Multi-agent Social Simulation + Efficient, Effective, and Stable alternative of RLHF. Code for the paper "Training Socially Aligned Language Models in Simulated Human Society".
Hello, thanks for your work!
I am reaching out to inquire about the GPU memory requirements for performing inference using your model. I have attempted to run the inference on a system with a NVIDIA RTX 3090 GPU, but unfortunately, I encountered issues related to insufficient GPU memory.
Could you please provide guidance on the GPU memory requirements for running inference with your model?
If the model does indeed require a significant amount of GPU memory, is it possible to utilize multi-GPU support to distribute the workload and alleviate the memory constraints? If so, could you provide some guidance or documentation on how to set this up?
Hello, thanks for your work! I am reaching out to inquire about the GPU memory requirements for performing inference using your model. I have attempted to run the inference on a system with a NVIDIA RTX 3090 GPU, but unfortunately, I encountered issues related to insufficient GPU memory. Could you please provide guidance on the GPU memory requirements for running inference with your model? If the model does indeed require a significant amount of GPU memory, is it possible to utilize multi-GPU support to distribute the workload and alleviate the memory constraints? If so, could you provide some guidance or documentation on how to set this up?