Nik

I tested it today, both master and next branches and while serial port 0 works like a charm, serial port 1 only works for writing, it spits tons of garbage...

I was able to run dalle mega full on my laptop with 32GB ram by adding "jax.config.update('jax_platform_name', 'cpu')" after the imports in dalle_model.py it takes a veeeery long time to...

Hi niklas! how's the debugging going? I saw the 1.6 version and it looks cool so i wanted to ask if you tested it and if the random failing gan...

I followed all the steps carefully again, everything compiles but the demo fails with an undefined symbol error: `CUDA_VISIBLE_DEVICES=0 python demo.py --cuda --checkepoch=8 --checkpoint=132028` ```Traceback (most recent call last): File...

I tried many versions of torch (1.0.0, 1.0.1, 1.3.0) and rebuilt what's under lib many times but I couldn't manage to solve the environment's issues. The best scenario I got...

this are my system's specs if it can be useful in any way Kernel: 5.15.2-arch1-1 x86_64 bits: 64 compiler: gcc v: 11.1.0 Distro: Arch Linux cuda 11.5.0-1 cudnn 8.2.4.15-1

fixed with pr #87, rebuild the package by cloning this repo don't forget that the package name was changed from google to googleapi to solve naming conflicts

I was actually able to convert, quantize and load the model, but there is some tensor math to debug and modify but I have no 40GB gpu to debug the...

@klosax it is still too big! To debug the weights the model needs to be loaded in fp16 on the gpu. this means that a 24GB gpu is needed in...

I find it useful to run the pytorch model with many print statements here and there to check that ggml is giving me the same numbers so that I know...