AI & ML interests

None defined yet.

Recent Activity

ariG23498Ā 
posted an update 2 months ago
view post
Post
1030
New post is live!

This time we cover some major updates to transformers.

šŸ¤—
  • 1 reply
Ā·
ariG23498Ā 
posted an update 4 months ago
ariG23498Ā 
posted an update 6 months ago
view post
Post
1732
🚨 Implement KV Cache from scratch in pure PyTorch. 🚨

We have documented all of our learning while implementing KV Cache to nanoVLM. Joint work with @kashif @lusxvr @andito @pcuenq

Blog: hf.co/blog/kv-cache
  • 1 reply
Ā·
ariG23498Ā 
posted an update 10 months ago
view post
Post
2849
Tried my hand at simplifying the derivations of Direct Preference Optimization.

I cover how one can reformulate RLHF into DPO. The idea of implicit reward modeling is chef's kiss.

Blog: https://huggingface.co/blog/ariG23498/rlhf-to-dpo
ariG23498Ā 
posted an update 10 months ago
ariG23498Ā 
posted an update 12 months ago
ariG23498Ā 
posted an update about 1 year ago
ariG23498Ā 
posted an update about 1 year ago
ariG23498Ā 
updated a Space almost 2 years ago