Open AlleyOop23 opened 6 months ago
Hi Alley, thank you for your question. For real-time application, I would recommond replacing the 7b model with a smaller language model and reducing the number of tokens predicted to speed up the inference process.
Hi,Thanks for your great work! I would like to inquire, based on your experience and research, do you believe it is feasible to deploy this work onto real vehicles? Particularly, considering our current computational resources are 2 A800 GPUs (80G). In this scenario, how long do you think it might take us to achieve this goal? Are there any key technical challenges or issues that need to be addressed?