Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Log In
Sign Up
Open to Work
3
HAN
GKKWD
Follow
21world's profile picture
1 follower
Ā·
26 following
AI & ML interests
None yet
Recent Activity
replied
to
SeaWolf-AI
's
post
3 days ago
𧬠Darwin V6: Diagnostic-Guided Evolutionary Model Merging We are releasing Darwin-31B-Opus ā a reasoning-enhanced model merging Google's Gemma-4-31B-it and TeichAI's Claude Opus Distill using the Darwin V6 engine. Model: https://huggingface.co/FINAL-Bench/Darwin-31B-Opus Demo: https://huggingface.co/spaces/FINAL-Bench/Darwin-31B-Opus š¬ What Darwin V6 Does Conventional merging tools (mergekit, etc.) apply a single ratio to all tensors. Set ratio=0.5 and all 1,188 tensors blend identically, with no distinction between which tensors matter for reasoning versus coding. Darwin V6 diagnoses both parents at the tensor level before merging. It measures Shannon entropy, standard deviation, and L2 norm for every tensor, then passes 5 diagnostic probes (REASONING, CODE, MATH, KNOWLEDGE, LANGUAGE) through the model to determine layer-wise functional importance. Each of the 1,188 tensors receives an independent optimal ratio. combined = static(entropy/std/norm) x 0.4 + probe(cosine_distance) x 0.6 final_ratio = mri_ratio x mri_trust + genome_ratio x (1 - mri_trust) When one parent is overwhelmingly superior for a tensor (ratio < 0.15 or > 0.85), Darwin transplants it directly without interpolation. The mri_trust parameter itself is optimized by CMA-ES evolutionary search, so optimal transplant intensity is determined automatically. After merging, a Health Check compares the child against both parents layer-by-layer to detect interference or function loss. 𧬠Parent Models Father: google/gemma-4-31B-it Mother: TeichAI/gemma-4-31B-it-Claude-Opus-Distill 𧬠Results Compared under identical conditions (same 50 questions, same seed, greedy, thinking mode): Father: 60.0% (30/50) Darwin-31B-Opus: 66.0% (33/50) ā +10% relative improvement ARC-Challenge: 82.89% (loglikelihood, zero-shot, 200 questions) Optimal genome found by evolution: ffn_ratio=0.93 ā FFN layers strongly favor Mother (Claude Opus Distill) block_5 (L50-L59)=0.86 and more...
updated
a collection
3 days ago
GU GOL
liked
a model
3 days ago
google/gemma-4-26B-A4B-it
View all activity
Organizations
None yet
GKKWD
's activity
All
Models
Datasets
Spaces
Buckets
Papers
Collections
Community
Posts
Upvotes
Likes
Articles
liked
3 models
3 days ago
google/gemma-4-26B-A4B-it
Image-Text-to-Text
ā¢
27B
ā¢
Updated
1 day ago
ā¢
1.73M
ā¢
ā¢
610
google/gemma-4-31B-it
Image-Text-to-Text
ā¢
33B
ā¢
Updated
1 day ago
ā¢
2.24M
ā¢
ā¢
1.74k
google/madlad400-3b-mt
Translation
ā¢
3B
ā¢
Updated
Nov 27, 2023
ā¢
316k
ā¢
192