view post Post 1215 New post is live!This time we cover some major updates to transformers.π€ See translation 1 reply Β· π€ 1 1 + Reply
view post Post 877 I have always advocated for writing techinical stories without using LLMs.The following one page editorial really drives the point home.https://www.nature.com/articles/s44222-025-00323-4 See translation π§ 3 3 + Reply
view post Post 1738 π¨ Implement KV Cache from scratch in pure PyTorch. π¨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 See translation 1 reply Β· π 2 2 + Reply
view post Post 2852 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 See translation π 4 4 + Reply
view post Post 2075 Timm β€οΈ TransformersWtih the latest version of transformers you can now use any timm model with the familiar transformers API.Blog Post: https://huggingface.co/blog/timm-transformersRepository with examples: https://github.com/ariG23498/timm-wrapper-examplesCollection: ariG23498/timmwrapper-6777b85f1e8d085d3f1374a1 See translation π 10 10 + Reply
view post Post 1467 We are blessed with another iteration of Pali Gemma. Google launches PaliGemma 2. google/paligemma-2-release-67500e1e1dbfdd4dee27ba48 merve/paligemma2-vqav2 See translation π€ 3 3 + Reply
pyimagesearch/brain-tumor-object-detection-paligemma Viewer β’ Updated Dec 5, 2024 β’ 1.1k β’ 17 β’ 1
pyimagesearch/construction-safety-object-detection-paligemma Viewer β’ Updated Dec 5, 2024 β’ 398 β’ 16 β’ 4