jbaron34 comments

Results 4 comments of


                                            jbaron34

Error creating pre-trained FluxPipeline with diffusers "Cannot instantiate this tokenizer from a slow version"

I have the same issue, tried both `pip install sentencepiece` and `pip install transformers[sentencepiece]` and no change.

Error creating pre-trained FluxPipeline with diffusers "Cannot instantiate this tokenizer from a slow version"

That gives me the same error. In fact the way I have been trying to do it is: ``` from diffusers import FluxPipeline, AutoencoderKL from diffusers.image_processor import VaeImageProcessor from transformers...

Error creating pre-trained FluxPipeline with diffusers "Cannot instantiate this tokenizer from a slow version"

My issue turned out to be the way I was running jupyter in a virtualenv. Thanks for your help

How do you make Transformer generate tokens in parallel?

> The parallel decoding is done by feeding next-scale queries (e.g., 4x4=16) to the transformer decoder and getting 16 predicted token distributions simultaneously. Are the 16 tokens predicted independently or...