Cyril issues

Repositories
Issues
Comments

Results 3 issues of


                                            Cyril

Any suggestions to handle longer text?

I'm trying to do predictions with the pre-trained model and I keep running into the issue of; ``` Token indices sequence length is longer than the specified maximum sequence length...

Updated TF softmax function for TF 2.0

TF2 changed the softmax cross entropy function, they removed the variable `dim` and recommended to use `axis`.

How to use the unfiltered version with the Python client?

There are instructions on how to run it through the CMD UI, but how do I call the [gpt4all-unfiltered](https://the-eye.eu/public/AI/models/nomic-ai/gpt4all/gpt4all-lora-unfiltered-quantized.bin) model with the Python interface?