issues
search
mindspore-lab
/
mindrlhf
Apache License 2.0
26
stars
12
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
inputs shape problem during make_experience for llama,pangu, baichuan
#42
kfertakis
opened
10 months ago
0
origin_inputs size problem for llama,pangu,baichuan models
#41
kfertakis
opened
10 months ago
0
Problem running gpt2 model
#40
kfertakis
closed
10 months ago
1
add basemodel and llama2
#39
ChessQian
closed
10 months ago
0
Can not run training with the latest update.
#38
zhz44
closed
10 months ago
1
change pipeline context
#37
ChessQian
closed
10 months ago
0
fix bug when dp greater than 1
#36
KerryKou
closed
10 months ago
2
update docs of reward model and rlhf dataset
#35
KerryKou
closed
11 months ago
0
update with pretrain_ids and loss_mask
#34
KerryKou
closed
11 months ago
1
Add GPT2 to mindrlhf
#33
MashiroChen
closed
11 months ago
1
Support for gpt2
#32
kfertakis
closed
10 months ago
1
fixed training dataset columns projection to match tldr dataset
#31
kfertakis
closed
10 months ago
1
Training dataset schema issue
#30
kfertakis
closed
10 months ago
2
update readme
#29
ChessQian
closed
11 months ago
0
update readme
#28
ChessQian
closed
11 months ago
0
add baichuan2 and code format
#27
ChessQian
closed
11 months ago
0
Revert "add baichuan2 and format code"
#26
ChessQian
closed
11 months ago
0
add baichuan2 and format code
#25
ChessQian
closed
11 months ago
0
using autopep8 format code
#24
ChessQian
closed
11 months ago
0
Dataset issue.
#23
zhz44
closed
11 months ago
1
code clean and add baichuan2
#22
ChessQian
closed
11 months ago
0
Circular import error
#21
kfertakis
closed
11 months ago
2
add args and add init funcs
#20
ChessQian
closed
11 months ago
0
0.3.0 mindrlhf
#19
ChessQian
closed
11 months ago
0
add rlhf_train_tutorial folder and rlhf data preprocess script
#18
KerryKou
closed
12 months ago
1
process cvalues_comparison dataset
#17
okbaguo
closed
12 months ago
0
process cvalues_comparison dataset
#16
okbaguo
closed
1 year ago
1
0.2.0 add critic model
#15
ChessQian
closed
1 year ago
0
0.2.0 mindrlhf
#14
ChessQian
closed
1 year ago
0
add reward model infer and evaluate script
#13
KerryKou
closed
1 year ago
0
fixed import typo error on getTLDRMR.py
#12
kfertakis
closed
1 year ago
0
fix some default path
#11
ChessQian
closed
1 year ago
0
fix version in readme and add reward model in examples
#10
ChessQian
closed
1 year ago
0
fix readme and ppo_trainer
#9
ChessQian
closed
1 year ago
0
Update ppo_trainer.py
#8
ChessQian
closed
1 year ago
0
Update README_CN.md
#7
ChessQian
closed
1 year ago
1
add framework
#6
ChessQian
closed
1 year ago
0
add rlhf
#5
ChessQian
closed
1 year ago
1
add readme
#4
ChessQian
closed
1 year ago
1
add readme
#3
ChessQian
closed
1 year ago
1
add readme
#2
ChessQian
closed
1 year ago
0
readme
#1
ChessQian
closed
1 year ago
1
Previous