view post Post 519 Most Powerful Vision Model CogVLM 2 now works amazing on Windows with new Triton pre-compiled wheels - 19 Examples - Locally tested with 4-bit quantization - Second example is really wild - Can be used for image captioning or any image vision taskThe APP and the installers : https://www.patreon.com/posts/120193330Check below screenshots to see how to use itCurrently the APP works amazing with 4-bit quantization very fastI am searching to lower VRAM usage even further with like adding CPU-Offloading and other stuff if possiblePreviously we were lacking Triton but it now works perfectMy installer installs into a Python 3.10 VENV completely isolated and cleanYou can see entire APP and installer source codeIf you get Triton error make sure to delete your Triton cache after installing the app like belowC:\Users\Furkan.tritonHugging Face repo with sample code : THUDM/cogvlm2-llama3-chat-19BGitHub repo : https://github.com/THUDM/CogVLM2Triton Windows : https://github.com/woct0rdho/triton-windows/releases See translation π₯ 3 3 π 2 2 π 1 1 β€οΈ 1 1 π€ 1 1 π 1 1 β 1 1 π§ 1 1 π 1 1 π€ 1 1 π€― 1 1 + Reply
Running on Zero 14 π·πΈπΉπΊποΈποΈποΈπ§ Audiocraft Demo for Jasco Model Music Stems Generation
librarian-bots/dataset_cards_with_metadata Viewer β’ Updated about 13 hours ago β’ 210k β’ 246 β’ 12
view post Post 1420 New smolagents example landed on Hugging Face cookbook π€ Learn how to create an inventory managing multi-agent system with smolagents, MongoDB and DeepSeek Chat π https://huggingface.co/learn/cookbook/mongodb_smolagents_multi_micro_agents See translation π₯ 7 7 π€ 3 3 π 2 2 + Reply