Resources

View closed (13)

Adding `safetensors` variant of this model

#29 opened 8 months ago by

SFconvertbot

Response

#20 opened about 1 year ago by

lalit34

How to use all gpu?

#19 opened about 1 year ago by

fuliu2023

How to only get the model answer as output

#18 opened about 1 year ago by

ibrim

Why inference is very slow?

#17 opened over 1 year ago by

hanswang73

mosaicml/mpt-30b-chat on sagemaker ml.p3.8xlarge

#16 opened over 1 year ago by

markdoucette

How to Finetune mpt-30b-chat?

#15 opened over 1 year ago by

nandakishorej8

Decreased performance with recent updated model?

#14 opened over 1 year ago by

Roy-Shih

The model keeps generating up to the maximum length but no EOS token.

#13 opened over 1 year ago by

xianf

could yo provide a prompt template

#11 opened over 1 year ago by

enzii

DIfferent results here in the chat and locally

#10 opened over 1 year ago by

KarBik

how to load the model with multiple GPUs

#9 opened over 1 year ago by

Sven00

How many GPUs for this model to run this fast?

#8 opened over 1 year ago by

edureisMD

The model is extremelly slow in 4bit, is my code for loading ok?

#7 opened over 1 year ago by

zokica

How to run on Colab's CPU?

#4 opened over 1 year ago by

deepakkaura26

Sagemaker endpoint inference script help?

#3 opened over 1 year ago by

varuntejay