🔄 In a Training Loop

Arthur EDMOND

Shumatsurontek

5 55 114

Shumatsurontek
arthur-edmond-7155b8187

AI & ML interests

LLM & Computer Vision

Organizations

Collections 3

View 3 collections

spaces 2

Qwen3 8B SFT

🚀

LFM2 2.6B SFT

🚀

models 14

datasets 2

Shumatsurontek/Synth-QA-Github

Viewer • Updated May 27 • 100 • 7

Shumatsurontek/neo-sql-reasoning-combined

Viewer • Updated Apr 6 • 17k • 31

Arthur EDMOND

AI & ML interests

Organizations

Collections 3

Can One Domain Help Others? A Data-Centric Study on Multi-Domain Reasoning via Reinforcement Learning

Test-Time Scaling with Reflective Generative Model

Can One Domain Help Others? A Data-Centric Study on Multi-Domain Reasoning via Reinforcement Learning

Test-Time Scaling with Reflective Generative Model

spaces 2

Qwen3 8B SFT

LFM2 2.6B SFT

models 14

Shumatsurontek/Qwen3.5-4B-neo

Shumatsurontek/LFM2-2.6-Exp-hermes

Shumatsurontek/LFM2-2.6B-Exp-hermes

Shumatsurontek/Qwen3-8B-SFT

Shumatsurontek/LFM2-2.6B-SFT-merged

Shumatsurontek/LFM2-2.6B-SFT

Shumatsurontek/alyssagpt

Shumatsurontek/lora_model

Shumatsurontek/granite-4.0-h-micro-Toucan-120k

Shumatsurontek/neo_planner_qwen3_8b

datasets 2

Shumatsurontek/Synth-QA-Github

Shumatsurontek/neo-sql-reasoning-combined

Arthur EDMOND

AI & ML interests

Organizations

Collections 3

spaces 2 Sort: Recently updated

Qwen3 8B SFT

LFM2 2.6B SFT

models 14 Sort: Recently updated

datasets 2 Sort: Recently updated

spaces 2

models 14

datasets 2