Collection dedicated to all the datasets, checkpoints and any additional artifacts for Tiny Think
🔄 In a Training Loop
Bojan Jakimovski
Shekswess
AI & ML interests
AWS Ambassador | Machine Learning & Applied Research Lead | College Professor
Recent Activity
liked a model about 1 month ago
lokahq/Trinity-Mini-AI-Scientist updated a collection about 2 months ago
AI Scientist updated a model about 2 months ago
lokahq/Trinity-Mini-AI-ScientistOrganizations
models 31
Shekswess/tiny-think-dpo-math-stem-apo_zero-beta0_3-lr3e-6-e1-bs8
Text Generation • 0.1B • Updated • 11
Shekswess/tiny-think-dpo-math-stem-apo_zero-beta1-lr3e-6-e1-bs8
Text Generation • 0.1B • Updated • 9
Shekswess/tiny-think-dpo-math-stem-apo_zero-beta0_5-lr3e-6-e1-bs8
Text Generation • 0.1B • Updated • 10
Shekswess/tiny-think-dpo-math-stem-dpo-beta1-lr3e-6-e1-bs8
Text Generation • 0.1B • Updated • 10
Shekswess/tiny-think-dpo-math-stem-dpo-beta1-lr5e-6-e1-bs8
Text Generation • 0.1B • Updated • 7
Shekswess/tiny-think-dpo-math-stem-dpo-beta1-lr1e-6-e1-bs8
Text Generation • 0.1B • Updated • 7
Shekswess/tiny-think-dpo-math-stem-dpo-beta2-lr2e-6-e1-bs8
Text Generation • 0.1B • Updated • 7
Shekswess/tiny-think-dpo-math-stem-dpo-beta1-lr2e-6-e1-bs8
Text Generation • 0.1B • Updated • 7
Shekswess/tiny-think-dpo-math-stem-dpo-beta0-5-lr2e-6-e1-bs8
Text Generation • 0.1B • Updated • 13
Shekswess/tiny-think-sft-math-stem-loss-nll-bf16-e2-bs8
Text Generation • 0.1B • Updated • 6
datasets 38
Shekswess/OpenR1-Math-10k-GRPO
Viewer • Updated • 10k • 26
Shekswess/OpenR1-Math-10k-SFT
Viewer • Updated • 10k • 34
Shekswess/OpenR1-Math-10k-Raw
Viewer • Updated • 10k • 33
Shekswess/fineweb-edu-700m
Viewer • Updated • 681k • 77
Shekswess/tiny-think-sft-math-n-stem
Viewer • Updated • 29.1k • 22
Shekswess/tiny-think-dpo-math-n-stem
Viewer • Updated • 2.86k • 20
Shekswess/trlm-sft-stage-1-final-2
Viewer • Updated • 58k • 18 • 1
Shekswess/trlm-sft-stage-2-final-2
Viewer • Updated • 78k • 11 • 1
Shekswess/trlm-dpo-stage-3-final-2
Viewer • Updated • 50k • 15
Shekswess/customer-support
Viewer • Updated • 1k • 61 • 1