ā¢
Updated
Jul 21, 2024
TroyDoesAI/BlackSheep-RP
Text Generation
ā¢
7B
ā¢
Updated
Jul 19, 2024
TroyDoesAI/BlackSheep-Writer
Text Generation
ā¢
7B
ā¢
Updated
Jul 19, 2024
ā¢
1
TroyDoesAI/Merge2
Text Generation
ā¢
8B
ā¢
Updated
Jul 14, 2024
TroyDoesAI/Merge1
Text Generation
ā¢
8B
ā¢
Updated
Jul 14, 2024
ā¢
3
TroyDoesAI/Abliterated-Merge-WIP-2
Text Generation
ā¢
8B
ā¢
Updated
Jul 14, 2024
ā¢
1
TroyDoesAI/Abliterated-Merge-WIP-3
Text Generation
ā¢
8B
ā¢
Updated
Jul 14, 2024
ā¢
1
TroyDoesAI/Abliterated-Merge-WIP
Text Generation
ā¢
8B
ā¢
Updated
Jul 14, 2024
ā¢
1
TroyDoesAI/BlackSheep-4B
Text Generation
ā¢
4B
ā¢
Updated
Jul 8, 2024
ā¢
18
ā¢
4
TroyDoesAI/BlackSheep-4k-Q6_K-RAM-5GB-gguf
4B
ā¢
Updated
Jul 7, 2024
ā¢
4
ā¢
1
TroyDoesAI/BlackSheep-4k-f16-RAM-9GB-gguf
4B
ā¢
Updated
Jul 7, 2024
ā¢
2
TroyDoesAI/BlackSheep-8k-Q6_K-RAM-7GB-gguf
4B
ā¢
Updated
Jul 7, 2024
TroyDoesAI/BlackSheep-8k-f16-RAM-11GB-gguf
4B
ā¢
Updated
Jul 7, 2024
ā¢
2
TroyDoesAI/BlackSheep-16k-Q6_K-RAM-10.3GB-gguf
4B
ā¢
Updated
Jul 7, 2024
ā¢
2
TroyDoesAI/BlackSheep-16k-f16-RAM-14.5GB-gguf
4B
ā¢
Updated
Jul 7, 2024
ā¢
2
ā¢
1
TroyDoesAI/BlackSheep-32k-Q6_K-gguf
4B
ā¢
Updated
Jul 7, 2024
ā¢
22
TroyDoesAI/BlackSheep-32k-f16-gguf
4B
ā¢
Updated
Jul 7, 2024
ā¢
1
TroyDoesAI/Mini
Text Generation
ā¢
4B
ā¢
Updated
Jul 6, 2024
TroyDoesAI/Mini_Llama-3B-Base
Text Generation
ā¢
4B
ā¢
Updated
Jul 5, 2024
ā¢
2
TroyDoesAI/Mini-Llama
Text Generation
ā¢
4B
ā¢
Updated
Jul 2, 2024
TroyDoesAI/JailbrokeAI
Text Generation
ā¢
15B
ā¢
Updated
Jun 6, 2024
ā¢
9
ā¢
2
TroyDoesAI/TroyDoesAGI
Text Generation
ā¢
15B
ā¢
Updated
Jun 5, 2024
ā¢
9
TroyDoesAI/RAG-15B
Text Generation
ā¢
15B
ā¢
Updated
Jun 3, 2024
Previous
1
2
3
4
5
Next