AI & ML interests

Deep Learning, Computer Vision, Machine Learning

ariG23498Β 
posted an update about 1 month ago
view post
Post
1567
🚨 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
Β·
ariG23498Β 
posted an update 6 months ago
view post
Post
2833
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
ariG23498Β 
posted an update 6 months ago
ariG23498Β 
posted an update 7 months ago
ariG23498Β 
posted an update 8 months ago