Henry Zhu

> Minigpt-4 is recently released, which is a multimodal model capable of handling both text and image inputs (similar to GPT-4, but this is built by Vicuna-13b and Blit2). From...

> This is surprisingly non trivial because pytorch models often have a variable computational graph defined at runtime based on conditional logic. Interesting. How does onnx handle variable computation graphs?

What version of windows and which models are you using?

Interesting, I haven't encountered that error before running minigpt4.cpp on windows. The python script does not have to be moved anywhere. As long as `minigpt.dll` is somewhere in the base...

Unfortunately, I'm not able to reproduce your results on my end... This is the output from my computer running windows 10. ``` (llm) C:\Users\maknee\Desktop\minigpt4.cpp\minigpt4>python minigpt4_library.py minigpt4-13B-f16.bin ggml-vicuna-13B-v0-q5_k.bin Loading minigpt4 shared...

Here is the uploaded result in [releases](https://github.com/Maknee/minigpt4.cpp/releases) Download the appropriate version for windows. The ones with `opencv` may require you to install [opencv](https://opencv.org/releases/).

> > Here is the uploaded result in [releases](https://github.com/Maknee/minigpt4.cpp/releases) > > Download the appropriate version for windows. The ones with `opencv` may require you to install [opencv](https://opencv.org/releases/). > > Thank...

Take a look at #15. Minigpt4 model is composed of two models (vision and text). The vision model does not support GPU usage, but the text model (vicuna) does. Try...

Thanks @felladrin. Interesting, I'll have to look into this with that PR in mind. Unfortunately, I haven't tested any other input besides english characters/words.

Interesting, authors released [MiniGPT-v2](https://github.com/Vision-CAIR/MiniGPT-4) as an improvement on minigpt4 I don't have time currently to update the repo to support MiniGPT-v2, but it should be relatively easy to add support...