QuangHyperGAI

Results 3 comments of QuangHyperGAI

We are working on a demo platform and will announce it soon with the future release. Thank you for your understanding!

You can quantize our model at run time using bitsandbyte. Please refer to the steps below. 1. Install bitsandbyte ``` pip install bitsandbyte ``` 2. Modify the ```vlmeval/vlm/hpt.pt``` file as...

The demo works fine on my end, can you please share with me your environment setup such as transformer and pytorch version?