🔄 In a Training Loop

swappy

rycerzes

1 47 42

https://rycerz.es

AI & ML interests

Deep learning, LLMs/VLMs, RL

Recent Activity

published a dataset about 8 hours ago

rycerzes/swe-rebench-v2.1-rl-isolated-1k

updated a dataset about 8 hours ago

rycerzes/swe-rebench-v2.1-rl-isolated-1k

upvoted an article 1 day ago

Decision Models in Hugging Face

View all activity

Organizations

liked a Space 6 days ago

The Ultimate MoE Training Handbook

🧩

557

A hands-on guide to training Mixture-of-Experts models

liked 2 models 6 days ago

ricursiveAI/Ripple-65B-Preview

65B • Updated 1 day ago • 7.11k • 509

nvidia/NVIDIA-Nemotron-Labs-Dory1.0-4B-NVFP4

Text Generation • 4B • Updated 12 days ago • 5.25k • 26

liked a model 9 days ago

deepseek-ai/DeepSeek-V4.1-Flash-1017

Image-Text-to-Text • 763B • Updated 1 day ago • 349k • • 5.5k

liked a dataset 10 days ago

rycerzes/beam-expert-atlas

Viewer • Updated 12 days ago • 285k • 718 • 1

liked a Space 12 days ago

Inside Beam

🔦

What Beam-1.0-501B says when one of its experts is pushed

liked 2 models 13 days ago

Qwen/Qwen3.8-27B

Image-Text-to-Text • 28B • Updated 5 days ago • 7.23M • • 19.6k

deepseek-ai/DeepSeek-V4-Flash-0731

Text Generation • 304B • Updated Aug 1 • 2.58M • • 4.1k

liked a Space 16 days ago

Alignment Hub

📚

Explore AI misalignment incident reports

liked 2 models 17 days ago

vllm-sr/d3-turbo-NVFP4

Zero-Shot Classification • 26B • Updated 17 days ago • 443 • 3

rycerzes/Qwen3.5-4B-Decision

Text Generation • 4B • Updated 22 days ago • 161 • 2

liked a model 20 days ago

HuggingFaceBio/Carbon-X

Text Generation • 15B • Updated 13 days ago • 4.94k • 303

liked a Space 20 days ago

Introducing Carbon-X

🧬

The best open model for DNA understanding

liked a model 20 days ago

reflection/Beam-1.0-501B-A23B

Text Generation • 501B • Updated 8 days ago • 13.3k • • 319

liked a model 21 days ago

RecursiveSI/flint

Text Generation • 40B • Updated 21 days ago • 49.6k • 1.39k

liked 2 models 24 days ago

unsloth/Qwen3.8-27B-NVFP4

20B • Updated Sep 8 • 1.96M • 538

nvidia/Qwen3.8-27B-NVFP4

Text Generation • 18B • Updated Sep 17 • 269k • 238

liked a model 25 days ago

google/embeddinggemma-2

Feature Extraction • 0.7B • Updated 15 days ago • 492k • 3.27k

liked a model about 1 month ago

Cloudflare/clef

Image-Text-to-Text • 27B • Updated 1 day ago • 72.4k • 2.35k

liked a Space about 1 month ago

MiMo RL Environment Explorer

🧭

Explore the MiMo-V2.6 RL environments and run rollouts