Bojan Jakimovski's picture

In a Training Loop 🔄

1 5 10

Bojan Jakimovski

Shekswess

·

https://shekswess.github.io/

AI & ML interests

AWS Ambassador | Machine Learning Lead | College Professor | GenAI | MLOps

Recent Activity

updated a model 15 minutes ago

Shekswess/tiny-think-sft-math-stem-loss-nll-bf16-lr5e-5-e2-bs8

published a model about 1 hour ago

Shekswess/tiny-think-sft-math-stem-loss-nll-bf16-lr5e-5-e2-bs8

updated a model about 1 hour ago

Shekswess/tiny-think-sft-math-stem-loss-nll-bf16-lr2e-5-e2-bs8

View all activity

Organizations

Collections 6

View 6 collections

models 22

Shekswess/tiny-think-sft-math-stem-loss-nll-bf16-lr5e-5-e2-bs8

Text Generation • 0.1B • Updated 15 minutes ago

Shekswess/tiny-think-sft-math-stem-loss-nll-bf16-lr2e-5-e2-bs8

Text Generation • 0.1B • Updated about 1 hour ago

Shekswess/tiny-think-sft-math-stem-loss-dft-bf16-lr5e-5-e2-bs8

Text Generation • 0.1B • Updated about 18 hours ago • 57

Shekswess/tiny-think-sft-math-stem-loss-dft-bf16-lr2e-5-e2-bs8

Text Generation • 0.1B • Updated 1 day ago • 52

Shekswess/tiny-think-sft-math-stem-loss-nll-bf16-e3-bs8

Text Generation • 0.1B • Updated 2 days ago • 187

Shekswess/tiny-think-sft-math-stem-loss-dft-bf16-e3-bs8

Text Generation • 0.1B • Updated 3 days ago • 264

Shekswess/tiny-think-sft-math-stem-loss-dft-bf16-e3-bs8-more-stem

Text Generation • 0.1B • Updated 3 days ago • 144

Shekswess/tiny-think-sft-math-stem-loss-nll-bf16-e3-bs8-more-stem

Text Generation • 0.1B • Updated 3 days ago • 71

Shekswess/trlm-stage-1-sft-final-2

Text Generation • 0.1B • Updated Nov 6, 2025 • 2 • 1

Shekswess/trlm-stage-2-sft-final-2

Text Generation • 0.1B • Updated Nov 6, 2025 • 11 • 1

datasets 42

Shekswess/tiny-think-dpo

Viewer • Updated 3 days ago • 10.5k • 54

Shekswess/tiny-think-dpo-math-n-stem

Viewer • Updated 3 days ago • 2.86k • 67

Shekswess/tiny-think-sft

Viewer • Updated 3 days ago • 111k • 80

Shekswess/tiny-think-sft-math-n-stem

Viewer • Updated 3 days ago • 29.1k • 66

Shekswess/tiny-think-dpo-code

Viewer • Updated 7 days ago • 2.71k • 47

Shekswess/tiny-think-dpo-chat-n-instruct

Viewer • Updated 7 days ago • 4.91k • 47

Shekswess/tiny-think-sft-code

Viewer • Updated 7 days ago • 30.2k • 49

Shekswess/tiny-think-sft-chat-n-instruct

Viewer • Updated 7 days ago • 52k • 63

Shekswess/gsm8k_think_sft

Viewer • Updated 7 days ago • 7.47k • 34

Shekswess/tlm-dolma-3-ablation

Viewer • Updated Dec 9, 2025 • 1.53M • 14

View 42 datasets