jondurbin
/

mpt-30b-qlora-compatible

Text Generation

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

Resources

View closed (0)

Issue trying to tune using the fork of qlora, KeyError: 'response' ?

#2 opened over 1 year ago by

num_train_epochs = 3 but save_steps = 250?

#1 opened over 1 year ago by