Brian PRO

bmoir

AI & ML interests

None yet

Recent Activity

upvoted a collection 7 days ago

Datasets

liked a dataset 7 days ago

Anthropic/EconomicIndex

reacted to Jaward's post with 👀 7 days ago

Finally here it is: a faster, custom, scalable GRPO trainer for smaller models with < 500M params, can train on 8gb ram cpu, also supports gpu for sanity sake (includes support for vllm + flash attention). Using smolLM2-135M/360M-instructs as ref & base models. Experience your own “aha” moment 🐳 on 8gb ram. Code: https://github.com/Jaykef/ai-algorithms/blob/main/smollm2_360M_135M_grpo_gsm8k.ipynb

View all activity

Organizations

bmoir's activity

upvoted a collection 7 days ago

Datasets

Collection

1 item • Updated 7 days ago • 1

liked a dataset 7 days ago

Anthropic/EconomicIndex

Viewer • Updated 14 days ago • 3.51k • 5.51k • 163

reacted to Jaward's post with 👀 7 days ago

Post

3798

Finally here it is: a faster, custom, scalable GRPO trainer for smaller models with < 500M params, can train on 8gb ram cpu, also supports gpu for sanity sake (includes support for vllm + flash attention). Using smolLM2-135M/360M-instructs as ref & base models. Experience your own “aha” moment 🐳 on 8gb ram.
Code: https://github.com/Jaykef/ai-algorithms/blob/main/smollm2_360M_135M_grpo_gsm8k.ipynb