PKU-YuanGroup / MoE-LLaVA

Mixture-of-Experts for Large Vision-Language Models
https://arxiv.org/abs/2401.15947
Apache License 2.0
1.91k stars 121 forks source link

Method to Replicate Results from Huggingface Spaces #3

Closed hiroalchem closed 7 months ago

hiroalchem commented 7 months ago

I tried Huggingface Spaces and got wonderful results. Thank you. How can I replicate these results locally?

LinB203 commented 7 months ago

HF demo locally: https://github.com/PKU-YuanGroup/MoE-LLaVA?tab=readme-ov-file#-demo

CLI inference: https://github.com/PKU-YuanGroup/MoE-LLaVA?tab=readme-ov-file#cli-inference

Our API to use: https://github.com/PKU-YuanGroup/MoE-LLaVA?tab=readme-ov-file#-api

hiroalchem commented 7 months ago

@LinB203 Thank you for your response. There are several models shown, but which model is used in Huggingface Spaces?

LinB203 commented 7 months ago

@LinB203 Thank you for your response. There are several models shown, but which model is used in Huggingface Spaces?

Phi2.

hiroalchem commented 7 months ago

@LinB203 Thank you. I appreciate your response to my detailed questions.

LinB203 commented 7 months ago

You're welcome. Btw, if you like our project, please give us a star ⭐ on GitHub for latest update.

@LinB203 Thank you. I appreciate your response to my detailed questions.