Johnny Opcode
Johnny Opcode
I have no Git installed or on my path. I do have GitHub Desktop however. This directory does not exist on my PC nor the .crt file as well. C:\Program...
I wonder if we can squeeze a bit (pun) more performance using the Intel OneAPI Toolkits. https://www.intel.com/content/www/us/en/developer/tools/oneapi/toolkits.html#base-kit
How many different GGML BIN file headers are there floating around now? 3? 4? Asking for a friend..
Here is a good explanation if anyone is interested. https://neuralmagic.com/blog/sparsegpt-remove-100-billion-parameters-for-free/
Could we add proper checkpointing to the training loop in train.py? I've tried torch.save({}), but the model can't be opened with Netron for validation. I'm missing something obviously ..
I am grateful for the guidance. There is so much untapped potential in NN-Console through the use of plugins is this manner.
Ryzen AI series like https://www.amd.com/en/products/processors/consumer/ryzen-ai.html don't seem to have Linux support yet.
> Hi @htibosch, I think he means that the network interface of xilinx_ultrascale does not support multiple interface, which is introduced by TCP V4. > > Hello @JohnnyOpcode, We warmly...
With Colab Pro, the default TPU lib (and JAX) is now at 0.3.25. I jumped thru these hoops as well and have run with !pip install mesh-transformer-jax/ jax==0.3.15 tensorflow==2.8.2 chex==0.1.4...
> @JohnnyOpcode How did you infer with JAX 0.3.15? I think it runs only with 0.2.12. I was using Colab Pro (paid) and I experimented with different versions of the...