Hyperparameters training setting
#10 opened 11 months ago
by
hyuk199
synthetic-instruct-gptj-pairwise pairwise data how to pre-process for train data
2
#9 opened 11 months ago
by
chaochaoli
How to fine tune this model with the Trainer API?
1
#8 opened about 1 year ago
by
duzm
How to score a <instruction, input, output> pair?
#7 opened about 1 year ago
by
qldu
Validation split indices?
1
#6 opened over 1 year ago
by
cmglaze
np.int deprecation issue
#5 opened over 1 year ago
by
whiteg671
Question about evaluating this reward model on Anthropic/hh-rlhf
1
#4 opened over 1 year ago
by
songff
Adding `safetensors` variant of this model
#3 opened over 1 year ago
by
SFconvertbot
How to optimize loss function?
1
#1 opened almost 2 years ago
by
nidong