issues
search
allenai
/
reward-bench
RewardBench: the first evaluation tool for reward models.
https://huggingface.co/spaces/allenai/reward-bench
Apache License 2.0
375
stars
47
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
Fix chat template issues
#46
natolambert
closed
7 months ago
0
Train rm
#45
jacob-morrison
closed
7 months ago
0
deleted some nits and initialized a variable
#44
ValentinaPy
closed
7 months ago
0
dpo nits
#43
ValentinaPy
closed
7 months ago
1
fixes!
#42
natolambert
closed
7 months ago
0
Set default chat template to None
#41
natolambert
closed
7 months ago
1
Actual fix + DPO Ref Free
#40
natolambert
closed
7 months ago
0
small dpo fixes
#39
natolambert
closed
7 months ago
0
WIP: Add experiments on per-token reward
#38
ljvmiranda921
opened
7 months ago
0
Pref Sets updates
#37
natolambert
closed
7 months ago
1
Clean up model loading system
#36
natolambert
closed
7 months ago
0
Truncation of long sequences
#35
natolambert
closed
7 months ago
1
Fix score saving PairRM and SteamSHP
#34
natolambert
closed
7 months ago
2
Add linechart capability for per-token rewards
#33
ljvmiranda921
closed
7 months ago
2
Plot subset distribution across all models
#32
natolambert
closed
7 months ago
0
DPO
#31
ValentinaPy
closed
7 months ago
0
Best of N pipeline + tests
#30
natolambert
closed
7 months ago
0
Per token multiple rms
#29
khyathiraghavi
closed
7 months ago
0
Per token multiple rms
#28
khyathiraghavi
closed
7 months ago
0
visualizing multiple rewards
#27
khyathiraghavi
closed
7 months ago
0
Add model type to results
#26
natolambert
closed
7 months ago
1
Update per token reward
#25
ljvmiranda921
closed
7 months ago
2
Experiment with human vs gpt4 data
#24
natolambert
opened
7 months ago
1
Clean repo
#23
natolambert
closed
7 months ago
0
Improve per-token reward tool
#22
natolambert
closed
7 months ago
0
Save scores per prompt
#21
natolambert
closed
7 months ago
0
Change data storage location
#20
natolambert
closed
7 months ago
1
Docker eval into my training pr
#19
jacob-morrison
closed
7 months ago
0
Add docker image and script for submitting eval jobs
#18
jacob-morrison
closed
7 months ago
0
Add function to get subtoken statistics
#17
ljvmiranda921
closed
7 months ago
3
Add function to get subtoken statistics
#16
ljvmiranda921
closed
7 months ago
3
Fix code formatting
#15
ljvmiranda921
closed
7 months ago
1
Fix table loading from viewer updates
#14
ljvmiranda921
closed
7 months ago
0
Beaver fix; working towards another model
#13
natolambert
closed
7 months ago
4
Add Beaver model from PKU-Alignment
#12
natolambert
closed
7 months ago
0
Best of N benchmark
#11
natolambert
closed
1 month ago
2
Add markdown / LaTeX tables
#10
ljvmiranda921
closed
8 months ago
2
Print per-token reward over an RM
#9
natolambert
closed
8 months ago
1
Fix test failing on main
#8
natolambert
closed
8 months ago
0
Updates histogram + prints table
#7
natolambert
closed
8 months ago
0
Add function to draw histograms on the evaluation dataset
#6
ljvmiranda921
closed
8 months ago
6
chore: Make .gitignore more comprehensive
#5
ljvmiranda921
closed
8 months ago
1
Save reward scores for each prompt
#4
natolambert
closed
7 months ago
0
Generative RM
#3
natolambert
closed
6 months ago
0
DATASET TRACKING
#2
natolambert
closed
8 months ago
1
Multiple styles of computing reward with DPO
#1
natolambert
closed
6 months ago
1
Previous