Derek Zhang

Here is the minimum code I tried: ```python from fastapi import FastAPI, Request, Response, Query from transformers import pipeline import deepspeed, torch, os, uvicorn app = FastAPI() local_rank = int(os.getenv('LOCAL_RANK',...

Any updates on this?

I have the similar problem. I am not familiar with MacOS development, but the following thoughts may help you: 1. Enable App nap and listen to system event described. The...

Tried to resolve the conflicts but it seems that you have changed the structure a lot. Any suggestion on how to merge?

I eventually wrote my own script on multi-label classification task. Basically using customized BCE with weights to deal with imbalanced classes and macro-F1 for metrics, as well as AdamW with...

@pablonieto0981 Thanks for the input. I am new to this repo. As of an quick glance of the code, it seems that the code for text generation can be replaced...

@pablonieto0981 thanks for the reply. Do you have the snippet for your `be_creative_with_perturbation` function? BTW I ended up using prompt based method as it is much faster but less controllable.

Hi @dyfcalid , I used your weights and the size is mismatched: ```python Exception has occurred: RuntimeError Error(s) in loading state_dict for PersFormer: size mismatch for laneatt_head.attention_layer.weight: copying a param...

That might be a good idea:) > On Mar 25, 2018, at 6:35 AM, mkolomeychenko wrote: > > What if we push working docker image to the Docker Hub and...

@luke0x I pretty much fixed it on my last pull request. Since @sbonami provided me the admin rights, I haven't had a chance to get out of my daily work...