Commit 1afc044

authored

Adds Minesweeper game GPT-OSS-20B GRPO finetuning (#217)

1 parent 248a5e8 commit 1afc044Copy full SHA for 1afc044

3 files changed

+3418

-0

lines changed

nb
- gpt_oss_(20B)_Reinforcement_Learning_GRPO_Minesweeper_Game_BF16.ipynb
original_template
- gpt_oss_(20B)_Reinforcement_Learning_GRPO_Minesweeper_Game_BF16.ipynb
python_scripts
- gpt_oss_(20B)_Reinforcement_Learning_GRPO_Minesweeper_Game_BF16.py

3 files changed

+3418

-0

lines changed

Comments

(0)