Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
24130001930.4
TFLOPS
3
3
9
Underscore
underscore2
Follow
trentmkelly's profile picture
1 follower
·
5 following
AI & ML interests
cooming
Recent Activity
updated
a model
5 days ago
underscore2/modernbert_large_slop_writing
published
a model
5 days ago
underscore2/modernbert_large_slop_writing
reacted
to
codelion
's
post
with 🔥
5 days ago
🧬 We just published our comprehensive analysis of OpenEvolve - an open-source evolutionary coding agent that automatically optimizes algorithms using LLMs! Our key findings from 29 experiments across 10 models: - Gemini Flash 2.5 achieved 2.04x speedup across 30 benchmark tasks - Open models like Gemma 3 27B (1.63x) and Qwen3-Coder 480B (1.41x) rivaled proprietary models - The system discovered entirely new algorithms - not just code optimizations! - One task evolved from DFS to BFS to Union-Find approaches - Specialized coding models outperformed much larger general models 200 iterations beat 100 iterations by 24% - Ensembles surprisingly failed due to conflicting optimization strategies Most fascinating: watching models evolve code step-by-step, like transforming matrix operations from basic eigendecomposition to vectorized one-liners with 32x speedup. Our systematic experimental approach reveals that open-source evolutionary coding is becoming seriously competitive with proprietary solutions. We tested everything from temperature settings to evolution strategies to find optimal configurations. This research shows automated code optimization is ready for real-world applications. The methodology we developed can guide anyone building evolutionary coding systems. Full paper with code examples, detailed methodology, and all experimental results: https://huggingface.co/blog/driaforall/towards-open-evolutionary-agents What optimization challenges could benefit from evolutionary approaches in your work?
View all activity
Organizations
None yet
underscore2
's models
65
Sort:Â Recently updated
underscore2/modernbert_large_slop_writing
Text Classification
•
0.4B
•
Updated
5 days ago
•
3
underscore2/qwen2.5-3b-grpo-diversity-v3
3B
•
Updated
5 days ago
underscore2/qwen2.5-7b-grpo-diversity-v2
8B
•
Updated
15 days ago
underscore2/qwen2.5-7b-grpo-diversity
8B
•
Updated
16 days ago
underscore2/llama3-8b-bluesky-engagement-kto
Updated
17 days ago
underscore2/llama3-8b-bluesky-tpot-v19
8B
•
Updated
18 days ago
underscore2/llama3-8b-bluesky-tpot-v18
8B
•
Updated
Jul 8
underscore2/llama3-8b-bluesky-tpot-v16
8B
•
Updated
Jul 5
underscore2/llama3-8b-bluesky-tpot-v15
8B
•
Updated
Jul 5
underscore2/llama3-8b-bluesky-tpot-v13
8B
•
Updated
Jul 5
underscore2/llama3-8b-bluesky-tpot-v12
8B
•
Updated
Jul 5
underscore2/llama3-8b-bluesky-tpot-v11
8B
•
Updated
Jul 4
underscore2/llama3-8b-bluesky-tpot-v10
8B
•
Updated
Jun 28
underscore2/llama3-8b-bluesky-tpot-v7
Updated
Jun 23
underscore2/llama3-8b-bluesky-tpot-v6
Updated
Jun 22
underscore2/llama3-8b-bluesky-tpot-v5
Updated
Jun 22
underscore2/qwen-grpo-bluesky-maxxing
Text Generation
•
3B
•
Updated
Jun 19
•
4
•
1
underscore2/qwen-grpo-anti-slop-2
Text Generation
•
3B
•
Updated
Jun 18
•
5
underscore2/qwen-grpo-conspiracy-max3
Text Generation
•
3B
•
Updated
Jun 18
•
14
underscore2/modernbert_large_likes_predictor
Text Classification
•
0.4B
•
Updated
Jun 14
•
5
underscore2/llama3-8b-bluesky-tpot-v4
Updated
Jun 9
underscore2/llama3-8b-bluesky-tpot-v3
Updated
Jun 8
underscore2/llama3-8b-bluesky-tpot-v2
Updated
Jun 8
underscore2/llama3-8b-bluesky-tpot
Updated
Jun 7
underscore2/modernbert_large_slop_classifier_v3
Text Classification
•
0.4B
•
Updated
Jun 4
•
4
underscore2/modernbert_base_slop_classifier_v2
Text Classification
•
0.1B
•
Updated
Jun 4
•
2
underscore2/modernbert_base_slop_classifier
Text Classification
•
0.1B
•
Updated
Jun 1
•
4
underscore2/modernbert_agree_classifier
Text Classification
•
0.4B
•
Updated
May 21
•
4
underscore2/llama3-8b-ols
Updated
May 12
underscore2/llama3-8b-schizophrenia-2
Updated
May 10
Previous
1
2
3
Next