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
19.2
TFLOPS
1
16
Tomoya Sawada
STomoya
Follow
0 followers
·
18 following
https://stomoya.github.io/
STomoya0110
STomoya
AI & ML interests
CV, illustration.
Recent Activity
liked
a Space
28 days ago
llm-jp/open-japanese-llm-leaderboard-v2
reacted
to
SeaWolf-AI
's
post
with 👍
about 1 month ago
Why This Matters — David Defeats Goliath MODEL: https://huggingface.co/FINAL-Bench/Darwin-4B-David SPACE: https://huggingface.co/spaces/FINAL-Bench/Darwin-4B-david We're releasing Darwin-4B-David, the first second-generation model in the Darwin Opus family. By evolving an already-evolved model, it achieves 85.0% on GPQA Diamond — surpassing its 58.6% original ancestor and even gemma-4-31B (84.3%) — with just 4.5B parameters. Second-Generation Evolution Most merges start from a base model and produce a single offspring. Darwin-4B-David breaks this pattern. The Father (Darwin-4B-Opus) was already evolved from gemma-4-E4B-it with Claude Opus reasoning distillation — a Gen-1 model. The Mother (DavidAU's DECKARD-Expresso-Universe) brings Unsloth deep tuning across 5 in-house datasets with thinking mode by default. Crossbreeding these two produced the first Gen-2 Darwin model. Darwin V6's Model MRI scanned both parents across all 42 layers, assigning independent optimal ratios per layer. The Mother's creativity and Korean language hotspot (Layer 22-25, weight 0.95) was maximally absorbed, while the Father's reasoning core (Layer 30-40, weight 0.48) was preserved. This is "Merge = Evolve" applied recursively — evolution of evolution. Benchmarks Darwin-4B-David scores 85.0% on GPQA Diamond (+26.4%p over original 58.6%), evaluated generatively with maj@8 (8 generations per question, majority vote), Epoch AI prompt format, thinking mode enabled, 50 sampled questions. On ARC-Challenge (25-shot, loglikelihood), both score 64.93% — expected, as loglikelihood doesn't capture thinking-mode reasoning differences. Why This Matters gemma-4-31B (30.7B) scores 84.3%. Darwin-4B-David surpasses it at 1/7th the size — no training, no RL, just 45 minutes of MRI-guided DARE-TIES on one H100. The name "David" honors Mother creator DavidAU and evokes David vs. Goliath.
liked
a dataset
2 months ago
nvidia/Nemotron-Cascade-2-SFT-Data
View all activity
Organizations
None yet
STomoya
's models
51
Sort: Recently updated
STomoya/efficientnet_b5.st_safebooru_1k
Image Classification
•
Updated
Dec 30, 2023
•
6
STomoya/efficientnet_b4.st_safebooru_1k
Image Classification
•
Updated
Dec 24, 2023
•
5
STomoya/efficientnet_b3.st_safebooru_1k
Image Classification
•
Updated
Dec 21, 2023
•
2
STomoya/efficientnet_b2.st_safebooru_1k
Image Classification
•
Updated
Dec 18, 2023
•
10
STomoya/efficientnet_b1.st_safebooru_1k
Image Classification
•
Updated
Dec 16, 2023
•
2
STomoya/efficientnet_b0.st_safebooru_1k
Image Classification
•
Updated
Dec 13, 2023
•
3
STomoya/convnext_base.st_safebooru_1k
Image Classification
•
Updated
Dec 11, 2023
•
6
STomoya/convnext_small.st_safebooru_1k
Image Classification
•
Updated
Dec 3, 2023
•
10
STomoya/convnext_tiny.st_safebooru_1k
Image Classification
•
Updated
Nov 25, 2023
•
8
STomoya/swin_base_patch4_window7_224.st_safebooru_1k
Image Classification
•
Updated
Nov 18, 2023
•
6
STomoya/swin_small_patch4_window7_224.st_safebooru_1k
Image Classification
•
Updated
Nov 9, 2023
•
6
STomoya/swin_tiny_patch4_window7_224.st_safebooru_1k
Image Classification
•
Updated
Nov 5, 2023
•
3
STomoya/vit_base_patch16_224.st_safebooru_1k
Image Classification
•
Updated
Oct 21, 2023
•
7
STomoya/vit_base_patch32_224.st_safebooru_1k
Image Classification
•
Updated
Oct 16, 2023
STomoya/vit_small_patch16_224.st_safebooru_1k
Image Classification
•
Updated
Oct 10, 2023
•
3
STomoya/vit_tiny_patch16_224.st_safebooru_1k
Image Classification
•
Updated
Oct 4, 2023
•
8
STomoya/resnet152.st_safebooru_1k
Image Classification
•
Updated
Sep 25, 2023
•
8
STomoya/resnet101.st_safebooru_1k
Image Classification
•
Updated
Sep 15, 2023
STomoya/resnet34.st_safebooru_1k
Image Classification
•
Updated
Sep 7, 2023
STomoya/resnet18.st_safebooru_1k
Image Classification
•
Updated
Aug 29, 2023
•
4
STomoya/resnet50.st_safebooru_1k
Image Classification
•
Updated
Aug 21, 2023
•
2
Previous
1
2
Next