view post Post 2198 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 👍 4 4 + Reply
view post Post 1945 Timm ❤️ 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 🚀 10 10 + Reply
view post Post 1424 We are blessed with another iteration of Pali Gemma. Google launches PaliGemma 2. google/paligemma-2-release-67500e1e1dbfdd4dee27ba48 merve/paligemma2-vqav2 See translation 🤗 3 3 + Reply
view post Post 2953 Qwen/qwen25-66e81a666513e518adb90d9e Qwen/Qwen2.5-Coder-Artifacts Qwen/Qwen2.5-Coder-demo 🚀 7 7 😎 4 4 👍 2 2 + Reply
view post Post 1598 Cohere drops two new multilingual models! CohereForAI/aya-expanse-8b CohereForAI/aya-expanse-32bTry them out here CohereForAI/aya_expanse 👍 6 6 👀 2 2 + Reply
view post Post 1626 You can now use DoRA for your embedding layers!PR: https://github.com/huggingface/peft/pull/2006I have documented my journey of this specific PR in a blog post for everyone to read. The highlight of the PR was when the first author of DoRA reviewed my code.Blog Post: https://huggingface.co./blog/ariG23498/peft-doraHuge thanks to @BenjaminB for all the help I needed. 🔥 7 7 + Reply
G-SimCLR : Self-Supervised Contrastive Learning with Guided Projection via Pseudo Labelling Paper • 2009.12007 • Published Sep 25, 2020