2 1 20

Alfaxad Eyembe

Alfaxad

https://alfaxad.github.io/

AI & ML interests

AI, Robotics

Recent Activity

upvoted an article 1 day ago

LLM Inference on Edge: A Fun and Easy Guide to run LLMs via React Native on your Phone!

liked a dataset 4 days ago

Skier8402/prompt-garden

new activity 4 days ago

Alfaxad/gemma2-27b-swahili-it:More datasets

View all activity

Organizations

None yet

Alfaxad's activity

upvoted an article 1 day ago

Article

LLM Inference on Edge: A Fun and Easy Guide to run LLMs via React Native on your Phone!

7 days ago

• 31

liked a dataset 4 days ago

Skier8402/prompt-garden

Viewer • Updated 2 days ago • 12 • 147 • 1

New activity in Alfaxad/gemma2-27b-swahili-it 4 days ago

More datasets

#1 opened 18 days ago by

Skier8402

liked a model 17 days ago

perplexity-ai/r1-1776

Text Generation • Updated 16 days ago • 55k • • 2.12k

liked a dataset 19 days ago

CohereForAI/Global-MMLU

Viewer • Updated 11 days ago • 487k • 14.2k • 111

reacted to Jaward's post with 🔥🧠❤️ 24 days ago

Post

3867

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