Magma
Magma copied to clipboard
microsoft
[CVPR 2025] Magma: A Foundation Model for Multimodal AI Agents
Hello, I am trying to install and run magma locally on a jetson device, particularly on Jetson IGX Orin. It has 64GB unified memory, ubuntu 20.04 installed and cuda 11.4,...
when installing [agents] parts, pip install paddle would report "ModuleNotFound: No module named "data",which signs "data" is required to install "paddle".I found the same at paddle's website. please fix it
Thank you for sharing your code. Although `sh lmms_eval_magma.sh` was executed, I was only able to evaluate textvqa benchmark despite I changed name of the argument eval_tasks. Could you please...
I want to use a pre-trained model for downstream tasks like robot manipulation. Are there any clear guidelines for this? Or do you know any useful projects on how to...
Hey team, I was wondering how the multiple-step reasoning works, like the video showed "what's the weather in Seattle". I read the demo of `ui_agent`, but cannot understand the reasoning...
**Issue Description:** I'd like to request a feature that integrates the Magma foundation model with Ollama and vLLM. This would significantly enhance the accessibility and performance of Magma for multimodal...
As the title says. Which GPU/RAM would be sufficient to run this model.
Hi Magma team, First, thank you for releasing such an impressive model with both multimodal understanding and action planning capabilities! I'm specifically interested in the model's ability to generate action...
Where in the code can I see the ToM (algorithm2) mentioned in the paper? I would like to see the detailed code of the ToM algorithm using CoTracker. And I...
