7 16 102

P.M.SALMAN KHAN

salmankhanpm

https://salmankhanpm.co

AI & ML interests

NLP - LLM - AI SAFETY

Recent Activity

upvoted a paper 3 days ago

TiDAR: Think in Diffusion, Talk in Autoregression

reacted to nroggendorff's post with 😔 5 days ago

Developing with ZeroGPU without a PRO account is painful. They give you so many requests at once, but then have like a 24 hour cooldown. I vote less requests in a batch, but then a shorter cooldown. or just less of a cooldown, but i understand if that is not allowed

liked a dataset 5 days ago

isaiahbjork/cot-logic-reasoning

View all activity

Organizations

upvoted a paper 3 days ago

TiDAR: Think in Diffusion, Talk in Autoregression

Paper • 2511.08923 • Published 8 days ago • 92

reacted to nroggendorff's post with 😔 5 days ago

Post

2270

Developing with ZeroGPU without a PRO account is painful. They give you so many requests at once, but then have like a 24 hour cooldown. I vote less requests in a batch, but then a shorter cooldown.

or just less of a cooldown, but i understand if that is not allowed

3 replies

liked a dataset 5 days ago

isaiahbjork/cot-logic-reasoning

Viewer • Updated Sep 6, 2024 • 10.5k • 68 • 15

upvoted an article 6 days ago

Article

⛳ Optimizer: What Does It Do and Why We Need It

8 days ago

•

reacted to onekq's post with 🔥 6 days ago

Post

2831

The reaction on the QAT post is beyond expectations so below is my optimizer post as promised. But I found that I had lots of explanation to do about optimizer itself. So this post is actually a historical recount. The Muon optimizer (used by Kimi) post (coming very soon) can only continue after this.

https://huggingface.co/blog/onekq/adam-optimizer

If you know Adam(W) optimizer already, you can just skip and sorry for the wait. Otherwise, it should be a useful read.