Tayogo Lassora's picture

Tayogo Lassora

tayogo33
ยท

AI & ML interests

None yet

Recent Activity

updated a model 11 days ago
tayogo33/deepnude-ai
published a model 11 days ago
tayogo33/deepnude-ai
updated a model 11 days ago
tayogo33/top-deepnude-ai-websites
View all activity

Organizations

None yet

tayogo33's activity

published a model 11 days ago
reacted to Jaward's post with ๐Ÿ”ฅ 12 days ago
view post
Post
4937
made a few improvements on custom grpo trainer:
- added sequence similarity reward (seems to work)
- improved vllm support (5x inference speed)
- adjusted reward scores (this helped with format/accuracy)
- can now push to hf hub (already pushed mine lol: Jaward/smollm2_360m_grpo_gsm8k_reasoner)

Code: https://github.com/Jaykef/ai-algorithms/blob/main/smollm2_360M_135M_grpo_gsm8k.ipynb