instruct fine tuning setup
This commit is contained in:
@@ -155,7 +155,7 @@ class UnslothDDPOConfig(DDPOConfig):
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
exp_name = 'train',
|
||||
exp_name = 'inference',
|
||||
run_name = '',
|
||||
seed = 3407,
|
||||
log_with = None,
|
||||
|
||||
Reference in New Issue
Block a user