🔄 In a Training Loop

Bojan Jakimovski

Shekswess

1 6 19

https://shekswess.github.io/

AI & ML interests

AWS Ambassador | Machine Learning & Applied Research Lead | College Professor

Recent Activity

liked a model 2 days ago

lokahq/Trinity-Mini-AI-Scientist

updated a collection 8 days ago

AI Scientist

updated a model 8 days ago

lokahq/Trinity-Mini-AI-Scientist

View all activity

Organizations

liked a model 2 days ago

lokahq/Trinity-Mini-AI-Scientist

Text Generation • Updated 8 days ago • 12 • 1

liked a Space 5 months ago

The Synthetic Data Playbook: Generating Trillions of the Finest Tokens

📝

269

Visualize synthetic‑data experiments as an interactive bookshelf

liked 2 models 5 months ago

Qwen/Qwen3-0.6B

Text Generation • 0.8B • Updated Jul 26, 2025 • 28.3M • • 1.47k

lokahq/Trinity-Mini-DrugProt-Think

Text Generation • Updated Jun 26 • 6 • 5

liked 2 datasets 5 months ago

math-ai/aime26

Viewer • Updated Feb 21 • 30 • 11.9k • 18

PleIAs/common_corpus

Viewer • Updated May 6 • 69.9k • 60.3k • 411

liked a Space 6 months ago

Sparsity Viz

📉

Explore and compare MoE model sparsity visualizations

liked a dataset 6 months ago

allenai/dolma3_mix-6T-1025-7B

Viewer • Updated Jan 15 • 1.35B • 190k • 56

liked a Space 6 months ago

Shekswess Trlm 135m

📊

Tiny reasoning language model

liked a Space 7 months ago

Falcon-H1-Tiny: A series of extremely small, yet powerful language models redefining capabilities at small scale

📝

Generate text using extremely small yet powerful language models

liked a dataset 7 months ago

reasoning-core/procedural-pile

Viewer • Updated about 21 hours ago • 30.2M • 3.01k • 8

liked a model 7 months ago

allura-forge/Llama-3.3-8B-Instruct

8B • Updated Dec 31, 2025 • 1.81k • 206

liked a dataset 7 months ago

OpenMed/agab-db

Viewer • Updated Dec 22, 2025 • 982k • 22 • 15

liked a dataset 8 months ago

allenai/dolma3_dolmino_pool

Updated Jan 5 • 24.8k • 8

liked a dataset 9 months ago

PleIAs/SYNTH

Viewer • Updated May 6 • 68M • 7.11k • 272

liked a Space 9 months ago

The Smol Training Playbook

📚

3.25k

The secrets to building world-class LLMs

liked a dataset 10 months ago

scottgeng00/olmo-3-preference-mix-deltas_reasoning-chosen_qwen4b-yolo_scottmix-DECON

Viewer • Updated Sep 25, 2025 • 294k • 53 • 1

liked 2 datasets 11 months ago

open-r1/Mixture-of-Thoughts

Viewer • Updated May 26, 2025 • 699k • 9.81k • 325

open-r1/SYNTHETIC-1-SFT-Data-Code_decontaminated

Viewer • Updated Feb 24, 2025 • 49.7k • 103 • 3

Bojan Jakimovski

AI & ML interests

Recent Activity

Organizations

Shekswess's activity

The Synthetic Data Playbook: Generating Trillions of the Finest Tokens

Sparsity Viz

Shekswess Trlm 135m

Falcon-H1-Tiny: A series of extremely small, yet powerful language models redefining capabilities at small scale

The Smol Training Playbook