Running 552 552 Vision Arena (Testing VLMs side-by-side) πΌ Analyze images to detect and label objects
mlx-community/paligemma-3b-mix-448-8bit Image-Text-to-Text β’ 0.8B β’ Updated Oct 18, 2024 β’ 960 β’ 7
view article Article ColPali: Efficient Document Retrieval with Vision Language Models π By manu β’ Jul 5, 2024 β’ 284
mlx-community/Meta-Llama-3.1-70B-Instruct-8bit Text Generation β’ 20B β’ Updated Nov 26, 2024 β’ 54 β’ 4
SpreadsheetLLM: Encoding Spreadsheets for Large Language Models Paper β’ 2407.09025 β’ Published Jul 12, 2024 β’ 138