Walker Hughes

banachspace

AI & ML interests

AI/ML/RL

Organizations

None yet

models 4

banachspace/Qwen-0.5B-TTT-SFT-merged-TicTacToe-GRPO

Updated May 12, 2025

banachspace/Qwen-0.5B-TTT-SFT-merged

0.5B • Updated May 12, 2025 • 2

banachspace/Qwen-2.5-3B-Instruct-TicTacToe-GRPO

Updated May 11, 2025

banachspace/sanity-check

Text Generation • 0.5B • Updated Apr 19, 2025 • 8

datasets 1

banachspace/tic-tac-toe-wins-Qwen2.5-3B-Instruct

Viewer • Updated May 12, 2025 • 59 • 4 • 1