Kory Watson
Kory Watson
Phi3.5 is now in active development on our end. Stay tuned.
Phi3.5 has been available for a while now, apologies we didn't get to this issue sooner.
Thanks for the feature request. We're aware of this and are working on some sample scripts that will allow you to run models locally on the X Elite.
See our Stable Diffusion demo here: https://github.com/quic/ai-hub-apps/tree/main/apps/windows/python
This application was replaced by https://github.com/quic/ai-hub-apps/tree/main/apps/android/ImageClassification. Extra care was taken in this app to replicate the performance AI Hub reports. Let us know (open an issue on the quic/ai-hub-apps repository)...
Performance for ViT has been improved to 17ms in the newest version of AI Hub Models (https://aihub.qualcomm.com/jobs/j56y4rd0p). Must faster than even the expected behavior in the opening issue :)
Hello, You can call from_pretrained() on the model to download that weight file and instantiate the pyTorch model automatically. Closing this out due to inactivity. Please reopen the issue or...
Folks, thanks for the report. We investigated internally. This model expects Infrared image grayscale input, stacked from 1 to 3 channels. The problem you're facing is you're passing an RGB...
This has been fixed.
We now have a quantization tutorial available for Llama: https://github.com/quic/ai-hub-models/blob/main/tutorials/llm/quantize_llama3.md This will be expanded to Qwen & beyond in the next few months. Closing this out due to inactivity. Please...