Nicholas

Is it even possible to utilize 2 GPUs without messing a lot with the code?

As soon as I start the usage code shown in the Readme, I just get a 500 Internal Server Error when visiting https://localhost:5000/oauth/management

pymupdf and llama_index

1

The example at https://llamahub.ai/l/file-pymu_pdf is broken Here's my slightly modified code: ``` from pathlib import Path from llama_index import GPTVectorStoreIndex, download_loader PyMuPDFReader = download_loader("PyMuPDFReader") loader = PyMuPDFReader() documents = loader.load(file=Path('./paper.pdf'),...

G1on/G1xon

26

Does this work with G1on/G1xon and, in general, with pedals that use the ZDL format? Thanks

OK, I'm looking at the mxnet_backend.py and especially on how gradients are calculated since I'm developing a custom optimizer. However K.gradients do not implement any kind of call to mx:...

Compilation

2

This repo seriously needs a Makefile

Difference between nodes and entities

2

### Describe the issue I'm having some difficulty to understand what is the difference between generated nodes and entities. In believe that these two coincide, but for some datasets nodes...

### Do you need to file an issue? - [X] I have searched the existing issues and this feature is not already filed. - [ ] My model is hosted...

Support for Intel based Macs

6

Any chance to also support Intel based Macs at some point? I understand that Linux support is cuda based but those were pretty capable computational machines that now just gather...